Science & methodology
Biology is complex. A useful summary should make that complexity easier to explore, while keeping its assumptions and uncertainty in view.
The reporting language
Δ-years expresses a model output relative to chronological age. A positive value sits above that age reference; a negative value sits below it.
It does not