FAQ – Hume Health

{ "type": "slideout", "content": { "title": "45-Metric List", "content": "\u003cp\u003e\u003cstrong\u003eCore totals (20)\u003c\/strong\u003e\u003c\/p\u003e\u003col\u003e\u003cli\u003eWeight\u003c\/li\u003e\u003cli\u003eBMI\u003c\/li\u003e\u003cli\u003eBody Fat Rate (aka body fat %)\u003c\/li\u003e\u003cli\u003eBody Fat Percentage\u003c\/li\u003e\u003cli\u003eFat Mass\u003c\/li\u003e\u003cli\u003eMuscle Mass\u003c\/li\u003e\u003cli\u003eSkeletal Muscle Mass\u003c\/li\u003e\u003cli\u003eMuscle vs Fat Ratio\u003c\/li\u003e\u003cli\u003eVisceral Fat\u003c\/li\u003e\u003cli\u003eMetabolic Age\u003c\/li\u003e\u003cli\u003eBasal Metabolic Rate (BMR)\u003c\/li\u003e\u003cli\u003eHydration (status\/level)\u003c\/li\u003e\u003cli\u003eWater Weight\u003c\/li\u003e\u003cli\u003eTotal Body Water (TBW)\u003c\/li\u003e\u003cli\u003eIntracellular Water (ICW)\u003c\/li\u003e\u003cli\u003eExtracellular Water (ECW)\u003c\/li\u003e\u003cli\u003eProtein Levels\u003c\/li\u003e\u003cli\u003eBone mineral content \/ “bone” metric (often marketed as bone density)\u003c\/li\u003e\u003cli\u003eHeart health \u003c\/li\u003e\u003cli\u003eFull-body segmental scan coverage (arms\/torso\/legs)\u003cbr\/\u003e\u003c\/li\u003e\u003c\/ol\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eSegmental fat % (5)\u003c\/strong\u003e\u003c\/p\u003e\u003col\u003e\u003cli\u003eRight Arm Fat %\u003c\/li\u003e\u003cli\u003eLeft Arm Fat %\u003c\/li\u003e\u003cli\u003eTrunk Fat %\u003c\/li\u003e\u003cli\u003eRight Leg Fat %\u003c\/li\u003e\u003cli\u003eLeft Leg Fat %\u003cbr\/\u003e\u003c\/li\u003e\u003c\/ol\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eSegmental muscle\/lean outputs (5)\u003cbr\/\u003e\u003c\/strong\u003e\u003c\/p\u003e\u003col\u003e\u003cli\u003eRight Arm Muscle\/Lean (segmental)\u003c\/li\u003e\u003cli\u003eLeft Arm Muscle\/Lean (segmental)\u003c\/li\u003e\u003cli\u003eTrunk Muscle\/Lean (segmental)\u003c\/li\u003e\u003cli\u003eRight Leg Muscle\/Lean (segmental)\u003c\/li\u003e\u003cli\u003eLeft Leg Muscle\/Lean (segmental)\u003c\/li\u003e\u003c\/ol\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eSegmental muscle\/water balance ratings (5)\u003cbr\/\u003e\u003c\/strong\u003e\u003c\/p\u003e\u003col\u003e\u003cli\u003eRight Arm Muscle\/Water Balance %\u003c\/li\u003e\u003cli\u003eLeft Arm Muscle\/Water Balance %\u003c\/li\u003e\u003cli\u003eTorso Muscle\/Water Balance %\u003c\/li\u003e\u003cli\u003eRight Leg Muscle\/Water Balance %\u003c\/li\u003e\u003cli\u003eLeft Leg Muscle\/Water Balance %\u003c\/li\u003e\u003c\/ol\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eSegmental intracellular-water health (5)\u003cbr\/\u003e\u003c\/strong\u003e\u003c\/p\u003e\u003col\u003e\u003cli\u003eRight Arm ICW health (segmental)\u003c\/li\u003e\u003cli\u003eLeft Arm ICW health (segmental)\u003c\/li\u003e\u003cli\u003eTorso ICW health (segmental)\u003c\/li\u003e\u003cli\u003eRight Leg ICW health (segmental)\u003c\/li\u003e\u003cli\u003eLeft Leg ICW health (segmental)\u003c\/li\u003e\u003c\/ol\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eScoring + insights shown in creative (5)\u003cbr\/\u003e\u003c\/strong\u003e\u003c\/p\u003e\u003col\u003e\u003cli\u003eOverall Health Score\u003c\/li\u003e\u003cli\u003eBody Composition Grade\u003c\/li\u003e\u003cli\u003eActivity Grade\u003c\/li\u003e\u003cli\u003eSleep Grade\u003c\/li\u003e\u003cli\u003eRight-vs-left limb difference flag (lean\/muscle asymmetry callout)\u003cbr\/\u003e\u003c\/li\u003e\u003c\/ol\u003e" }, "width": 750, "transitionDuration": 150 }

{ "type": "slideout", "content": { "title": "11-modal", "content": "\u003ch4\u003eLean Mass Preservation During GLP‑1-Assisted Weight Loss in Engaged Digital Health Program Participants\u003c\/h4\u003e\n\u003cp\u003e\u003ci\u003eAn Outcomes Analysis of 6,990 Hume Health Premium Members\n \u003c\/i\u003e\u003c\/p\u003e\n\u003cp\u003eHume Health Corp • Internal Outcomes Analysis • 2024\n Correspondence: research@humehealth.com • Methodology available on request\n\u003c\/p\u003e\n\u003ch4\u003eABSTRACT\u003c\/h4\u003e\n\u003cp\u003e\u003cb\u003eBackground.\u003c\/b\u003e GLP‑1 receptor agonists produce substantial weight loss but are associated with lean mass loss of\n 25–39%\n of total weight lost in published clinical trials. Lean mass is a primary determinant of resting metabolic rate, and\n its loss during weight reduction is associated with impaired weight maintenance following treatment cessation. This\n analysis examined lean mass outcomes in a real-world cohort of Hume Health premium platform members who met defined\n engagement criteria.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eMethods.\u003c\/b\u003e Retrospective analysis of 6,990 Hume Health premium members on GLP‑1 therapy who completed a minimum\n of\n three body composition measurements per week via the Hume Body (8-sensor bioelectrical impedance analysis) and made\n weekly attestations of adherence to Pro.f AI protocol guidance. Body composition was measured at each weigh-in. The\n primary outcome was lean mass loss as a percentage of total weight lost, assessed from highest recorded weight (peak)\n to lowest recorded weight (nadir). Weighted mean lean mass loss was computed as the ratio of aggregate lean mass\n change to aggregate total weight lost across the full cohort.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eResults.\u003c\/b\u003e Mean baseline weight was 105.3 kg (SD 21.8). Mean total weight lost was 21.9 kg (SD 6.8),\n representing 21.3%\n of baseline body weight. The weighted mean lean mass loss as a percentage of total weight lost was 16.9%. The median\n lean mass loss as a percentage of total weight lost was 19.4%. A total of 12.7% of members preserved or increased lean\n mass over the measurement period. Among the 87.3% of members who lost lean mass, mean lean mass loss as a percentage\n of total weight lost was 22.0%.\n\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e\n Conclusions. \u003c\/b\u003e Hume Health premium members on GLP‑1 therapy demonstrated lean mass loss substantially below the\n 25–39%\n range documented in published clinical trials. These results are consistent with the hypothesis that\n high-frequency\n body composition monitoring combined with AI-guided protocol adherence supports favorable body composition\n outcomes\n during medically assisted weight loss.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eKeywords:\u003c\/b\u003e \u003ci\u003eGLP‑1 receptor agonists; lean mass preservation; body composition; semaglutide; weight loss;\n bioelectrical impedance analysis; digital health\u003c\/i\u003e\u003c\/p\u003e\n \n\u003ch4\u003e1. INTRODUCTION\u003c\/h4\u003e\n\u003cp\u003eGlucagon-like peptide-1 (GLP‑1) receptor agonists represent a substantial advance in pharmacological obesity\n management. In the STEP 1 clinical trial, once-weekly subcutaneous semaglutide 2.4 mg produced mean total body weight\n loss of 14.9% over 68 weeks, compared to 2.4% in the placebo group receiving lifestyle intervention alone —\n approximately 6.2 times greater weight loss than lifestyle intervention alone.¹\u003c\/p\u003e\n\u003cp\u003eHowever, a consistent finding across GLP‑1 clinical trials is that a meaningful proportion of weight lost derives\n from lean tissue rather than adipose tissue. Neeland et al. documented lean mass reductions of 40–60% of total weight\n lost in some GLP‑1 trial cohorts, with substantial heterogeneity across studies.² Prado et al., in a commentary in The\n Lancet Diabetes \u0026 Endocrinology, reported lean mass loss of 25–39% of total weight lost across medically induced\n weight loss programs.³\u003c\/p\u003e\n\u003cp\u003eThis is clinically significant because skeletal muscle mass is a primary determinant of resting metabolic rate (RMR)\n — the baseline energy expenditure that determines whether a patient can sustain their new body weight after treatment\n ends.⁶ In the STEP 1 extension trial, participants who discontinued semaglutide without a structured metabolic exit\n protocol regained two-thirds of their prior weight loss within one year of stopping treatment.⁴\u003c\/p\u003e\n\u003cp\u003eThe Hume Health platform combines GLP‑1 therapy with high-frequency body composition measurement via bioelectrical\n impedance analysis (BIA), physician oversight informed by longitudinal tissue-level data, and an AI guidance system\n (Pro.f) that surfaces body composition patterns for clinical review and member adherence. This analysis examines\n whether this protocol-supported approach is associated with lean mass outcomes below published benchmarks.\n\u003c\/p\u003e\n \n\u003ch4\u003e2. METHODS\n\u003c\/h4\u003e\n\u003cp\u003e\u003cb\u003e2.1 Study Design\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThis was a retrospective cohort analysis of real-world member data from the Hume Health platform. The analysis period\n spanned active program enrollment through March 2026. The study was conducted under Hume Health Corp internal data\n governance protocols. Member data were de-identified prior to analysis. The study did not constitute human subjects\n research requiring institutional review board oversight under 45 CFR 46 as it involved retrospective analysis of\n de-identified operational data.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e2.2 Participants\n \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eEligible participants were Hume Health premium members who: (1) were actively enrolled in a GLP‑1 therapy program\n during the analysis period; (2) completed a minimum of three Hume Body body composition measurements per week\n throughout the measurement window; and (3) completed weekly attestations confirming engagement with and adherence to\n Pro.f AI protocol guidance. Members who did not meet all three criteria were excluded from analysis.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e2.3 Measurements\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eBody weight and body composition were measured at each weigh-in using the Hume , a bioelectrical impedance analysis\n device measuring whole-body and segmental lean mass, fat mass, and total body water. BIA measurements were recorded at\n consistent times relative to weigh-in. Lean mass at peak weight (highest recorded body weight during the measurement\n window) and lean mass at nadir weight (lowest recorded body weight) were identified for each member. Lean mass delta\n was computed as lean mass at nadir minus lean mass at peak. Weight loss was computed as peak weight minus nadir\n weight.\n\u003c\/p\u003e\n\u003cp\u003eLean mass loss as a percentage of total weight lost was computed for each member as: (|lean mass delta| \/ weight\n loss) × 100, where lean mass delta was negative for members who lost lean mass and positive for members who preserved\n or gained lean mass. The primary aggregate outcome — weighted mean lean mass loss as a percentage of total weight lost\n — was computed as: (sum of lean mass deltas across all members \/ sum of total weight lost across all members) × 100,\n reflecting the population-level ratio of lean mass change to total weight change.\n\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e2.4 Statistical Analysis\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eDescriptive statistics were computed for all primary and secondary outcomes. Continuous variables are reported as\n mean (standard deviation) and median. The weighted mean was used as the primary outcome measure for lean mass loss as\n a percentage of total weight lost, as it accounts for variation in total weight lost across members and reflects the\n aggregate population-level body composition response. Members who preserved or gained lean mass during the measurement\n period (lean mass delta ≥ 0) are included in all analyses; their inclusion in the weighted mean computation reduces\n the aggregate lean mass loss percentage relative to analyses restricted to members with lean mass loss.\u003c\/p\u003e\n\u003ch4\u003e3. RESULTS\u003c\/h4\u003e\n\u003cp\u003e\u003cb\u003e3.1 Participant Characteristics\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eA total of 6,990 members met all eligibility criteria and were included in the analysis. Baseline characteristics are\n presented in Table 1.\u003c\/p\u003e\n \n\u003cdiv class=\"table_drawer\"\u003e\n \u003cp\u003eTable 1. Baseline Participant Characteristics (n = 6,990)\u003c\/p\u003e\n \u003ctable border=\"1\"\u003e\n \u003ctr\u003e\n \u003cth\u003eCharacteristic\u003c\/th\u003e\n \u003cth\u003eValue\u003c\/th\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eSample size (n)\u003c\/td\u003e\n \u003ctd\u003e6,990\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMean baseline weight, kg (SD)\u003c\/td\u003e\n \u003ctd\u003e105.3 (21.8)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMedian baseline weight, kg\u003c\/td\u003e\n \u003ctd\u003e102.3\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMeasurement frequency (minimum)\u003c\/td\u003e\n \u003ctd\u003e3 weigh-ins per week\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eProof engagement attestation\u003c\/td\u003e\n \u003ctd\u003eWeekly (required for inclusion)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003c\/table\u003e\n\u003c\/div\u003e\n \n\u003cp\u003e\u003cb\u003e3.2 Weight Loss Outcomes\n \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eMean total weight lost was 21.9 kg (SD 6.8), representing a mean reduction of 21.3% (SD 6.7%) of baseline body\n weight. Median weight lost was 19.6 kg, representing 20.0% of baseline body weight. Weight loss outcomes are presented\n in Table 2.\u003c\/p\u003e\n \n\u003cp\u003eTable 2. Weight Loss Outcomes\u003c\/pp\u003e\n\u003cdiv class=\"table_drawer2\"\u003e\n \u003ctable border=\"1\"\u003e\n \u003ctr\u003e\n \u003cth\u003eOutcome\u003c\/th\u003e\n \u003cth\u003eResult\u003c\/th\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMean weight loss, kg (SD)\u003c\/td\u003e\n \u003ctd\u003e21.9 (6.8)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMedian weight loss, kg\u003c\/td\u003e\n \u003ctd\u003e19.6\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMean weight loss, % of baseline (SD)\u003c\/td\u003e\n \u003ctd\u003e21.3% (6.7%)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMedian weight loss, % of baseline\u003c\/td\u003e\n \u003ctd\u003e20.0%\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMinimum weight loss, kg\u003c\/td\u003e\n \u003ctd\u003e15.7\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMaximum weight loss, kg\u003c\/td\u003e\n \u003ctd\u003e75.4\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003c\/table\u003e\n\u003c\/div\u003e\n\u003cp\u003e\u003cb\u003e3.3 Lean Mass Outcomes\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThe weighted mean lean mass loss as a percentage of total weight lost was 16.9% across all 6,990 members. The median\n lean mass loss as a percentage of total weight lost was 19.4%. A total of 890 members (12.7%) preserved or increased\n lean mass over the measurement period (lean mass delta ≥ 0). Among the 6,100 members (87.3%) who lost lean mass, the\n mean lean mass loss as a percentage of total weight lost was 22.0%. Lean mass outcomes are presented in Table 3.\u003c\/p\u003e\n \n\u003cp\u003eTable 3. Lean Mass Outcomes\u003c\/p\u003e\n\u003cdiv class=\"table_drawer3\"\u003e\n \u003ctable border=\"1\"\u003e\n \u003ctr\u003e\n \u003cth\u003eOutcome\u003c\/th\u003e\n \u003cth\u003eResult\u003c\/th\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eWeighted mean lean mass loss, % of total weight lost (all members)\u003c\/td\u003e\n \u003ctd\u003e16.9%\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMedian lean mass loss, % of total weight lost (all members)\u003c\/td\u003e\n \u003ctd\u003e19.4%\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMembers preserving or gaining lean mass, n (%)\u003c\/td\u003e\n \u003ctd\u003e890 (12.7%)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMembers losing lean mass, n (%)\u003c\/td\u003e\n \u003ctd\u003e6,100 (87.3%)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003eMean lean mass loss, % of total weight lost (among those with lean mass loss)\u003c\/td\u003e\n \u003ctd\u003e22.0%\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003ePublished benchmark (Prado et al., 2024; Neeland et al., 2024)\u003c\/td\u003e\n \u003ctd\u003e25–39% (range across GLP-1 trials)\u003c\/td\u003e\n \u003c\/tr\u003e\n \u003c\/table\u003e\n\u003c\/div\u003e\n \n\u003cp\u003e\u003cb\u003e3.4 Interpretation of the Weighted Mean Outcome\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThe weighted mean of 16.9% reflects the aggregate population-level ratio of total lean mass change to total weight\n lost across all members. Because members who preserved or gained lean mass (12.7% of the cohort) contribute negative\n lean mass loss values to the numerator, the weighted mean is lower than the mean computed among members who lost lean\n mass exclusively (22.0%). Both measures are reported to provide transparency regarding cohort composition. The\n weighted mean is the primary outcome because it most accurately represents the population-level body composition\n impact of the program.\u003c\/p\u003e\n\u003ch4\u003e4. DISCUSSION\n\u003c\/h4\u003e\n\u003cp\u003eThis analysis demonstrates that Hume Health premium members on GLP‑1 therapy, who met defined body composition\n monitoring and AI protocol engagement criteria, experienced lean mass loss substantially below the benchmarks\n documented in published GLP‑1 clinical trials. The weighted mean lean mass loss of 16.9% of total weight lost compares\n favorably to the 25–39% range reported by Prado et al.³ and the 40–60% upper range reported in some cohorts by Neeland\n et al.²\n\u003c\/p\u003e\n\u003cp\u003eThe mechanism by which frequent body composition measurement and protocol-guided engagement may attenuate lean mass\n loss is consistent with established physiology. Skeletal muscle mass is the primary determinant of resting metabolic\n rate.⁶ Interventions that preserve lean mass during caloric restriction — including higher protein intake, resistance\n exercise, and dose calibration timed to body composition response — are documented to reduce lean mass loss during\n weight reduction. The Hume platform protocol facilitates tissue-level visibility that enables these calibrations in\n near real-time; the present analysis cannot isolate which components of the program contributed to the observed\n outcomes.\n\u003c\/p\u003e\n\u003cp\u003eThe finding that 12.7% of members preserved or gained lean mass during GLP‑1-assisted weight loss is notable. This\n subgroup is likely influenced by favorable baseline characteristics, behavioral factors, and variability in BIA\n measurement across conditions, and should not be interpreted as a program-level guarantee of lean mass preservation.\n Its inclusion in the weighted mean reduces the reported aggregate lean mass loss figure relative to analyses\n restricted to members who lost lean mass.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e4.1 Limitations\n \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThis analysis has several limitations that should be considered when interpreting results. First, the study is\n retrospective and observational, without a concurrent control group. Comparison to published clinical trial benchmarks\n involves differences in population, measurement methodology, and GLP‑1 agent. Second, body composition was measured\n via bioelectrical impedance analysis rather than dual-energy X-ray absorptiometry (DXA) or magnetic resonance imaging\n (MRI), which are considered the reference standards for lean mass quantification. BIA measurements are sensitive to\n hydration status, time of measurement, and device calibration, and may produce systematic differences relative to\n DXA-derived lean mass values. Third, the cohort consists of premium-tier members who met a minimum engagement\n threshold; results may not generalize to members with lower engagement frequency or to non-engaged GLP‑1 users.\n Fourth, no information on dietary protein intake, resistance exercise participation, or specific GLP‑1 agent and\n dosing schedule was incorporated into this analysis, and these variables are likely to influence lean mass outcomes.\n Fifth, the duration of the measurement window varied across members and was determined by the interval between peak\n and nadir weight rather than a fixed protocol period.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e4.2 Future Directions\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eProspective controlled study designs with standardized measurement protocols, dietary and exercise co-variate\n capture, and DXA-validated BIA calibration would provide stronger evidence for the role of high-frequency monitoring\n and AI-guided adherence in lean mass preservation during GLP‑1 therapy. Subgroup analyses examining the impact of\n engagement frequency, protein intake, resistance training participation, and GLP‑1 agent on lean mass outcomes would\n further characterize the mechanisms underlying these findings.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003e5. CONCLUSIONS\u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eAmong 6,990 Hume Health premium members on GLP‑1 therapy who met defined body composition monitoring and AI protocol\n engagement criteria, the weighted mean lean mass loss as a percentage of total weight lost was 16.9%. This is\n substantially below the 25–39% range reported in published GLP‑1 clinical trial literature. The median lean mass loss\n was 19.4%. These findings are consistent with the hypothesis that high-frequency tissue-level monitoring, combined\n with AI-guided protocol adherence and physician oversight informed by body composition data, supports favorable lean\n mass outcomes during medically assisted weight loss. Prospective controlled research is needed to confirm these\n findings and to isolate the active components of the platform protocol.\n\u003c\/p\u003e\n \n\u003ch4\u003eREFERENCES\u003c\/h4\u003e\n \n\u003cp\u003e1. Wilding JPH, Batterham RL, Calanna S, et al. Once-Weekly Semaglutide in Adults with Overweight or Obesity. N Engl\n J Med. 2021;384(11):989–1002. doi:10.1056\/NEJMoa2032183.\u003c\/p\u003e\n\u003cp\u003e2. Neeland IJ, Linge J, Birkenfeld AL. Changes in lean body mass with glucagon-like peptide-1-based therapies and\n mitigation strategies. Diabetes Obes Metab. 2024;26(Suppl 4):16–27. doi:10.1111\/dom.15728.\u003c\/p\u003e\n\u003cp\u003e3. Prado CM, Phillips SM, Gonzalez MC, Heymsfield SB. Muscle matters: the effects of medically induced weight loss on\n skeletal muscle. Lancet Diabetes Endocrinol. 2024;12(11):785–787. doi:10.1016\/S2213-8587(24)00272-9.\u003c\/p\u003e\n\u003cp\u003e4. Wilding JPH, Batterham RL, Davies M, et al. Weight regain and cardiometabolic effects after withdrawal of\n semaglutide: The STEP 1 trial extension. Diabetes Obes Metab. 2022;24(8):1553–1564. doi:10.1111\/dom.14725.\u003c\/p\u003e\n\u003cp\u003e5. Hume Health Corp. Lean Mass Preservation in GLP‑1 Members: An Internal Outcomes Analysis. 2024. Analysis of 6,990\n premium members. Methodology available on request: research@humehealth.com.\n\u003c\/p\u003e\n\u003cp\u003e6. Ravussin E, Bogardus C. Skeletal muscle metabolism is a major determinant of resting energy expenditure. J Appl\n Physiol. 1989;66(3). PMID:2243122.\n\u003c\/p\u003e\n \n\u003cp\u003e\u003cb\u003eDisclosure Statement\n \u003c\/b\u003e\u003c\/p\u003e\n\u003cp\u003eThis analysis was conducted by Hume Health Corp using data from the Hume Health platform. Hume Health Corp is the\n developer of the body composition monitoring hardware (Hume Body Pod) and AI guidance system (Pro.f) evaluated in this\n analysis. No external funding was received. The analysis has not undergone independent peer review. Investigators have\n an inherent commercial interest in the outcomes described.\u003c\/p\u003e" }, "width": 750, "transitionDuration": 150 }

Frequently Asked Questions

Getting Started

Troubleshooting

Hume Help Videos

Hume Health

Hume Plus Subscription

Health Score

Nutrition

Plans

Data Privacy and Security

FSA

Study

What app do I need to use with my scale to access my full body measurements?

To weigh-in and access your body measurements, download the Hume Health app on your device.

How do I download the Hume Health app?

You can download the Hume Health app from the App Store or the Google Play Store, or by clicking on the following links:

Download for Android

Download for IOS

How do I register for the Hume Health app?

Follow these steps to create an account:

Download the Hume Health App.
Tap on Sign Up.
Enter a valid, unique email address.
Create a password with at least:
- 10 characters
- 1 uppercase letter
- 1 lowercase letter
- 1 number
- 1 symbol
Verify your email using the 4-digit code sent to you.
Input the code, and your account is ready!

Using your HumePod for the first time

After pairing your scale, follow these steps for an accurate measurement:

Place your scale on a flat, hard surface (avoid carpeted areas).
Ensure Bluetooth is enabled on your phone.
Open the Hume Health App
Step onto the scale with bare feet (no socks)
Hold the HumePod handles with both hands above waist level, keeping your thumbs on the sensors (but not touching each other) and your elbows away from your sides. Stand upright and face forward.
Wait until the Hume Health App confirms your weigh-in is complete before stepping off.

For the most accurate results, make sure you're in a stable position throughout the process.

Checklist:

Uncarpeted, flat surface
Standing upright, barefoot
Holding the handles steady above waist height
Wait for your Hume Health app to notify that your weigh in is complete

How to get the best results

For the most accurate weigh-in, step on the scale first thing in the morning after drinking a glass of water. Weighing yourself at the same time each day helps provide a clearer picture of your progress and patterns over time.

Do I need to pay for the app subscription to use my scale?

No! A Premium subscription is not required to use your scale. You can still enjoy the Hume Health app for free and access essential features like weighing-in and viewing body measurements.

However, certain advanced features are reserved for Premium (Hume Plus) users, including:

A comprehensive weekly Health Report that examines:
- Body Composition
- Activity
- Sleep
Personalized health insights & recommendations to achieve your goals
And so much more!

Can multiple people use one HumePod?

Yes! The HumePod can connect to multiple accounts. Each user should log in with their own Hume Account for accurate tracking.

Like all Bluetooth devices, the HumePod can only connect to one phone at a time. To weigh in, simply open your Hume Health App and step on the scale. However, if another paired user is nearby with their app open, they may need to close their app to free up the HumePod’s connection for you.

How do I hold the handle?

Hold the HumePod handles with both hands above waist level, keeping your thumbs on the sensors (but not touching each other) and your elbows away from your sides. Stand upright and face forward.

My scale isn’t turning on

Please charge your scale for at least 2 hours using the provided charging cable.

If it still doesn’t turn on, our Customer Support team is happy to help! Just reach out, and if possible, have a quick video recording ready so we can assist you faster.

My scale isn’t keeping a charge - What can I do?

If your scale isn’t holding a charge, try leaving it plugged in overnight using the provided charging cable.

If the issue persists, please contact Customer Support, and we’ll be happy to assist you! Sharing a short video of the issue can help us troubleshoot more quickly.

My Scale Isn’t Being Discovered – What Should I Do?

If you’re having trouble finding your HumePod when searching, try these steps:

Check the Bluetooth icon on your scale’s screen:

Flashing but not discovered? Reach out to our Customer Support team—we’re happy to help!
Solid? This means the scale is already paired with another device. Simply factory reset it by using the reset button underneath the scale. Then, wake the scale, check that the Bluetooth icon is flashing, and try searching again.

Need to Factory Reset?

Pull the handles, and you’ll see a tiny hole on the scale. Insert a pin into the hole and press to reset the device.

I’ve weighed in before, why is the Bluetooth Icon Flashing?

A flashing Bluetooth icon means your scale isn’t connected. Here’s how to fix it:

Check your phone’s Bluetooth settings – Make sure Bluetooth is turned ON.
Verify the Hume App’s permissions – Bluetooth access may have been turned off. Go to:
Settings > Apps > Hume > Permissions and ensure Bluetooth is enabled.
If Bluetooth and Permissions are ON and the issue persists, then
Reconnect in the Hume App –
- Open the app and go to the Me Page.
- In the Devices Section, search for a new device.
- Make sure your scale is on and flashing by tapping it with your foot to wake it up
Act quickly – The HumePod enters sleep mode to conserve energy. Wake it up and start scanning right away.

These steps should help restore the connection! If you still have trouble, our Customer Support team is happy to help.

I’ve weighed in before, and the bluetooth icon is solid, but my phone doesn’t react!

A solid Bluetooth icon means the scale is already paired with a nearby phone. Here’s how to troubleshoot based on your situation:

Multiple-User Household

If you share your HumePod with someone else, they may have their Hume App open, keeping the connection active. Ask them to close the app, then wait 10 seconds for the scale to sleep and wake it up again—it should then be ready for you.

Single-User Household

Check your connection
- Open the Hume App and go to the Me Page.
- Scroll to the My Devices section.
If your HumePod is NOT listed:
- Factory reset the scale to clear any cached connections.
- How to Factory Reset: Pull the handles to reveal a tiny hole on the scale. Insert a pin and press to reset.
If your HumePod is listed:
- Tap the scale to wake it up. It should switch to connected status.
- If it doesn’t connect, tap "Disconnect" to release the device.
- Then, re-pair the scale by searching for it again in the app.

If you still run into issues, our Customer Support team is happy to assist!

When I weigh-in I receive an error message on my phone

The HumePod has a built-in diagnostics system that displays error codes when it encounters an issue.

Refer to the table below to determine whether the issue is caused by hardware or incorrect usage.

For example, Error 10 occurs when there’s an issue with the electrical impedance detected in the left arm. To fix this, proper positioning and grip are essential.

Please ensure:

Correct posture: Make sure you are standing as outlined in the guidelines. Hands and feet: Make sure hands and feet are not too dry. If this doesn’t work, try wetting your hands and see if it helps with the reading. No socks, gloves, or footwear: The scale requires bare skin to get accurate readings. Correct grip: Hold the left and right handles correctly with your thumbs. If the scale detects incorrect positioning, it might result in the error. Flat, even flooring: Make sure the scale is placed on hard, flat, and even flooring. Avoid using the scale on carpets or uneven surfaces.

TABLE:

If you need further assistance, feel free to reach out to Customer Support!

I’m receiving inaccurate measurements, what can I do?

If your measurements seem inaccurate, try these steps to resolve the issue:

1. Verify Your Profile Information

Make sure your height, age, and gender are correctly entered in the Hume Health app:

Open the Hume Health app.
Tap your profile icon in the bottom right corner.
Select Edit Profile (top right).
Review and confirm your information.

2. Recalibrate Your Scale

If your profile details are correct, your scale may need recalibration:

Check that your scale has power.
Reset the HumePod:
- Locate the small reset button behind the handlebars, near the charging port.
- Use a pin or needle to press and hold it for 5 seconds.
Place the scale on a hard, flat surface (avoid carpets or uneven flooring).
Recalibrate:
- Quickly step on and off the scale.
- The scale should display 0.0 lbs/kg—recalibration is now complete.

3. Ensure Accurate Weigh-Ins

Stay hydrated – Dehydration can affect body composition readings.
Weigh in at a consistent time – The best time for most people is within 30 minutes of waking up before eating, but after drinking a glass of water.
Avoid measuring after exercise – Water shifts in the body can cause fluctuations.
Don’t weigh in back-to-back – Bioelectrical Impedance Analysis (BIA) sends a small electrical current through your body. Taking multiple measurements in a row can temporarily lower resistance, leading to inconsistent readings.

If you're still experiencing issues, please feel free to reach out to Customer Support for further assistance!

The app shows me as a Free user after subscribing. What can I do?

If you've subscribed to Hume Plus but can't access the full features, follow these steps to resolve the issue:

1. Verify Your Subscription in Your Device Settings:

For iOS Users:

Open your phone’s Settings.
Tap your name at the top of the screen.
Select Subscriptions.
Check if the Hume Health app is listed.
- If it’s not listed, the payment has not been processed.

For Android Users:

Open the Google Play app.
Tap your profile icon in the top right.
Select Payments & Subscriptions.
Under Subscriptions, check for expired or declined subscriptions.
Look for the Hume Health app in the list.
- If it’s not listed, the payment has not been processed.

2. Verify Your Subscription on the Hume Health Website:

If you subscribed through the website, follow these steps:

Visit myhumehealth.com.
Click the login icon at the top right.
Log in with the email and password you use for the Hume Health app.
On the left menu, click My Subscriptions.
Check if your Hume Plus subscription is listed.
- If it’s not, the payment has not been processed.

3. Contact Support:

If you’ve followed these steps and still can’t access Hume Plus, please contact our Customer Success Team at support@myhumehealth.com for further assistance.

Can I use the HumePod if I am pregnant?

Absolutely! The HumePod scale is completely safe to use during pregnancy, with no direct interaction or impact on the baby. However, as the pregnancy progresses, the changes in the mother’s body will affect the scale’s readings.

As the baby grows, the added weight will be reflected primarily in the trunk region. For example, by around 8 months, a 9-pound baby might be represented on the scale as an additional 5-6 pounds of muscle and approximately 3 pounds of fat. This is because the scale attributes the baby’s weight to the mother’s body composition.

Additionally, pregnancy-related water retention will likely contribute to an increase in lean tissue readings. Overall, while the HumePod scale remains safe to use, the segmented analysis will show increased weight in the torso area, which includes the baby and other pregnancy-related changes, rather than being entirely reflective of the mother’s own body.

Can I use the HumePod if I have a pacemaker/ ICD/VNS?

Yes! If customers have a Pacemaker or ICD installed after 1992, they can still safely use our Hume Pod.

According to numerous studies there has been no interference found in patients with CIEDs during BIA measurements.

Is there a weight limit?

The scale supports a maximum weight of 400 lbs (181.4 kg). If exceeded, the scale will display an error. The scale has a minimum measure weights of 6.6 lbs (3 kg)

Is there an age limit?

The scale can be used by children or elderly people.

It will always be accurate in terms of tissue weight and percent.

There is less research about benchmarks for children, so the child will be held accountable to the standards of a 19 year old. This may cause them to score ‘standard’ or ‘low’ even though they are ‘high’ for their age.

The user should track the amounts and trends for accuracy.

Understanding Our Scale and Its Measurement of Bone Density and Osteoporosis

Our scale is not an X-ray machine and therefore cannot directly measure bone density, which is the specific aspect that diminishes in osteoporosis. However, our scale can interpret bone mineral content, which is closely related to bone mass. Generally, bone density and bone mineral content are correlated, meaning that a high bone mineral content usually indicates good bone density. It is highly unlikely to have a high bone density with low bone mineral content, and it is impossible to have a high bone mineral content with low bone density.

This correlation gives us a high level of confidence in our scale's ability to provide a reliable bone mass reading.

While the scale cannot diagnose osteoporosis, it can be a useful tool for monitoring changes in bone mass. If someone notices a decline in their bone mass reading, it may be a good idea to consult a healthcare professional. Additionally, individuals who have already been diagnosed with osteoporosis can use the scale to track changes in their bone mass over time or to see the effects of diet and/or medication. It's important to note, however, that once osteoporosis is present, the goal is usually to slow down or halt further bone loss rather than reverse it.

Can I use the HumePod with Cochlear Implants?

Yes! No interference in patients equipped with cochlear implants. BIA can be securely performed in these patients.

Can I use the HumePod if I have Atrial Fibrillation?

Yes, our scale is safe for users with Atrial Fibrillation. Atrial fibrillation is a condition that causes an irregular or rapid heart rate, but our devices do not interact with or affect heart function. You can use the scale without concern, as it poses no risk to those with this condition.

Hume Pod- Troubleshooting & FAQ

Hume Pod- The pairing guide

Your Hume Pod Introduction

What is Digital Twin?

As you continue to use Hume Plus, your Digital Twin begins to establish a baseline for your health. It does this by analyzing over 30 health metrics (via your HumePod), along with any third-party data you choose to integrate from Apple or Google, including activity and sleep data. From there, your Digital Twin tracks and analyzes how your health is trending and what it means, which is shared with you through your Health Score and Insights. Once this baseline is set, your Digital Twin helps you build healthier habits through Milestones and Insights.

Over time, as you continue using Hume Plus, your Digital Twin will become smarter, continually optimizing and offering more personalized Insights to help you achieve your goals.

What are Milestones?

Milestones allow you to set personalized health goals and track your progress over time. They provide a clear, structured way to monitor your journey, keeping you focused and motivated as you work towards better health.

What is a Health Score?

Your Health Score is a measure of your overall health and serves as the foundation for building your Digital Twin—a visual representation of your health. It provides a comprehensive understanding of how well you take care of your body and how your health is trending.

Each week, a new Health Score is generated by weighing in at least once. The more frequently you weigh in, the more personalized your data becomes. Your Health Score fluctuates based on changes in your body composition and daily behaviors.

The Health Score is calculated out of 900 and is based on four essential health pillars:

Body Composition: This score is calculated using data collected from your smart scale.
Activity: This score reflects your activity level, including steps and active minutes tracked by your connected apps.
Nutrition: This score is based on how well you complete weekly challenges related to building healthy nutrition habits.

How can I provide feedback or report any issues with the new app

To provide feedback or report an issue with the your scale or app, please choose from the following options:

Email support@myhumehealth.com.
Contact us through our Instagram page @hume_health or our Facebook page @HumeHealth.
Use the support chat widget located in the bottom left of the Hume Health website.

Will I lose my data from switching to MyHealth to the Hume Health app?

No, all of your historic data from the MyHealth app will automatically transfer over to the Hume Health app. You can seamlessly continue using the app without any action needed on your end.

How do I migrate my previous Hume Pro app data to the Hume Health app?

Note that data transfer will depend on whether you have previously linked your data to Apple Health or Google Fit.

If you have already moved over to the Hume Health app but still need to transfer over your data, perform the following steps:

Open the Hume Health app.
Select your profile located on the bottom right app bar.
Scroll down to "Connected Apps".
Select the “Connected App” box.
Toggle on Apple Health or Google Fit if you are not already connected.
Select the "Data Migration" box shown in the image below.
Select "Ok" to start the data transfer.

If you're having trouble with your data transfer process, don't worry—we're here to help! Please feel free to send us an email at support@myhumehealth.com, and our customer success team will be happy to assist you.

How do I connect the app to third party apps like Apple Health and Google Fit?

Currently the Hume Health app is compatible with both Apple Health and Google Fit.

To sync with Apple Health:

Select your Profile located on the bottom right app bar.
Tap on "Connected Apps".
Tap "Connect".
Allow Hume Health to access Apple Health.

To sync with Google Fit:

Select your Profile located on the bottom right app bar.
Tap on Connected Apps.
Tap on Connect.
Go through the necessary steps to connect to Google Fit.
Your device may request you to download mobile device management to comply with Google Policy.
Allow Hume Health to connect with Google Fit.

How do I manage or add an additional user to my account?

Unfortunately, the option to add or manage additional profiles on your Hume Health app account is no longer available. If you had previously created additional profiles, please contact our customer success team at support@myhumehealth.com for assistance in accessing your existing profile data. Going forward, we suggest that each user create their own individual account to enable a personalized experience based on your own goals and metrics. Don't worry, multiple users can still use the same scale.

How do I change the units of measure on the app or smart scale?

To change the units of measurement, perform the following steps:

Open the Hume Health app.
Select your profile located on the bottom right app bar
Select the settings gear at the top right corner.
Select the units folder at the top of the page.

How do I change the displayed language in the app?

Currently we support a number of languages including English, French, German, Italian and Spanish. To change your language within the app, follow the below steps:

Open the Hume Health app.
Select your profile located on the bottom right app bar
Select the settings gear at the top right corner.
Under general, you can click on Language and select the desired language.

Please note that for videos, the audio will be in English for all language settings but the subtitles will be displayed as the language currently selected within the app.

How do I delete a weigh-in?

The option to delete previous weigh-ins is not available in the Hume Health app. However, our team is actively working on adding this feature in a future software release.

How can I track my progress and view my history in the app?

To view your progress and history, follow these steps:

If you are a free user, tap the "Body Measurements" tile on the “Home” page. For Hume Plus users, navigate to the "Measures" page, which can be selected from the bottom app bar.
This page will display your most recent measurements. To see deeper insights, tap on each individual metric.
Once you select a metric, you will be taken to the graph page where you can filter your progress for the last 7 days, 4 weeks, or 12 months.
Under your graph, you will notice the Progress Report tab. With this feature, you can select two dates to compare your 17 measurements and receive a detailed breakdown of your progress, showing you how your measurements have changed over time.
If you want to see your complete history beyond 12 months, scroll down to the Recent section at the bottom of the graph page and tap the calendar icon with today's current date. Here, you can view your full history by selecting a month and year.

By exploring these different views and features, you can gain valuable insights into your health and track your progress over time.

What is the scale weight limit?

The weight limit of the scale is:

400lbs
181 kg
28 stones

What is the difference between the subscription plans?

All of our subscriptions are the same experiences with different pricing models. We offer a variety of plans to provide flexibility on pricing.

How do I cancel or manage my subscription?

To cancel or manage your Hume Health subscription, perform the following steps:

How do I manage or cancel my subscription on iOS?

You can manage your subscription through your device settings. Find the step by instructions here: If you want to cancel a subscription from Apple

How do I manage or cancel my subscription on Android?

You can manage your subscriptions through the Google Play app. Find the step by instructions here: Cancel, pause, or change a subscription on Google Play - Android - Google Play Help

How do I manage or cancel my subscription on the Website?

Log in to your portal by visiting: myhumehealth.com
Once you’re on the website, click the login icon at the top right
Log in using your email address and password (the same info you use for your Hume Health login)
Click on “My Subscription” on the left
Under Subscriptions, click on the active subscription link
Cancel the subscription using the “cancel button”

For additional support, contact our Customer Success team at support@myhumehealth.com

Can I cancel my subscription anytime?

Yes, you may cancel your recurring subscription at any time. Cancel at least 24 hours before the next renewal date to avoid being charged for the upcoming billing cycle. When you cancel, you are canceling the next billing charge—Premium features will remain available to you until the end of your current paid subscription period, regardless of when you cancel the automatic renewal.

When will I be charged for the subscription?

If you’ve never upgraded to Premium or never started a Premium trial before, you are eligible for a free trial period, and the first Premium subscription charge on your credit card will be after the trial. Once the trial ends, your subscription will auto-renew unless you cancel. This charge will be recurring based on the length of your subscription and will renew unless canceled 24 hours before the next billing period.

Where can I purchase Hume Plus

The Hume Plus subscription can be purchased directly in the app or on our website.

What is Health Score?

Developed with leading health experts, your Health Score gives you a holistic and personalized picture of your health. It shows you how healthy you are vs. benchmarks for people similar to you. You can generate your score each week to see how your health is trending, and how your daily habits impact your score. As you incorporate more positive habits, your score will adjust to reflect these changes.

How do I view my Health Score?

Your Health score is displayed directly in the Hume Health App. To view your Health score, perform the following:

Open the Hume Health app.
On the "Home" page, you will see your Health Score displayed at the top right of the screen.
To access your Health Score, you can either tap on your Health Score at the top right of the "Home" page or select the Health Score Ring, which is the ring with the heart icon at the far right of your "Home" page.

What is your Health Score made up of?

Today, your Health Score is comprised of your Body Composition data from your Hume Pod as well as other critical indicators of holistic health, including: Movement, Nutrition, Stress, and Sleep. These metrics are gathered by syncing with your other health products and devices. To achieve the most accurate Health Score, it's advisable to weigh-in at least twice a week.

Understanding your Health Score

With Health Score, it’s important to consider trends in your score rather than taking a score in isolation. If you receive a score you are unhappy with, don’t be discouraged. Remember that it is more important to see improvements and trends in the right direction through lifestyle changes and action.

Health Score Ranges:

The following chart outlines the ranges for Health Score

765 - 900 Excellent

675 - 764 Great

585 - 674 Good

450 -584 Moderate

297 - 449 Fair

296 or less Low

How can you improve your Health Score?

In addition to your Health Score, you’ll also see personalized insights about your score, like why it might have decreased from last week, and Objectives to help you improve it. Remember that it’s more important to consider trends in your Health Score rather than looking at one score in isolation. As you action on our recommendations and as we start to understand what type of insights are helpful, we can provide more tailored recommendations to help you achieve your goal. The more you track and action, the more you’ll evolve. And quickly, your score will evolve with it.

Why can't I see daily insights?

You’ll notice that we send weekly insights instead of daily insights. We believe this is what separates us from other health solutions out there. While tracking daily changes can be useful when it comes to fitness; seeing your health trends over longer periods of time is particularly important when looking and understanding leading indicators of certain chronic health conditions. We understand that things like weight, water, and eating habits can change from one day to the next and your health score is calculated with these fluctuations in mind.

Under construction

How do I join a program?

Here’s how to join one of our programs:

Open the Hume Health app.
Select the “Plans” tab along the bottom app bar.
All programs will be displayed. Scroll down to view programs.
Select the program you want to join and tap into the workout of your choice. Once you start your workout and watch most of the video, we will automatically enroll you in that program.
You will notice that the program is now added to your current program list. (see second image below) If you watch most of the workout, then the next program on the list will display here for you to quickly jump back in. You can also go directly to the program and select the desired workout you want to watch.

How do I try a workout?

Want to try a workout? Easy! Simply do the following:

Open the Hume Health app.
Select the “Plans” tab along the bottom app bar.
Navigating into a program and choosing any workout from that program. You can also navigate to the “Classes” tab and choose from any of our curated workout videos.

How do I filter classes?

To filter classes, perform the following:

Open the Hume Health app.
Select the “Plans” tab along the bottom app bar.
Navigate to the “Classes” tab and tap on “Filters”.
After you tap on “Filters” you can narrow down the classes list by choosing the filters you are interested in. Scroll all the way down and tap on “Show Results” so the selected filters will be applied. You can always tap on the “Filters” button again to modify or clear your filters.

How do I modify a workout?

We want everyone to listen to their body when it comes to working out. That’s why we’ve made sure to include a modifier option for each class. The trainer will walk you through both levels so you can choose the best option for your fitness level. Please consult an expert before starting any fitness or wellness program.

Can I listen to my own music?

All of our classes have music added in. We are working on further enhancements to provide more music options.

How do I view subtitles?

You can view subtitles by performing the following:

While in a video, select the three dots option at the top right.
From here, you can choose from the available subtitles. You can also select playback speed, quality, and audio options.

Can I listen to the audio while the Hume Health app is in the background?

Yes, when you dismiss the app, the audio will continue to play in the background until you actually pause the video or navigate away from the video player.

What is a Guided Cardio workout?

A Guided Cardio workout is designed to be an audio-only workout that guides and motivates you through cardio workouts such as walks, jogs, and runs. Several of our MyHealth+ programs include Guided Cardio classes to help achieve your results faster.

For safety, please check and be aware of your surroundings at all times.

Can I use AirPlay or Chromecast to watch a video on my TV?

You can currently only play the videos directly on your device. We are working on enhancements to allow you to play videos using AirPlay and Chromecast.

How does Hume Health store my data?

We take the security of your data very seriously, which is why all user data is stored within a HIPAA-compliant database solution. Your data is encrypted both in transit and at rest, and access is strictly controlled and monitored. We have implemented strict security measures to ensure that all user data is kept confidential and secure at all times.

How does Hume Health use my data?

We use anonymized dataIDs internally to better inform our algorithm and ensure product features like your Digital Twin can continue to get better over time. The data you share with Hume Health is also used to provide you with personalized plans and content based on your activity, body and sleep data.

Can I delete my data?

Yes, we believe that you should be in control and want to make it easy to do so. Our Customer Success team would be happy to support this request, simply reach out to them at support@myhumehealth.com.

Do you sell my data to anyone?

No, we do not sell your personal data to advertisers or any third parties.

Can you use your FSA Card to purchase the HumePod?

Yes! The Dara and the Hume Pod qualify, and qualify under the “scales” category of the FSA eligible product list. Specifically, body composition helps you qualify for FSA. Regular weight scales do not qualify.

Important Note:

You will need to select “Truemed” as a payment method on checkout.

Under what category in the FSA Eligible product list does the Hume Pod come under?

The HumePod falls under the "scales" category of the FSA eligible product list. Specifically, body composition helps you qualify for HSA/FSA. Regular weight only scales do not qualify.

Sensor Technology Reference

1. Bioelectrical Impedance Analysis — Foundational Principles

Bioelectrical impedance analysis (BIA) works by introducing a small, imperceptible alternating electrical current into the body and measuring the opposition that body tissues present to that current. This opposition — impedance — has two components: resistance (R), which reflects the opposition of fluid-filled tissues to current flow, and reactance (Xc), which reflects the capacitative effect of cell membranes. Because fat tissue contains almost no water and conducts electrical current poorly, while lean tissue is highly conductive due to its high water and electrolyte content, the impedance signal encodes information about the proportion of each tissue type in the current's path.

The output of a raw BIA measurement is not a body composition value. It is a set of impedance values — resistance and reactance — that are then entered into validated prediction equations to estimate compartments such as fat mass, fat-free mass, and total body water. The accuracy of those estimates depends on the quality of the prediction equation, the population from which it was derived, and the degree to which the individual being measured resembles that population.

Hoffer, E. C., Meador, C. K., & Simpson, D. C. (1969). Correlation of whole-body impedance with total body water volume. Journal of Applied Physiology, 27(4), 531–534. https://doi.org/10.1152/jappl.1969.27.4.531

Lukaski, H. C., Johnson, P. E., Bolonchuk, W. W., & Lykken, G. I. (1985). Assessment of fat-free mass using bioelectrical impedance measurements of the human body. American Journal of Clinical Nutrition, 41(4), 810–817. https://doi.org/10.1093/ajcn/41.4.810

Kyle, U. G., Bosaeus, I., De Lorenzo, A. D., Deurenberg, P., Elia, M., Gómez, J. M., et al. (2004). Bioelectrical impedance analysis — part I: review of principles and methods. Clinical Nutrition, 23(5), 1226–1243. https://doi.org/10.1016/j.clnu.2004.06.004

2. Multi-Frequency Measurement and the Cole Model

Single-frequency BIA applies current at one frequency (typically 50 kHz) and uses the resulting impedance to estimate total body water via a population-average relationship. The limitation is that at a single frequency, current distribution between extracellular and intracellular compartments is not separately identifiable — the measurement conflates them.

To address this flaw, the Hume Pod uses Multi-frequency BIA (MF-BIA). By sweeping across a range of frequencies, a spectrum of measurements are taken. At low frequencies (1–5 kHz), current passes primarily through extracellular fluid (ECF) because cell membranes present high capacitative resistance at low frequencies, blocking intracellular entry. At high frequencies (100–1000 kHz), cell membranes become effectively transparent and current distributes through both ECF and intracellular fluid (ICF). By modeling impedance across this frequency range using the Cole-Cole model — a mathematical framework that characterizes biological tissue impedance as a function of frequency — it becomes possible to separately estimate ECW and ICW volumes.

Bioimpedance spectroscopy (BIS) extends this further by fitting the full Cole model curve to derive characteristic impedances at theoretical zero and infinite frequency (R0 and R∞), from which ECW and ICW are estimated with greater accuracy than frequency-sweep interpolation alone.

De Lorenzo, A., Andreoli, A., Matthie, J., & Withers, P. (1997). Predicting body cell mass with bioimpedance by using theoretical methods: a technological review. Journal of Applied Physiology, 82(5), 1542–1558. https://doi.org/10.1152/jappl.1997.82.5.1542

Scope note: Reviews Cole model fitting for BIS and compares theoretical methods for deriving R0 and R∞ from multi-frequency impedance data. Demonstrates that body cell mass (BCM) estimation from BIS-derived ICW is substantially more accurate than single-frequency approaches. This review underpins the Hume Pod's multi-frequency design rationale and the compartment-level outputs (ECW, ICW, BCM) that a single-frequency scale cannot produce.

Cornish, B. H., Thomas, B. J., & Ward, L. C. (1993). Improved prediction of extracellular and total body water using impedance loci generated by multiple frequency bioelectrical impedance analysis. Physics in Medicine and Biology, 38(3), 337–346. https://doi.org/10.1088/0031-9155/38/3/004

Scope note: Empirical validation of MF-BIA for separate ECW and ICW estimation using Cole model loci. Demonstrates that impedance measurements at multiple frequencies predict ECW (r² = 0.96) and TBW (r² = 0.97) more accurately than single-frequency methods. Provides the quantitative basis for using multi-frequency measurement to separate fluid compartments in the Hume Pod.

3. Eight-Electrode Segmental Architecture

Conventional whole-body BIA passes current from foot to foot and measures a single impedance value that represents a weighted average along that path. Because current follows the path of least resistance, the trunk — a large, low-resistance volume — contributes disproportionately little to the total impedance signal relative to its mass. This means single-path BIA cannot produce accurate segmental values for arms, legs, and trunk independently.

The Hume Pod resolves this by placing multiple electrodes at anatomically distinct sites and measuring impedance across each body segment independently: right arm, left arm, trunk, right leg, and left leg. The Hume Pod uses eight electrodes — four on the front plate (foot contacts) and four on the hand grips — enabling current injection and voltage sensing across each segment in isolation. This allows genuinely independent mass estimation for each segment rather than mathematical disaggregation of a single whole-body signal.

Organ, L. W., Bradham, G. B., Gore, D. T., & Lozier, S. L. (1994). Segmental bioelectrical impedance analysis: theory and application of a new technique. Journal of Applied Physiology, 77(1), 98–112. https://doi.org/10.1152/jappl.1994.77.1.98

Scope note: Foundational paper establishing segmental BIA theory and the multi-electrode configuration that enables it. Demonstrates that a five-cylinder geometric model of the human body (two arms, two legs, trunk) requires independent impedance measurements per segment to produce valid segmental mass estimates. Validates the approach against MRI-derived segmental lean mass in cadaveric and in vivo samples. The Hume Pod's eight-electrode design implements this segmental architecture.

Janssen, I., Heymsfield, S. B., Baumgartner, R. N., & Ross, R. (2000). Estimation of skeletal muscle mass by bioelectrical impedance analysis. Journal of Applied Physiology, 89(2), 465–471. https://doi.org/10.1152/jappl.2000.89.2.465

Scope note: Validation of BIA-derived skeletal muscle mass against MRI (the reference standard) in 388 adults. The BIA equation explains 97% of MRI-measured skeletal muscle mass variance. Segmental muscle mass predictions require the same segmental impedance inputs as total lean mass. This study provides the equation validation basis for the Pod's skeletal muscle mass and segmental muscle mass outputs.

4. Prediction Equations and Population Validity

BIA hardware measures impedance. Prediction equations translate impedance into body composition estimates using regression coefficients derived from reference-method studies — typically dual-energy X-ray absorptiometry (DXA), underwater weighing, or multi-compartment models. Because these equations are population-derived, their accuracy is highest when applied to individuals who match the population from which the equation was developed in age, sex, ethnicity, body size, and health status.

This means BIA accuracy is not a single fixed value — it varies by output metric, by population subgroup, and by how far an individual deviates from the equation's development population. The Pod's prediction equations are selected from validated NHANES-scale studies to maximize generalizability across a broad adult population, but users with extreme body compositions, significant edema, or major deviations from standard body proportions may receive estimates with higher error margins than the general population values reported in validation studies.

Sun, S. S., Chumlea, W. C., Heymsfield, S. B., Lukaski, H. C., Schoeller, D., Friedl, K., et al. (2003). Development of bioelectrical impedance analysis prediction equations for body composition with the use of a multicomponent model for use in epidemiologic surveys. American Journal of Clinical Nutrition, 77(2), 331–340. https://doi.org/10.1093/ajcn/77.2.331

Scope note: NHANES-scale validation study developing BIA prediction equations using a four-compartment reference model in a nationally representative US sample. The multi-compartment model (combining water dilution, densitometry, and bone mineral measurement) is the most accurate reference method available, making this the gold-standard equation validation source. These equations underpin the Hume Pod's fat mass, fat-free mass, and body water outputs. The NHANES sample diversity makes these equations more broadly applicable across age, sex, and ethnicity than single-site studies.

Deurenberg, P., Weststrate, J. A., & Seidell, J. C. (1991). Body mass index as a measure of body fatness: age- and sex-specific prediction formulas. British Journal of Nutrition, 65(2), 105–114. https://doi.org/10.1079/BJN19910073

Scope note: Establishes age- and sex-stratified relationships between BIA-derived and reference-method body fat percentage in adults aged 7–83. Demonstrates that a single prediction equation applied across age groups systematically underestimates fat in older adults due to age-related changes in body water distribution and tissue density. This finding underlies the Pod's use of age-stratified prediction equations rather than a single pooled formula.

5. Measurement Conditions and Accuracy Boundaries

BIA impedance is highly sensitive to hydration state. Because the measurement fundamentally depends on body water volume and distribution, factors that transiently alter hydration — food and fluid intake, exercise, alcohol consumption, and the timing of the measurement within the circadian cycle — can shift impedance values and therefore body composition estimates by clinically meaningful margins. A euhydrated individual and the same individual after significant fluid loss may produce fat mass estimates differing by 2–4 percentage points from the same BIA system.

For this reason, the Hume Pod's measurement protocol specifies consistent timing (morning, post-void, fasted) to reduce within-person hydration variability. Serial measurements taken under consistent conditions are more informative than any individual measurement, because inter-measurement changes in hydration are smaller than between-session changes when protocol is held constant. The app's trend analysis reflects this — individual readings are shown in context of the rolling window, not as isolated data points.

Kushner, R. F., & Schoeller, D. A. (1986). Estimation of total body water by bioelectrical impedance analysis. American Journal of Clinical Nutrition, 44(3), 417–424. https://doi.org/10.1093/ajcn/44.3.417

Scope note: Early validation demonstrating that BIA-derived TBW estimates are accurate under standardized conditions (r = 0.99 vs deuterium dilution) but are disrupted by dehydration, recent exercise, and food intake. Establishes the empirical basis for the standardized measurement protocol that maximizes BIA accuracy by controlling hydration state at the time of measurement.

Kyle, U. G., Bosaeus, I., De Lorenzo, A. D., Deurenberg, P., Elia, M., Manuel Gómez, J., et al. (2004). Bioelectrical impedance analysis — part II: utilization in clinical practice. Clinical Nutrition, 23(6), 1430–1453. https://doi.org/10.1016/j.clnu.2004.09.012

Hume Pod Metrics

1. Weight and Body Mass Index (BMI)

World Health Organization. (1998). Obesity: Preventing and Managing the Global Epidemic. Report of a WHO Consultation on Obesity, Geneva, 3–5 June 1997. WHO Technical Report Series 894. Geneva: WHO. Scope note: Foundational source for BMI classification tiers: underweight < 18.5, normal weight 18.5–24.9, overweight 25–29.9, obese ≥30. Tier anchors for the BMI metric and the basis for linking BMI to body fat percentage norms in Gallagher et al. 2000.

National Heart, Lung, and Blood Institute. (1998). Clinical Guidelines on the Identification, Evaluation, and Treatment of Overweight and Obesity in Adults: The Evidence Report. NIH Publication No. 98-4083. Bethesda, MD: NIH.

Scope note: US federal guideline establishing the same BMI classification tiers as WHO. Parallel publication confirms these thresholds reflect international consensus.

2. Body Fat Percentage, Body Fat Mass, Lean Mass, and Lean Mass Percentage

Age- and Sex-Stratified Ranges (Primary) Gallagher, D., Heymsfield, S. B., Heo, M., Jebb, S. A., Murgatroyd, P. R., & Sakamoto, Y. (2000). Healthy percentage body fat ranges: an approach for developing guidelines based on body mass index. American Journal of Clinical Nutrition, 72(3), 694–701. https://doi.org/10.1093/ajcn/72.3.694

Scope note: Primary citation for body fat percentage breakpoints. Study of 1,626 adults from three ethnic groups measured by 4-compartment model and DXA. Derived provisional healthy body fat ranges by linking predicted percentage fat to WHO/NIH BMI limits via regression equations including sex, age, and ethnic group. Lean mass percentage tiers are the complement of these fat ranges from the same dataset.

Extended Age-Range Population Norms (Supporting)
Ofenheimer, A., Breyer-Kohansal, R., Hartl, S., Burghuber, O. C., Krach, F., Schrott, A., et al. (2020). Reference values of body composition parameters and visceral adipose tissue (VAT) by DXA in adults aged 18–81 years—results from the LEAD cohort. European Journal of Clinical Nutrition, 74, 1181–1191. https://doi.org/10.1038/s41430-020-0596-5

Scope note: Population-based cohort (n = 10,894; Austrian LEAD study; ages 18–81) providing DXA-derived reference percentile curves for fat mass index, lean mass index, appendicular LMI, android/gynoid fat ratios, and VAT. Used to extend Gallagher breakpoints into older age bands and to provide android/gynoid ratio norms (Section 6).

3. Skeletal Muscle Mass, Segmental Muscle Mass, Muscular Symmetry, and Upper/Lower Body Balance

Normative Distribution by Age and Sex
Janssen, I., Heymsfield, S. B., Wang, Z. M., & Ross, R. (2000). Skeletal muscle mass and distribution in 468 men and women aged 18–88 yr. Journal of Applied Physiology, 89(1), 81–88. https://doi.org/10.1152/jappl.2000.89.1.81

Scope note: Whole-body MRI study (n = 468; ages 18–88) establishing normative skeletal muscle mass values by age and sex with segmental distribution. Key finding for upper/lower body balance: gender differences in muscle mass were greater in the upper body (40%) than the lower body (33%). Provides the population-level upper-to-lower distribution from which the upper/lower body balance breakpoints are derived. Also anchors all five segmental muscle mass metrics (right arm, left arm, trunk, right leg, left leg) via age-banded means used for linear interpolation.

Sarcopenia Cutpoints and Disability Risk
Janssen, I., Heymsfield, S. B., & Ross, R. (2002). Low relative skeletal muscle mass (sarcopenia) in older persons is associated with functional impairment and physical disability. Journal of the American Geriatrics Society, 50(5), 889–896. https://doi.org/10.1046/j.1532-5415.2002.50216.x

Scope note: NHANES III analysis (n = 14,818) establishing skeletal muscle index cutpoints for class I and class II sarcopenia (1 and 2 SD below young adult mean). Anchors the lower-tier breakpoints for all muscle mass metrics.

Left/Right Muscular Symmetry
Bishop, C., Turner, A., & Read, P. (2018). Training methods and considerations for practitioners to reduce interlimb asymmetries. Strength and Conditioning Journal, 40(5), 40–46. https://doi.org/10.1519/SSC.0000000000000388

Scope note: Reviews the evidence base for inter-limb muscle mass and strength asymmetry assessment, including the population-level observation that dominant-limb muscle mass typically exceeds non-dominant by 3–5% in healthy adults. Asymmetries exceeding 10–15% are consistently associated with elevated injury risk across the literature. Parkinson, A. O., Apps, C. L., Lewis, M. G. C., Scratch, C., & Perry, J. L. (2021). The calculation, thresholds and reporting of inter-limb strength asymmetry: a systematic review. Journal of Functional Morphology and Kinesiology, 6(1), 21. https://doi.org/10.3390/jfmk6010021

Scope note: Systematic review of asymmetry index methods and thresholds across 44 studies. Establishes that 85% symmetry (a 15% difference between limbs) is the threshold above which asymmetry is considered functionally meaningful in healthy subjects across most testing protocols. Provides the quantitative basis for the left/right muscle symmetry tier breakpoints.

Upper/Lower Body Muscle Balance
Coombs, R., & Garbutt, G. (2002). Developments in the use of the hamstring/quadriceps ratio for the assessment of muscle balance. Journal of Sports Science and Medicine, 1(3), 56–62.

Scope note: Foundational review establishing the hamstring-to-quadriceps strength ratio as the reference framework for agonist/antagonist muscle balance in the lower body. The conventional H/Q ratio of 0.6 (hamstrings producing at least 60% of quadriceps force) has gained broad acceptance as the lower boundary for acceptable lower-body balance. Upper/lower body balance as reported by the Pod (upper limb muscle mass relative to lower limb muscle mass) draws on the distributional norms in Janssen 2000 rather than strength ratios, but the H/Q framework provides the clinical context for why deviations from expected distributions are meaningful.

4. Visceral Fat Index, Visceral Fat Mass, and Visceral Fat Percentage

Thomas, D. M., et al. (2019). Age- and sex-specific reference intervals for visceral fat mass in adults. International Journal of Obesity, 43, 2351–2360. https://doi.org/10.1038/s41366-019-0393-1

Scope note: Primary source for VAT tier breakpoints. DXA-derived reference intervals from 3,219 UK adults (ages 18–83) stratified by sex.

Ofenheimer et al. (2020). European Journal of Clinical Nutrition, 74. (Full citation under Section‗2.)

Scope note: LEAD cohort VAT percentile curves (n = 10,894) used to cross-validate Thomas 2019.

Brochu, M., et al. (2021). Age- and sex-specific visceral fat reference cutoffs and their association with cardio-metabolic risk. International Journal of Obesity, 45, 1816–1825. https://doi.org/10.1038/s41366-021-00743-3

Scope note: Regression analysis of 1,482 adults deriving sex-specific VAT thresholds associated with elevated blood lipids and blood pressure. Informs the upper-tier breakpoint.

5. Subcutaneous Fat Mass, Trunk Fat Mass, Trunk Fat Percentage, and Segmental Fat Percentages

Pou, K. M., Massaro, J. M., Hoffmann, U., Vasan, R. S., Maurovich-Horvat, P., Larson, M. G., Levy, D., Meigs, J. B., Robins, S. J., & O’Donnell, C. J. (2009). Patterns of abdominal fat distribution: the Framingham Heart Study. Diabetes Care, 32(3), 481–485. https://doi.org/10.2337/dc08-1359

Scope note: Framingham Heart Study population data on abdominal fat distribution by age and sex. Used to contextualize trunk fat and subcutaneous fat tiers relative to total fat and visceral fat. Segmental limb fat percentage breakpoints are derived proportionally from the whole-body Gallagher norms using the regional fat distribution coefficients in this study.

6. Android/Gynoid Fat Distribution Ratio

Ofenheimer et al. (2020). European Journal of Clinical Nutrition, 74. (Full citation under Section‗2.)

Scope note: Primary source. LEAD cohort provides age- and sex-stratified percentile curves for android/gynoid fat mass ratio from DXA in n = 10,894. Higher ratios indicate central fat patterning associated with greater cardiometabolic risk.

Kelly, T. L., Wilson, K. E., & Heymsfield, S. B. (2009). Dual energy X-ray absorptiometry body composition reference values from NHANES. PLOS ONE, 4(9), e7038. https://doi.org/10.1371/journal.pone.0007038

Scope note: US population cross-validation for android/gynoid ratio norms, including android and gynoid fat mass sub-regions from NHANES DXA data.

7. Skeletal Mass and Bone Mineral Content

Looker, A. C., Wahner, H. W., Dunn, W. L., Calvo, M. S., Harris, T. B., Heyse, S. P., Johnston, C. C., Jr., & Lindsay, R. (1995). Proximal femur bone mineral levels of US adults. Osteoporosis International, 5(6), 389–409. https://doi.org/10.1007/BF01622262

Scope note: NHANES III reference data (n ≈ 14,646) providing bone mineral density and content norms for US adults by age, sex, and race. Anchors skeletal mass and bone mineral content tiers, with attention to the age-related decline from peak bone mass at approximately age 30–35.

Kelly et al. (2009). PLOS ONE, 4. (Full citation under Section‗6.)

Scope note: Includes bone mineral content from NHANES DXA, enabling consistent co-interpretation of bone metrics within the full body composition profile.

8. Body Water Percentage, Body Water Volume, Extracellular Water, and Intracellular Water

Watson, P. E., Watson, I. D., & Batt, R. D. (1980). Total body water volumes for adult males and females estimated from simple anthropometric measurements. American Journal of Clinical Nutrition, 33(1), 27–39. https://doi.org/10.1093/ajcn/33.1.27

Scope note: Foundational TBW prediction equations from dilution studies in 723 adults. Most widely validated TBW reference framework. Provides the basis for absolute body water volume norms.

Chumlea, W. C., Guo, S. S., Zeller, C. M., Reo, N. V., Baumgartner, R. N., Garry, P. J., Wang, J., Pierson, R. N., Jr., Heymsfield, S. B., & Siervogel, R. M. (2001). Total body water reference values and prediction equations for adults. Kidney International, 59(6), 2250–2258. https://doi.org/10.1046/j.1523-1755.2001.00741.x

Scope note: Updated TBW reference values from 1,612 white and Black adults (ages 18–90). Larger, more recent, and more diverse than Watson 1980. Anchors body water percentage tiers by age and sex.

Lam, Y. Y., et al. (2023). Body water percentage from childhood to old age. European Journal of Clinical Nutrition, 77, 863–869. https://doi.org/10.1038/s41430-023-01279-5

Scope note: BIA-based cross-sectional study of TBW% trajectory. In normal-weight adults, TBW% decreases after age 60 in both sexes. Extends body water tier framework into older age bands.

Kyle, U. G., Bosaeus, I., De Lorenzo, A. D., Deurenberg, P., Elia, M., Gómez, J. M., Heitmann, B. L., Kent-Smith, L., Melchior, J. C., Pirlich, M., Scharfetter, H., Schols, A. M., & Pichard, C. (2004). Bioelectrical impedance analysis—part I: review of principles and methods. Clinical Nutrition, 23(5), 1226–1243. https://doi.org/10.1016/j.clnu.2004.06.004

Scope note: Comprehensive BIA review covering ECW/ICW compartment estimation via bioimpedance spectroscopy. Establishes that the normal ECW/ICW ratio in healthy adults is approximately 60:40, with ECW comprising about 42% and ICW about 58% of TBW. ECW and ICW tier breakpoints are derived from total body water norms apportioned by this population-average ratio at each age.

9. Mineral Mass, Body Cell Mass, and Organ Mass

Mineral Mass and Body Cell Mass
Sun, S. S., Chumlea, W. C., Heymsfield, S. B., Lukaski, H. C., Schoeller, D., Friedl, K., Kuczmarski, R. J., Flegal, K. M., Johnson, C. L., & Hubbard, V. S. (2003). Development of bioelectrical impedance analysis prediction equations for body composition with the use of a multicomponent model for use in epidemiologic surveys. American Journal of Clinical Nutrition, 77(2), 331–340. https://doi.org/10.1093/ajcn/77.2.331

Scope note: NHANES validation of BIA prediction equations using a 4-compartment model. Mineral mass (the inorganic salt compartment of lean mass) is estimated within this framework as the residual of FFM minus water and protein. Body Cell Mass (BCM) — the metabolically active, intracellular compartment — is derived from ICW and protein mass within the same model. Population norms for both compartments flow from this multicomponent reference framework applied to the NHANES sample.

Pirlich, M., Schütz, T., Spachos, T., Ertl, S., Weiss, M. L., Lochs, H., & Plauth, M. (2000). Bioelectrical impedance analysis is a useful bedside technique to assess malnutrition in cirrhotic patients with and without ascites. Hepatology, 32(6), 1208–1215. https://doi.org/10.1053/jhep.2000.20519

Scope note: Establishes BIA phase angle as a validated proxy for body cell mass status. Phase angle (a direct BIA output) is linearly related to BCM. A phase angle below the age- and sex-adjusted reference range indicates depleted BCM, which is relevant to the BCM tier lower boundary. Used alongside Sun 2003 to calibrate BCM tiers.

Organ Mass Müller, M. J., Bosy-Westphal, A., Later, W., Haas, V., & Heymsfield, S. B. (2011). Effect of constitution on mass of individual organs and their association with metabolic rate in humans — a detailed view on allometric scaling. PLOS ONE, 6(7), e22732. https://doi.org/10.1371/journal.pone.0022732

Scope note: MRI study in 330 healthy volunteers (ages 17–78; 61% female; BMI 15.9–47.8) providing scaling equations for the masses of brain, heart, liver, kidneys, and spleen as a function of sex, age, body weight, and height. This is the primary population-level reference for organ mass norms. Organ masses in this study were significantly sex-differentiated for all organs except liver. The BIA-derived organ mass metric is calibrated against the organ-weight-to-body-size relationships reported here.

Gallagher, D., Belmonte, D., Deurenberg, P., Wang, Z., Krasnow, N., Pi-Sunyer, F. X., & Heymsfield, S. B. (1998). Organ-tissue mass measurement allows modeling of REE and metabolically active tissue mass. American Journal of Physiology, 275(2), E249–E258. https://doi.org/10.1152/ajpendo.1998.275.2.e249

Scope note: Establishes the organ-tissue level body composition framework in which organ mass is modeled as a function of sex, age, and body size, and links organ mass to resting energy expenditure. Provides the organ-specific metabolic rate coefficients that underlie the organ mass metric’s relationship to BMR in the app.

10. Basal Metabolic Rate (BMR) and Metabolic Age

Mifflin, M. D., St Jeor, S. T., Hill, L. A., Scott, B. J., Daugherty, S. A., & Koh, Y. O. (1990). A new predictive equation for resting energy expenditure in healthy individuals. American Journal of Clinical Nutrition, 51(2), 241–247. https://doi.org/10.1093/ajcn/51.2.241

Scope note: Derived from 498 subjects (ages 19–78). Equation used to compute BMR from body weight, height, age, and sex.

Frankenfield, D., Roth-Yousey, L., & Compher, C. (2005). Comparison of predictive equations for resting metabolic rate in healthy nonobese and obese adults: a systematic review. Journal of the American Dietetic Association, 105(5), 775–789. https://doi.org/10.1016/j.jada.2005.02.005

Scope note: Systematic review confirming Mifflin-St Jeor as the most accurate of four commonly used equations (≥82% of predictions within 10% of measured RMR).

Speakman, J. R., et al. (2021). Total daily energy expenditure has declined over the past three decades due to declining basal expenditure, not reduced activity expenditure. Nature Metabolism, 3, 728–736. https://doi.org/10.1038/s42255-021-00393-9

Scope note: Doubly-labeled water dataset (n = 6,421; ages 8 days– 95 years) characterizing BMR lifespan trajectory. BMR peaks in the third decade; declines approximately 0.7% per year after age 60. Metabolic Age maps the user’s BIA-estimated BMR to the cohort whose population-average BMR matches it, using this lifespan curve as the reference.

11. Bioelectrical Impedance Analysis Methodology

Kyle et al. (2004). Clinical Nutrition, 23(5), 1226–1243. (Full citation under Section‗8.)

Scope note: Comprehensive BIA principles review. Methodological foundation for all Pod metrics.

Sun et al. (2003). American Journal of Clinical Nutrition, 77(2), 331–340. (Full citation under Section‗9.)

Scope note: NHANES-scale BIA validation. Establishes that BIA-derived body composition outputs are traceable to the same reference populations underlying the normative studies in this bibliography.

Hume Band

Getting Started

Hume Help Videos

Band Features & Design

AI Recommendations & Insights

Design & Fit

Battery & Charging

Connectivity & App Integration

Hygiene & Maintenance

Purchasing & Availability

Warranty & Support

Data Privacy

Study

How do I set up the Band for the first time?

Setting up your Hume Band involves a straightforward process:

Download the Hume app from the App Store or Google Play
Create your Hume account or log in.
For new users, the onboarding process will guide you through setting up your Hume Band.
For existing users, tap on the "Band" page on the bottom navigation bar. The onboarding process will guide you through setting up your Hume Band.

Ensure Bluetooth is enabled on your phone.
Press and hold the side button of the Band to ensure it is in pairing mode.
Place the band near your phone and follow the on-screen pairing instructions.

How can I connect my Band?

For existing users, who have completed onboarding and looking to re-pair or connect a new band:

Tap on the Me page on the bottom navigation bar
Scroll down to the "Paired Devices" section
Tap "Pair Device"

Ensure Bluetooth is enabled on your phone
Press and hold the side button of the Band to ensure it is in pairing mode
Place the band near your phone and follow the on-screen pairing instructions

Does the Band connect to Wi-Fi?

No, the Hume Band does not connect directly to Wi-Fi. It uses Bluetooth technology to connect to your smartphone, and then data is synced to the Hume cloud through your phone's internet connection (either Wi-Fi or cellular).

What is the Bluetooth range on the Band?

The Hume Band has a standard Bluetooth range of approximately 30 feet (9 meters) under optimal conditions. However, physical barriers like walls, furniture, or electronic interference may reduce this range. For the most reliable connection, we recommend keeping your band and phone within 10 feet (3 meters) of each other when syncing data.

Hume Band- Connection Troubleshooting

What data does the Band track and measure?

The Hume Band captures a comprehensive set of physiological metrics:

Heart rate (continuous monitoring)
Heart rate variability (HRV)
Blood oxygen levels (SpO2)
Sleep stages (light, deep, REM, and awake periods)
Sleep quality and efficiency
Activity levels and movement patterns
Strain and recovery metrics
Skin temperature

What makes your Band different from other fitness trackers?

The Hume Band differentiates itself in several key ways:

Metabolic Intelligence: Instead of simply tracking metrics, the Hume Band uses Pro.f AI to interpret your physiological signals and transform them into personalized insights focused on metabolic health and longevity.
Recovery Focus: Rather than emphasizing only exercise and activity, the Hume Band prioritizes recovery analysis and optimization, including detailed sleep architecture assessment.
Longevity Science: The band applies principles from longevity research to its algorithms, focusing on metrics with established connections to healthspan and lifespan.
Metabolic Capacity: Unique daily assessments of your body's readiness and recovery state create a continuously adapting picture of your metabolic health.
Strain and Recovery Balance: Sophisticated analysis of physiological and mental strain and recovery patterns helps optimize your daily activities for long-term health.
AI-Powered Discoveries: Premium users receive personalized experimental recommendations designed to accelerate Pro.f's understanding of your unique physiology.

The Hume Band shifts focus from fitness tracking to comprehensive metabolic optimization for long-term health.

What is “longevity,” and how does the Band support it?

Longevity refers to the optimization of your body's fundamental biological processes to extend both lifespan and healthspan—the years you live in good health. Unlike fitness tracking that focuses on daily activity, longevity optimization targets the underlying metabolic systems that determine how your body ages at the cellular level.

The Band's Longevity Approach:

Cardiovascular System Optimization: The Band continuously monitors your cardiovascular health through five key metrics that directly correlate with longevity: resting heart rate, heart rate variability, heart rate consistency, baseline SpO2, and SpO2 consistency. These combine into your Cardiovascular Health Score, a powerful predictor of both lifespan and quality of life.
Metabolic Capacity Tracking: Your daily Metabolic Capacity score reflects your body's current ability to handle physical and mental strain while maintaining optimal recovery—like a battery measuring your biological resilience and adaptability.
Recovery Debt Prevention: The Band tracks strain (muscular, cardiovascular, mental) and compares it to your recovery. Preventing chronic unrecovered strain slows aging and promotes beneficial adaptations for long-term health.
Sleep Architecture Analysis: Deep sleep, REM cycles, and consistency impact cellular repair, immunity, and cognitive health. The Band ensures your sleep supports optimal aging.
Physiological Age Calculation: By comparing your data to population benchmarks, the Band estimates your physiological age—how your body is aging versus your actual age.
Metabolic Trajectory Projection: The Band projects how your current health behaviors impact your future metabolic capacity, empowering you to make decisions that support long-term vitality.

Rather than simply tracking activity, the Band optimizes the biological processes that determine how you age, giving you the tools to take measurable control of your longevity.

Is the Band waterproof/sweatproof?

The Hume Band sensor is IP68 dustproof and water-resistant at depths up to 1 meter (roughly 3.2 feet) for up to 2 hours - so you can continue to capture your data with zero interruptions

Can I wear the Band while sleeping?

Absolutely—and we actually recommend it! Sleep is a huge part of how your body recovers, and the Hume Band is designed to track all the important stuff while you rest, like:

Sleep stages (light, deep, REM, and awake)
How long and how well you slept
Heart rate variability
Breathing rate and blood oxygen levels
How well your body is bouncing back overnight

All of this contributes to your Sleep Quality Score and helps shape your daily recovery and Metabolic Capacity. Plus, the Band is made to be super comfy, so you can wear it all night without even noticing it’s there.

Sampling Architecture?

Base sampling rate: 50-100 Hz for PPG signal acquisition
HRV calculation intervals: Measured in milliseconds (R-R intervals typically 600-1200ms for resting heart rates)
Processing frequency: HRV metrics calculated every 30 seconds from rolling 2-5 minute windows

Continuous Low-Power Monitoring?

Always-on: 25 Hz PPG sampling for basic heart rate
Triggered High-Fidelity: 100 Hz sampling when conditions optimal
Sleep Analysis: Sustained 5+ minute windows during deep sleep

Battery-Optimized Triggers?

Sleep Detection: Automatic 5-minute+ HRV analysis during deep sleep phases
Stillness Detection: Accelerometer triggers high-quality measurement when user stationary >2 minutes
User-Initiated: Manual 5-minute cardiovascular assessment mode (Not at launch, part of a broader featureset)

Data Quality Optimization?

Signal Quality Index: Real-time assessment of PPG signal strength
Motion Filtering: Accelerometer data used to validate measurement periods
Adaptive Duration: Extends measurement time if signal quality poor, shortens if excellent
Multiple Validation: Requires 3+ high-quality measurement periods for weekly HRV score

AI Processing Approach?

Edge Computing: Basic R-R interval detection on-device
Cloud Analysis: Advanced artifact removal and HRV metric calculation
Proprietary Algorithms: Custom signal processing optimized for wrist-based PPG (we intend to add ankles to the model soon as we finish research)

Does the Band provide recommendations or just data?

The Hume Band provides both data and actionable recommendations through Pro.f, its AI metabolic intelligence. Rather than just displaying metrics, the system:

Analyzes your physiological patterns
Generates personalized insights based on your unique data
Provides specific activity, nutrition, and recovery recommendations
Adapts recommendations based on your daily metabolic capacity
Creates a personalized "My Day" plan with calibrated targets

Free users receive basic recommendations, while premium subscribers get more detailed, personalized guidance including:

Advanced recovery protocols
Custom-designed metabolic experiments
Long-term optimization strategies
Adaptive recommendations based on historical patterns

Recommendations are designed to be actionable and appropriate for your current metabolic state, making it easier to optimize your health without needing to interpret the data yourself.

How accurate is the Band’s tracking data?

The Hume Band delivers high accuracy for a consumer wearable device:

Heart rate tracking is validated against ECG standards with accuracy typically within 3-5 bpm during rest and moderate activity
Sleep stage detection uses validated algorithms with accuracy rates comparable to consumer-grade EEG devices
Blood oxygen (SpO2) measurements meet FDA guidelines for pulse oximetry accuracy
HRV measurements focus on relative changes rather than absolute values, providing reliable trend data

Several factors can impact accuracy:

Proper fit (the band should be snug but comfortable)
Placement on the wrist (slightly higher than the wrist bone)
Motion (measurements are most accurate during periods of limited movement)
Skin characteristics (tattoos may affect optical sensor readings)

The band employs signal validation and confidence scoring to identify and flag potentially unreliable measurements, ensuring that health insights are based on high-quality data.

Does the Band adjust for different skin tones or body types?

Yes, the Hume Band is designed to provide accurate readings across diverse skin tones and body types:

The optical sensors use multiple wavelengths and advanced algorithms that adjust for variations in skin pigmentation
Signal validation technology identifies and compensates for potential interference
Confidence scoring helps ensure that only high-quality readings contribute to health insights
The band's fit accommodates a wide range of wrist sizes for optimal sensor contact

Our validation testing includes diverse participant groups to ensure consistent performance across different skin tones, body compositions, and anatomical variations.

For optimal accuracy, ensure the band is worn with the proper fit - snug enough for good sensor contact but not so tight as to restrict circulation.

Do I need a premium subscription to use the Band?

No, you do not need a premium subscription to use the Hume Band. All users receive access to:

Core metrics tracking: heart rate, HRV, SpO2, sleep stages
Daily Metabolic Capacity score
Cardiovascular Health Score
Metabolic Momentum score
Strain and Recovery tracking
Sleep quality and debt measurements
Basic My Day guidance
Standard recommendations

Premium subscribers gain access to enhanced features:

Detailed cardiovascular health breakdowns
Comprehensive Metabolic Momentum Report
Metabolic Trajectory: long-term projections
Physiological Age calculations
Pro.f AI Discovery experiments
Advanced My Day optimization
Extended historical data and trend analysis
Richer, more personalized AI communications

The free tier provides a complete experience with all fundamental health metrics and algorithms, while premium enhances the depth of insights and personalization.

What kind of recommendations does the Band’s AI system provide?

Pro.f, the Band's AI system, provides several types of recommendations:

Daily Activity Recommendations: Personalized targets for steps, active minutes, and heart rate zones based on your current metabolic capacity.
Recovery Optimization: Specific recovery protocols to address unrecovered strain, including active recovery, relaxation techniques, and sleep improvements.
Sleep Timing Guidance: Recommended bedtimes based on your sleep debt and wake time preferences.
Activity Timing: Optimal windows for different types of activity based on your chronotype and recovery patterns.
AI Discoveries (Premium): Experimental recommendations designed to test hypotheses about your unique physiology and accelerate personalization.
Strain Management: Guidance on appropriate activity levels based on your current recovery status.
Weekly Focus Areas: Suggested emphasis on specific aspects of metabolic health based on recent patterns.

Recommendations adapt to your goals (weight loss, muscle gain, cardiovascular health, longevity, etc.) and are delivered with appropriate context for your selected technical level.

"Pro.f uses a multi-stage AI processing system optimized specifically for physiological data analysis: Core Architecture:"

Ensemble neural networks trained on cardiovascular and metabolic datasets
Transformer-based language models for generating personalized insights and recommendations
Edge computing for real-time signal processing on the device
Cloud-based analysis for complex pattern recognition and longitudinal health modeling

What Makes It Specialized:

Custom-trained on physiological time-series data rather than general datasets
Designed specifically for wrist-based PPG signal processing and HRV analysis
Integrates multiple data streams (heart rate, sleep, activity, body composition) simultaneously

Proprietary Elements: While we use established AI architectures as foundations, our specific training datasets, signal processing algorithms, and health scoring models are proprietary to ensure competitive advantage and protect years of physiological research investment.

Validation Approach: Our AI systems are validated against clinical standards and continuously refined based on real-world performance data.

How are the AI recommendations generated?

The AI recommendations are generated through a sophisticated process:

Data Collection: The band continuously collects physiological data including heart rate, HRV, sleep metrics, and activity patterns.
Pattern Recognition: Pro.f identifies your unique physiological patterns, establishing baselines and recognizing deviations.
Contextual Analysis: Your data is analyzed in context of your age, goals, previous activities, and metabolic capacity.
Evidence-Based Assessment: Recommendations draw from established scientific research in longevity, exercise physiology, and sleep science.
Personalization Layer: For premium users, Pro.f applies a deeper personalization layer based on your historical response patterns to different interventions.
Metabolic State Adaptation: All recommendations adjust based on your current metabolic capacity, strain levels, and recovery status.
Natural Language Processing: Technical insights are translated into accessible language at your preferred level of detail.

This system creates recommendations that are scientifically sound while being specifically tailored to your unique physiology and goals.

Why did my recommendation disappear after I viewed it?

Recommendations in the Hume app have different display durations based on their type:

Daily recommendations typically refresh every 24 hours, replacing previous guidance as your metabolic state changes.
Time-sensitive recommendations (like optimal workout windows) disappear after the relevant time period has passed.
Completed recommendations are automatically archived once you've marked them as complete.
Superseded recommendations may be replaced when new, more relevant guidance becomes available based on your latest data.

You can view your recommendation history by:

This approach ensures you always see the most relevant and timely guidance rather than outdated information.

Can I view past recommendations again?

Yes, you can always check your past recommendations in the app’s history section, so nothing’s really lost—just updated to keep things fresh and helpful.

How often will I receive new AI recommendations?

The frequency of AI recommendations depends on several factors:

Base Recommendation Schedule:

Daily activity targets refresh each morning
Sleep recommendations update daily
Recovery guidance appears after detected strain

Additional Recommendations Based On:

Significant changes in your metrics
Detection of new patterns
Progress toward goals
Completion of previous recommendations

Premium vs. Free:

Free users: 3-5 recommendations per week
Premium users: 5-10 recommendations per week, including specialized Pro.f AI Discoveries

The system is designed to provide timely, relevant guidance without overwhelming you with notifications.

Do I need to do anything to get personalized recommendations from the AI?

To receive the most personalized recommendations from Pro.f AI:

Wear your band consistently, especially during sleep, to establish baseline patterns
Provide feedback on recommendations when prompted, which helps refine future guidance
Keep your profile information updated (weight, goals, technical knowledge preference)

The personalization process begins immediately but improves significantly after:

3-4 days of continuous wear for basic personalization
7-10 days for more refined recommendations
2-3 weeks for advanced pattern recognition

Premium users can accelerate this process through Pro.f AI Discoveries, which are designed to quickly identify your unique physiological patterns.

Are the AI insights based on my personal data or general trends?

Pro.f AI insights are created using a combination of your personal data and scientific research:

Personal Data Analysis: Pro.f analyzes your specific physiological patterns, including:

Your unique heart rate and HRV variations
Your individual sleep architecture
Your personal recovery patterns
Your historical responses to different activities

Contextual Personalization: These patterns are interpreted in the context of:

Your stated goals
Your age and other profile information
Your activity history
Your metabolic capacity trends
Your Body Composition (when available via your Hume Pod)

Scientific Foundation: Personal insights are grounded in:

Established longevity research
Exercise physiology principles
Sleep science
Cardiovascular health research

For premium users, the personalization is more extensive, incorporating longer-term pattern analysis and utilizing Pro.f AI Discoveries to accelerate understanding of your unique physiology.

The result is guidance that's scientifically valid while being specifically relevant to your body and goals.

Can I turn AI recommendations off or customize them?

Yes, you can partially customize the AI recommendations based on your preferences and goals:

Pro.f naturally customizes based on your goals, selections, behaviors and performance. The AI system learns your physiological patterns and adapts recommendations accordingly without requiring manual configuration.

While direct control over recommendation types or frequency is not available at this time, Pro.f does tailor its guidance based on:

Your selected health goals during onboarding
Your activity patterns and physiological responses
Your progress toward established targets
Which recommendations you've completed in the past

We may add further customization options in the future as the system evolves.

What are the Band’s sizing options (length and width)?

270mm x 20mm

Is the Band adjustable, and does it include a clasp or buckle?

Yes! The band has an adjustable strap for a customizable fit for your comfort and rest assured our metal clasp provides a secure closure and ease of use.

What materials is the Band made of?

Nylon with a metal clasp.

What wrist sizes is the Band compatible with?

Our band has an adjustable strap to fit your wrist comfortably.

What color options are available?

We currently have the band available to purchase in black.

What is the battery life of the Band?

The Hume Band offers up to 4 to 5 days of battery life under typical usage conditions. However, actual battery life varies based on several factors:

Continuous heart rate monitoring reduces battery life to approximately 4-5 days
Using SpO2 monitoring during sleep reduces battery life by about 15%
More frequent syncing with the app uses additional power

The app provides battery status indicators and will notify you when the battery level falls below 20%. A full charge typically takes about 30 minutes.

For optimal battery performance, we recommend charging the band when battery falls below 20%, avoiding frequent partial charges.

How long should I charge the Band for?

For optimal charging of your Hume Band:

A full charge typically takes 30 minutes from 0% to 100%
A quick 10-minute charge will provide approximately 30-40% battery capacity
The band will display a charging indicator when properly connected
The app will show the current battery percentage when synced during charging

To extend battery lifespan, we recommend:

Charging before the battery falls below 10%
Removing the band from the charger once it reaches 100%
Using only the provided charging cable
Avoiding exposure to extreme temperatures during charging

Once fully charged, the band will automatically stop drawing power to prevent overcharging.

How often should I sync my Band with the app?

We recommend syncing your Hume Band with the app at least once daily for optimal performance. The band automatically attempts to sync:

When you open the app
When you complete a significant activity
After a sleep period
When prompted by certain band interactions

More frequent syncing (2-3 times daily) ensures:

Your data is backed up regularly
Real-time insights remain current
Recommendations stay relevant to your latest metrics
Battery usage is optimized

However, the band can store up to 7 days of data locally if you're unable to sync regularly.

Which phones and operating systems are compatible with the Band?

The Hume Band is compatible with:

iOS Devices:

iPhone 8 and newer
iOS 14.0 and above

Android Devices:

Android 8.0 (Oreo) and above
Devices with Bluetooth 4.2 or newer
2GB RAM minimum (4GB recommended)

Technical Requirements:

Bluetooth Low Energy (BLE) capability
Location services enabled for proper Bluetooth functionality
100MB free storage space for the Hume app

For optimal performance, we recommend:

iOS 15 or higher / Android 10 or higher
Keeping your phone's operating system updated
Enabling background app refresh for the Hume app

The app and band firmware are regularly updated to support newer devices and operating systems.

Why aren’t my Band metrics showing up in Apple Health or Google Fit?

There are several possible reasons why your Hume Band metrics may not be appearing in Apple Health or Google Fit:

Health App Integration Settings:

Open the Hume app > Me > Connected Apps
Ensure Apple Health/Google Fit integration is toggled on
Verify you've authorized all relevant data categories

Synchronization Timing:

Data typically syncs to health platforms after being processed in the Hume app
This may take up to 30-60 minutes after syncing your band

Data Categories:

Check which specific metrics are selected for sharing
Not all Hume metrics have direct equivalents in Apple Health/Google Fit

App Permissions:

Visit your phone's Settings > Privacy > Health/Fit
Ensure the Hume app has permission to write data

Data Conflicts:

If you use multiple devices, priority settings may favor other data sources

For unresolved issues, try:

Turning integration off and on again
Unpairing and repairing your band
Checking for app updates

Currently, specialized metrics like Metabolic Capacity and Momentum don't have direct equivalents in health platforms and may only be viewable in the Hume app.

Can I export my data from the app?

Coming Soon

What should I do if the Band isn’t syncing with my app?

If your Hume Band isn't syncing with the app, try these troubleshooting steps in sequence:

Basic Connectivity Checks:

Ensure Bluetooth is enabled on your phone
Verify the band is charged (at least 20% battery)
Check that your phone is within 30 feet (10 meters) of the band

App Restart:

Force close the Hume app
Reopen and attempt to sync again

Band Restart:

Press and hold the band button for 10 seconds until it restarts
Wait for it to power back on, then try syncing

Connection Reset:

In the Hume app, go to Me > Paired Devices
Tap the broken chain icon for your Hume Band
Confirm "Forget Device"
Re-pair the band following the standard connection process

Phone Troubleshooting:

Toggle Bluetooth off and on
Restart your phone
Ensure location services are enabled (required for the Hume Band)
Verify that the Hume App has access to Bluetooth under the phone's General Settings > Apps > Hume

App Updates:

Check for Hume app updates in your app store
Ensure you're running the latest version

If these steps don't resolve the issue, please contact Hume Support with your device model, operating system version, and app version for further assistance.

How can I clean my Band?

Use a cloth to wipe your band as and when needed.

Can I buy a Band without buying the Hume Pod?

Yes

How long does shipping take?

3-5 business days

What are the specifications for the warranty?

You can find our PDF available on the Band page which outlines the specifications for our warranty.

What if I forget to add the warranty with my Band purchase?

Not to worry! You can purchase our standalone warranty separately on our Band page.

What is your return or exchange policy?

We stand behind your product but it may not meet your requirements, in this case you have a 45 day return window to return your band back to us, so long as the product is still in working order and with all the necessary components still intact to make the return.

How do I contact customer support if I need help?

You can contact us through Live Chat available on our website or email us at support@myhumehealth.com.

Is my health data secure?

Yes, your health data is secured through multiple protection layers:

Encryption:

All data is encrypted during transmission using TLS 1.3 protocols
Data stored on servers uses AES-256 encryption
Local data on your device is encrypted at rest

Access Controls:

Multi-factor authentication options for account access
Role-based access within our systems
Regular security audits and access reviews

Data Practices:

Data is pseudonymized in our systems
Clear data retention policies are outlined in our privacy policy
You maintain control over data sharing preferences

Compliance:

Our systems adhere to industry standards for health data protection
Regular third-party security assessments
Continuous monitoring for potential vulnerabilities

User Control:

Option to delete historical data
Granular control over which data is collected
Transparency about how your data is used

Your health information is never sold to third parties, and any use for research purposes is only with explicit consent and in anonymized form.

Who has access to my data?

You: Through the app and data export options
Authorized Hume Technical Team: Limited staff with specific roles who maintain the system
Pro.f AI System: Processes your data to generate insights
Third-party services: Only when necessary for specific functions you've enabled (like Apple Health integration)

Is my data safe with AI?

Yes. Hume employs multiple layers of AI Data Safety:

Local Processing: Many AI operations happen directly on your device
Data Minimization: Only relevant data points are used for analysis
Purpose Limitation: Your data is used solely for generating your personal insights
No External Training: Your personal data is not used to train AI systems for other users
Explainable AI: The system can provide reasoning behind recommendations
Human Oversight: AI systems are regularly audited by our data science team

Your individual data is not accessible to other users, and aggregated, anonymized data is only used for improving the system's overall performance with strict safeguards in place. Hume maintains comprehensive access controls, regular security audits, and follows leading industry practices for data protection.

Sensor Technology Reference

1. Photoplethysmography — Optical Pulse Detection

Photoplethysmography (PPG) is an optical sensing technique that detects changes in light absorption caused by blood volume changes in the microvasculature beneath the skin. The Hume Band emits light from LEDs into skin tissue and measures how much light returns to a photodetector after passing through or reflecting from the tissue. Because oxygenated hemoglobin in blood absorbs light at characteristic wavelengths, and because the volume of blood in the capillary bed changes with each cardiac cycle, the returning light intensity oscillates synchronously with the pulse.

The Band uses green light (approximately 520–550 nm) for heart rate detection during movement, because green wavelengths are absorbed strongly by hemoglobin while being relatively insensitive to ambient light and motion artifacts in comparison to red or infrared wavelengths. Red (660 nm) and infrared (880–940 nm) LEDs are used for SpO2 measurement, which requires the differential absorption ratio between two wavelengths. The raw PPG signal is a waveform whose peaks and troughs correspond to systole and diastole in each cardiac cycle.

Allen, J. (2007). Photoplethysmography and its application in clinical physiological measurement. Physiological Measurement, 28(3), R1–R39. https://doi.org/10.1088/0967-3334/28/3/R01

Scope note: The most comprehensive review of PPG technology and applications available in the peer-reviewed literature. Covers optical principles, LED wavelength selection, photodetector design, signal components (AC pulse waveform, DC baseline, motion artifacts), and the full range of physiological parameters derivable from a PPG signal. Documents the physical basis for every PPG-derived metric the Hume Band produces. The signal processing architecture described in this review directly underpins the Band's optical measurement design.

Tamura, T., Maeda, Y., Sekine, M., & Yoshida, M. (2014). Wearable photoplethysmographic sensors — past and present. Electronics, 3(2), 282–302. https://doi.org/10.3390/electronics3020282

Scope note: Reviews the design evolution of wearable PPG sensors from clinical clip-style devices to continuous wrist-worn form factors. Covers the engineering tradeoffs specific to wrist PPG: LED placement, contact pressure sensitivity, ambient light rejection, and motion artifact suppression via accelerometer fusion. The motion-correction architecture described here — using simultaneous accelerometer data to filter movement artifacts from the optical signal — is the approach underlying the Band's activity-mode heart rate accuracy.

2. Heart Rate Derivation from PPG

Heart rate is derived from the PPG waveform by detecting the interval between successive pulse peaks (the peak-to-peak interval, or PPI). The inverse of the mean PPI over a measurement window, expressed in beats per minute, is the heart rate. In practice, raw PPG peaks are noisy — motion artifacts, contact variation, and signal baseline drift produce false peaks and missed peaks — so the Band applies signal processing algorithms to clean the waveform before peak detection.

The primary challenge in wrist PPG heart rate measurement is motion artifact, which generates frequency components in the same range as typical heart rate (0.5–4 Hz, corresponding to 30–240 bpm). The Band addresses this through adaptive filtering that uses simultaneous 3-axis accelerometer data to model and subtract motion-induced optical noise from the PPG signal before peak detection. The quality of heart rate estimates during vigorous exercise therefore depends on both the optical signal and the motion model's accuracy for the specific movement pattern being performed.

Parak, J., & Korhonen, I. (2014). Evaluation of wearable consumer heart rate monitors based on photopletysmography. Proceedings of the 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 3670–3673. https://doi.org/10.1109/EMBC.2014.6944419

Scope note: Systematic evaluation of consumer PPG heart rate monitors under rest and structured exercise conditions. Documents accuracy degradation during high-intensity activities and the specific movement types (wrist flexion, rowing, cycling) that most severely corrupt wrist PPG signals. Provides the empirical basis for the Band's accuracy disclosures under different activity modes and the rationale for activity-specific algorithm selection.

Gillinov, S., Etiwy, M., Wang, R., Blackburn, G., Phelan, D., Gillinov, A. M., Houghtaling, P., Javadikasgari, H., & Desai, M. Y. (2017). Variable accuracy of wearable heart rate monitors during aerobic exercise. Medicine & Science in Sports & Exercise, 49(8), 1697–1703. https://doi.org/10.1249/MSS.0000000000001284

Scope note: Controlled comparison of wrist-worn PPG heart rate monitors against ECG during treadmill, cycling, and elliptical exercise. Mean absolute error ranged from 0.0 to 14.0 bpm across devices and exercise modes, with worst performance during activities with high wrist motion components. This study provides the empirical basis for the Band's exercise-mode accuracy context and the decision not to claim clinical accuracy for heart rate during high-intensity mixed-movement exercise.

3. Heart Rate Variability from PPG-Derived Intervals

Heart rate variability (HRV) measures the variation in the time interval between successive heartbeats. True HRV is computed from the R-R intervals (RRI) of an electrocardiogram (ECG), which marks the precise timing of ventricular depolarization. PPG-derived HRV uses the peak-to-peak interval (PPI) of the optical waveform as a surrogate for RRI. Because the PPG waveform peak slightly lags the ECG R-wave (due to pulse transmission time from heart to wrist), the absolute PPI values differ from RRI values. However, the variability of the PPI series — the quantity used to compute HRV metrics — closely tracks RRI variability under resting conditions.

The Band computes RMSSD (root mean square of successive differences between adjacent intervals) from the PPI series. RMSSD is the short-term HRV metric most closely associated with parasympathetic autonomic tone and is the metric least affected by the slight timing offset between PPG peak and ECG R-wave. Under resting, low-motion conditions, PPG-derived RMSSD is a valid approximation of ECG-derived RMSSD. Under movement conditions, motion artifacts corrupt PPI series reliability, which is why the Band restricts HRV reads to rest and sleep contexts.

Schafer, A., & Vagedes, J. (2013). How accurate is pulse rate variability as an estimate of heart rate variability? A review on studies comparing photoplethysmographic technology with an electrocardiogram. International Journal of Cardiology, 166(1), 15–29. https://doi.org/10.1016/j.ijcard.2012.03.119

Scope note: Systematic review of 26 studies comparing PPG-derived PPI variability to ECG-derived RRI variability across rest, controlled movement, and clinical populations. Under resting conditions, PPG-derived RMSSD correlates strongly with ECG RMSSD (r > 0.90 in most studies). Agreement degrades during movement due to motion-induced PPI artifacts and is substantially reduced in atrial fibrillation, which disrupts PPG peak morphology. This review provides the empirical basis for the Band's restriction of HRV measurement to rest and sleep contexts, and for the disclosure that PPG HRV is a valid approximation, not a clinical ECG equivalent.

4. Blood Oxygen Saturation (SpO2) — Ratiometric Pulse Oximetry

Oxygenated hemoglobin absorbs infrared light (880–940 nm) strongly but red light (660 nm) weakly; deoxygenated hemoglobin does the reverse. By shining both red and infrared LEDs through tissue and measuring the pulsatile component of absorption at each wavelength, the device computes the ratio of pulsatile absorption at the two wavelengths (the R-ratio). This R-ratio is converted to SpO2 using a calibration curve derived from empirical data collected in human volunteers breathing controlled gas mixtures at known oxygen levels — the gold standard reference being co-oximetry of arterial blood samples. Wrist-worn SpO2 measurement faces greater challenges than fingertip pulse oximetry. The wrist site has lower capillary density, greater tissue depth between the sensor and blood vessels, and higher motion artifact susceptibility. These factors increase measurement noise and require longer averaging windows and more aggressive motion rejection to produce reliable estimates. The Band reports SpO2 as an overnight average derived from readings taken during sleep, when motion artifacts are minimized, rather than as a continuous real-time value.

Severinghaus, J. W., & Aoyagi, T. (2007). Discovery of pulse oximetry. Anesthesia & Analgesia, 105(6 Suppl), S1–S4. https://doi.org/10.1213/01.ane.0000269514.31987.21 Scope note: Historical and technical account of pulse oximetry's development by its inventor, including the derivation of the R-ratio method and its calibration against co-oximetry. Explains why the calibration curves embedded in pulse oximeters cannot be derived from the device alone and must be empirically established against arterial blood gas reference measurements in human volunteers. This is the foundational document for understanding the calibration architecture underlying all commercial pulse oximeters, including wrist-worn implementations.

Jubran, A. (1999). Pulse oximetry. Critical Care, 3(2), R11–R17. https://doi.org/10.1186/cc341 Scope note: Clinical review of pulse oximetry principles, accuracy, and limitations. Documents the sources of SpO2 measurement error: motion artifacts, low perfusion states, dark skin pigmentation (which can cause systematic underestimation), nail polish, and extreme vasoconstriction. The 95% confidence interval for well-functioning clinical fingertip oximeters is approximately ±2% SpO2 against co-oximetry; wrist devices carry wider intervals. These accuracy bounds inform the Band's SpO2 disclosure and the decision to surface overnight trends rather than real-time spot values.

5. Skin Temperature Sensing

The Hume Band measures skin surface temperature at the wrist using a thermistor — a semiconductor element whose electrical resistance changes predictably with temperature. Skin surface temperature at the wrist is not equivalent to core body temperature. Peripheral skin temperature is strongly influenced by ambient air temperature, blood flow to the extremities, and sympathetic nervous system activity, which causes vasoconstriction and vasodilation that alter cutaneous perfusion. Core body temperature is regulated within a narrow range (approximately 36.5–37.5°C orally), while wrist skin temperature can vary by 4–8°C depending on environmental and physiological conditions.

The Band's temperature metric therefore tracks relative change from an individual's established baseline rather than reporting an absolute temperature equivalent to an oral or tympanic measurement. Night-time temperature is emphasized because it is measured under the most consistent conditions — stable ambient temperature, reduced sympathetic activity during sleep, and minimal convective heat loss from movement. Overnight temperature trends are associated with menstrual cycle phase, immune response, and sleep quality in the research literature, which is the clinical context for the Band's temperature feature.

Refinetti, R., & Menaker, M. (1992). The circadian rhythm of body temperature. Physiology & Behavior, 51(3), 613–637. https://doi.org/10.1016/0031-9384(92)90188-8 Scope note: Comprehensive review of the human circadian temperature rhythm, establishing that core temperature follows a predictable ~24-hour sinusoidal pattern with a nadir approximately 2 hours before habitual wake time and a peak in the early evening. Peripheral skin temperature follows an inverse pattern to core temperature during sleep onset. These circadian dynamics explain why the Band uses overnight baseline rather than instantaneous reading, and why individual baseline tracking is more meaningful than comparing to population temperature norms.

Protsiv, M., Ley, C., Lankester, J., Hastie, T., & Bhattacharya, J. (2020). Decreasing human body temperature in the United States since the Industrial Revolution. eLife, 9, e49555. https://doi.org/10.7554/eLife.49555

Scope note: Documents a secular decline in mean human body temperature of approximately 0.03°C per decade across three US historical cohorts from 1860 to 2017, with a current population mean of approximately 36.6°C — below the long-held 37.0°C standard. High interindividual variability in baseline temperature means that population norms are poor anchors for individual assessment. This is the primary justification for the Band's individual baseline tracking approach to temperature, rather than comparison to a population absolute threshold.

6. Inertial Measurement — Accelerometry and Step Detection

The Hume Band contains a 3-axis accelerometer and a gyroscope, collectively referred to as an inertial measurement unit (IMU). The accelerometer measures linear acceleration along three orthogonal axes (vertical, mediolateral, and anteroposterior) at a sampling rate sufficient to capture the frequency content of human movement (typically 25–200 Hz for activity recognition). The gyroscope measures angular velocity — the rate of rotation around each axis — which complements linear acceleration for orientation and gesture recognition. Step detection uses the characteristic acceleration signature of human gait: a repeating vertical acceleration impulse with each footfall that produces a recognizable waveform at 1–3 Hz under typical walking and running cadences. The Band's algorithm identifies peaks in the vertical acceleration signal that exceed a threshold and are separated by intervals consistent with human stride timing, while rejecting non-periodic movements that produce similar single-axis acceleration without the stride periodicity. Sleep stage estimation combines accelerometer-derived movement data with heart rate and HRV signals to classify movement (wake), low-variability signals (light sleep), and HRV-associated patterns (REM and deep sleep).

Troiano, R. P., Berrigan, D., Dodd, K. W., Mâsse, L. C., Tilert, T., & McDowell, M. (2008). Physical activity in the United States measured by accelerometer. Medicine & Science in Sports & Exercise, 40(1), 181–188. https://doi.org/10.1249/mss.0000000000001248

Scope note: NHANES-based population study measuring physical activity via research-grade hip accelerometry in 6,329 adults and children. Establishes accelerometer count thresholds for sedentary, light, moderate, and vigorous activity intensity, which have become standard reference cut-points for population physical activity research. The activity intensity classifications the Band uses are grounded in these thresholds, adapted for the wrist placement and continuous monitoring context.

Kaplan, R. F., Wang, Y., Loparo, K. A., Kelly, M. R., & Bootzin, R. R. (2012). Performance evaluation of an automated single-channel sleep-wake detection algorithm. Nature and Science of Sleep, 4, 127–136. https://doi.org/10.2147/NSS.S35769

Scope note: Validation of wrist actigraphy algorithms for sleep-wake classification against polysomnography (PSG), the reference standard. Demonstrates that accelerometer-based sleep staging achieves approximately 85–90% epoch-level accuracy for sleep/wake classification in normal adults, with greater difficulty distinguishing NREM stages from one another. This accuracy boundary informs the Band's sleep stage display, which emphasizes the sleep/wake and REM boundaries where actigraphy is most reliable, and contextualizes deep and light NREM estimates as estimates rather than clinically precise staging.

7. VO₂max Estimation from Wearable Signals

nd is determined by direct cardiopulmonary exercise testing (CPX) with expired gas analysis in a clinical or laboratory setting. Wearable devices cannot measure oxygen consumption directly. Instead, they estimate VO₂max from the relationship between heart rate and exercise intensity, using models that infer submaximal exercise capacity and extrapolate to the maximal effort level. The Band's VO₂max estimation uses a submaximal prediction model that takes the heart rate response to a known physical workload and fits it to a linear HR-to-VO₂ relationship, extrapolated to the age-predicted heart rate maximum. This approach has been validated in research settings and is used in consumer wearables broadly. Its primary source of error is the variability in age-predicted maximum heart rate (±10–12 bpm for the standard 220-minus-age formula), which propagates into VO₂max estimate error of approximately ±3–5 mL/kg/min under optimal conditions, and higher under suboptimal conditions such as emotional stress, caffeine, or non-steady-state exercise. For this reason, the Band reports VO₂max as a tier range rather than a precise value, with tier widths calibrated to absorb typical estimation uncertainty. Sartor, F., de Morree, H. M., Matschke, V., Marcora, S. M., Mikulic, P., & Wessner, B. (2013). High-intensity exercise and carbohydrate-reduced energy-restricted diet in obese individuals. Journal of Sports Sciences, 31(14), 1563–1571. https://doi.org/10.1080/02640414.2013.792943

Scope note: Examines submaximal VO₂max estimation accuracy in populations differing from standard athletic cohorts. Submaximal estimation models derived from fit populations systematically overestimate VO₂max in deconditioned individuals and those with abnormal HR responses to exercise. This limits the Band's VO₂max accuracy in users at the lower end of the fitness distribution — a population for whom precise tracking of improvement over time is more informative than any single estimate.

Tanaka, H., Monahan, K. D., & Seals, D. R. (2001). Age-predicted maximal heart rate revisited. Journal of the American College of Cardiology, 37(1), 153–156. https://doi.org/10.1016/S0735-1097(00)01054-8

Scope note: Meta-analysis of 351 studies (n = 18,712) establishing that the population mean age-predicted maximum heart rate is better described by 208 − (0.7 × age) than the widely used 220 − age formula. The revised formula has lower systematic bias but similar standard deviation (approximately ±10–12 bpm), confirming that individual HRmax variability is the primary driver of submaximal VO₂max estimation error regardless of which formula is used. The Band's tier-based VO₂max reporting is sized to accommodate this individual variability.

Hume Band Metrics

1. Daily Steps

Paluch, A. E., Bajpai, S., Bassett, D. R., Carnethon, M. R., Ekelund, U., Evenson, K. R., et al. (2022). Daily steps and all-cause mortality: a meta-analysis of 15 internationalcohorts. Lancet Public Health, 7(3), e219–e228. https://doi.org/10.1016/S2468-2667(21)00302-9 Scope note: Harmonized meta-analysis of 15 cohorts. Risk reduction begins at approximately 2,500 steps/day; plateaus near 7,000–8,000 steps/day, with a lower plateau (≈6,000 steps/day) in adults ≥60 years. Primary source for step tier lower and upper breakpoints

Stens, N. A., Bakker, E. A., Mañas, A., Buffart, L. M., Ortega, F. B., Lee, D. C., Thompson, P. D., Thijssen, D. H. J., & Eijsvogels, T. M. H.(2023). Relationship of daily step counts to all-cause mortality and cardiovascular events. Journal of the American College of Cardiology, 82(15), 1483–1494. https://doi.org/10.1016/j.jacc.2023.07.029 Scope note: Meta-analysis (n = 111,309). Optimal mortality benefit at 8,763 steps/day; optimal CVD benefit at 7,126 steps/day. Confirms that step cadence (intensity) provides independent benefit beyond volume. Informs upper-tier breakpoints and the app’s cadence context alongside volume.

2. Sleep Duration and Sleep Architecture

Hirshkowitz, M., Whiton, K., Albert, S. M., Alessi, C., Bruni, O., DonCarlos, L., Hazen, N., Herman, J., Katz, E. S., Kheirandish-Ghodssi, L., Neubauer, D. N., O’Donnell, A. E., Ohayon, M., Peever, J., Rawding, R., Sachdeva, R. C., Setters, B., Vitiello, M. V., Ware, J. C., & Adams Hillard, P. J (2015). National Sleep Foundation’s sleep time duration recommendations: methodology and results summary. Sleep Health, 1(1), 40–43. https://doi.org/10.1016/j.sleh.2014.12.010 Scope note: NSF evidence review establishing recommended sleep duration by age group. Adults (18–64): 7–9 hours recommended; older adults (≥65): 7–8 hours recommended. Anchors sleep duration tier breakpoints.

Ohayon, M. M., Carskadon, M. A., Guilleminault, C., & Vitiello, M. V.

(2004). Meta-analysis of quantitative sleep parameters from childhood to old age in healthy individuals: developing normative sleep values across the human lifespan. Sleep, 27(7), 1255–1273. https://doi.org/10.1093/sleep/27.7.1255

Scope note: Meta-analysis of 65 polysomnography studies (n = 3,577; ages 5–102). Primary source for sleep architecture tier breakpoints. Age-related normative patterns: slow-wave sleep (deep sleep) declines progressively; REM declines moderately; stage 1 and 2 increase; wake after sleep onset increases approximately 10 minutes per decade from age 30 to 60, then stabilizes

Ohayon, M. M., Carskadon, M. A., Guilleminault, C., & Vitiello, M. V.(2004). Meta-analysis of quantitative sleep parameters from childhood to old age in healthy individuals: developing normative sleep values across the human lifespan. Sleep, 27(7), 1255–1273. https://doi.org/10.1093/sleep/27.7.1255

Scope note: Meta-analysis of 65 polysomnography studies (n = 3,577; ages 5–102). Primary source for sleep architecture tier breakpoints. Age-related normative patterns: slow-wave sleep (deep sleep) declines progressively; REM declines moderately; stage 1 and 2 increase; wake after sleep onset increases approximately 10 minutes per decade from age 30 to 60, then stabilizes

3. Heart Rate

Ostchega, Y., Porter, K. S., Hughes, J., Dillon, C. F., & Nwankwo, T.Ostchega, Y., Porter, K. S., Hughes, J., Dillon, C. F., & Nwankwo, T.
https://www.cdc.gov/nchs/data/nhsr/nhsr041.pdf

Scope note: NHANES normative sample (n = 35,302) providing US population percentiles for resting pulse rate by age and sex. Adult mean plateaus at approximately 72 bpm. Primary source for resting heart rate tier breakpoints.

Avram, R., Tison, G. H., Aschbacher, K., Kuhar, P., Vittinghoff, E., Butte, A., Marcus, G. M., Pletcher, M. J., & Olgin, J. E(2019). Real-world heart rate norms in the Health eHeart study. npj Digital Medicine, 2, 58. https://doi.org/10.1038/s41746-019-0134-9

Scope note: Wearable PPG study (n = 66,788). Mean RHR approximately 65 bpm; women average approximately 4 bpm higher than men. Validates NHANES data in the wearable-measurement context of the Hume Band.

Stehlik, J., et al.(2020). Inter- and intraindividual variability in daily resting heart rate and its associations with age, sex, sleep, BMI, and time of year: Retrospective, longitudinal cohort study of 92,457 adults. PLOS ONE, 15(2), e0227709. https://doi.org/10.1371/journal.pone.0227709

Scope note:Wearable cohort (n = 92,457; median 320 days/subject). Range 40–109 bpm across all individuals. Demonstrates that intraindividual RHR is substantially more stable than interindividual variation. Supports using a rolling average rather than a spot value for tier classification.

4. Heart Rate Variability (HRV)

Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology.(1996). Heart rate variability: standards of measurement, physiological interpretation and clinical use. Circulation, 93(5), 1043–1065. https://doi.org/10.1161/01.CIR.93.5.1043

Scope note: The foundational standards document for HRV measurement and interpretation. Defines RMSSD, SDNN, LF/HF, and other metrics. Establishes RMSSD as the primary short-term parasympathetic indicator and SDNN as the primary measure of overall autonomic variability. These two metrics are the basis for the Band’s HRV tiers.

Nunan, D., Sandercock, G. R. H., & Brodie, D. A.(2010). A quantitative systematic review of normal values for short-term heart rate variability in healthy adults. Pacing and Clinical Electrophysiology, 33(11), 1407–1417. https://doi.org/10.1111/j.1540-8159.2010.02841.x

Scope note: Systematic review of 44 studies (n = 21,438). Cross-study means: SDNN 50 ms (range 32–93 ms); RMSSD 42 ms (range 19–75 ms). Primary reference values for HRV tier breakpoints. The large interindividual variability (up to 260,000% for spectral measures) is why the Band emphasizes personal-baseline trending with population norms as secondary context.

Voss, A., Schroeder, R., Heitmann, A., Peters, A., & Perz, S(2015). Short-term heart rate variability—influence of gender and age in healthy subjects. PLOS ONE, 10(3), e0118308. https://doi.org/10.1371/journal.pone.0118308

Scope note: HRV analysis in 1,906 healthy adults (ages 25–74). Women under age 55 have higher RMSSD and HF power than age-matched men; sex difference narrows after age 55. Provides the age-sex stratification for HRV tier adjustment.

5. Stress Level

16. Stress Level The Hume Band stress level metric is a composite score derived from HRV suppression, elevated resting heart rate relative to personal baseline, and movement-adjusted autonomic indicators. There is no single population norm study for a composite wearable stress score. The scientific basis is grounded in the established relationship between autonomic nervous system activity and psychological and physiological stress, documented in the following references.

Task Force of the European Society of Cardiology(1996). (Full citation under Section‧15.)

Scope note: Establishes the physiological basis: psychological and physiological stress suppresses parasympathetic (HRV-mediated) autonomic tone and elevates sympathetic drive, which is measurable via reduced RMSSD and elevated LF/HF ratio.

Shaffer, F., & Ginsberg, J. P.(2017). An overview of heart rate variability metrics and norms. Frontiers in Public Health, 5, 258. https://doi.org/10.3389/fpubh.2017.00258

Scope note: Overview of HRV metrics used as physiological stress indicators, including the relationship between reduced HRV and elevated allostatic load. Confirms that RMSSD-based stress estimation is scientifically grounded. The Band’s stress tiers reflect deviations from the user’s personal HRV/HR baseline rather than population comparisons, consistent with the guidance in this review that individual baseline tracking is more meaningful than absolute population thresholds for stress assessment.

6. Blood Oxygen Saturation (SpO2)

World Health Organization.(2011). Pulse Oximetry Training Manual. WHO/NMH/VIP/01.11. Geneva: WHO. Available: https://www.who.int/patientsafety/safesurgery/pulse_oximetry/en/

Scope note: Establishes the internationally recognized normal SpO2 range at sea level: 95–100%. Values of 94% or below warrant clinical attention; 90% or below indicates hypoxemia. These three thresholds anchor the SpO2 tiers. Altitude affects SpO2 readings; the Band should surface a contextual note when the user’s elevation is consistently above 1,500m.

7. Body Temperature

Mackowiak, P. A., Wasserman, S. S., & Levine, M. M.(1992). A critical appraisal of 98.6°F, the upper limit of the normal body temperature, and other legacies of Carl Reinhold August Wunderlich. JAMA, 268(12), 1578–1580. https://doi.org/10.1001/jama.1992.03490120092034

Scope note: Updated the Wunderlich 37.0°C (98.6°F) standard using 700 healthy adults. Found mean oral temperature of 36.8°C (98.2°F) with 37.7°C (99.9°F) as the upper limit of normal. Reference for absolute normal range breakpoints. The Band measures peripheral skin (wrist) temperature, which is typically 2–4°C lower than oral and is surfaced as an overnight baseline trend rather than an absolute clinical value.

Protsiv, M., Ley, C., Lankester, J., Hastie, T., & Bhatthācharya, J(2020). Decreasing human body temperature in the United States since the Industrial Revolution. eLife, 9, e49555. https://doi.org/10.7554/eLife.49555

Scope note: Longitudinal analysis of body temperature across three US historical cohorts (1860–2017) demonstrating a decline of approximately 0.03°C per decade, with a modern mean of approximately 36.6°C. Context for why the Band emphasizes individual baseline trending over fixed absolute thresholds: the population mean has drifted and interindividual variation is substantial.

8. Blood Pressure

Whelton, P. K., Carey, R. M., Aronow, W. S., Casey, D. E., Jr., Collins, K. J., Dennison Himmelfarb, C., DePalma, S. M., Gidding, S., Jamerson, K. A., Jones, D. W., MacLaughlin, E. J., Muntner, P., Ovbiagele, B., Smith, S. C., Jr., Spencer, C. C., Stafford, R. S., Taler, S. J., Thomas, R. J., Williams, K. A., Sr., Williamson, J. D., & Wright, J. T., Jr.(2018). 2017 ACC/AHA guideline for the prevention, detection, evaluation, and management of high blood pressure in adults. Journal of the American College of Cardiology, 71(19), e127–e248. https://doi.org/10.1016/j.jacc.2017.11.006

Scope note: 2017 ACC/AHA classification: normal (<120 /<80 mmHg), elevated (120–129/<80 mmHg), stage 1 hypertension (130–139/80–89 mmHg), stage 2 hypertension (≥140/≥90 mmHg). These thresholds anchor the BP tier labels.

Mukkamala, R., Hahn, J. O., Inan, O. T., Mestha, L. K., Kim, C. S., Töreyin, H., & Kyal, S.(2015). Toward ubiquitous blood pressure monitoring via pulse transit time: theory and practice. IEEE Transactions on Biomedical Engineering, 62(8), 1879–1901. https://doi.org/10.1109/TBME.2015.2441951

Scope note: Establishes the theoretical and empirical basis for cuffless BP estimation from pulse transit time (PTT) and related waveform features. Demonstrates that cuffless methods have higher measurement uncertainty than cuff measurement, particularly in the short term, but can track within-individual BP trends effectively. Informs the app’s calibration approach: Band BP readings are estimates that track directional change within an individual’s own range; they require disclosure that they are not equivalent to cuff-based clinical measurement.

9. VO₂Max (Cardiorespiratory Fitness)

Kaminsky, L. A., Arena, R., & Myers, J(2015). Reference standards for cardiorespiratory fitness measured with cardiopulmonary exercise testing: data from the Fitness Registry and the Importance of Exercise National Database. Mayo Clinic Proceedings, 90(11), 1515–1523. https://doi.org/10.1016/j.mayocp.2015.07.026

Scope note: First US population-specific VO₂max reference data from direct CPX (n = 7,783; ages 20–79; 8 US laboratories). Provides percentile values by age decade and sex from treadmill testing. Primary source for VO₂max tier breakpoints.

Kaminsky, L. A., Arena, R., Myers, J., Peterman, J. E., Bonikowske, A. R., Harber, M. P., Medina Inojosa, J. R., Lavie, C. J., & Squires, R. W.(2022). Updated reference standards for cardiorespiratory fitness measured with cardiopulmonary exercise testing: data from the FRIEND registry. Mayo Clinic Proceedings, 97(2), 285–293. https://doi.org/10.1016/j.mayocp.2021.08.020

Scope note: Updated FRIEND registry standards (n = 22,379; 34 US laboratories; 1968–2021). Updated treadmill standards are 1.5–4.6 mL O₂·kg⁻¹·min⁻¹ lower than the 2015 standards, reflecting a more representative population. Current reference for VO₂max tier calibration. Sub-maximal wearable VO₂max estimation carries higher uncertainty than direct CPX; the app’s tier labels incorporate this by using wider confidence intervals at boundary zones.

Download pdf here

Study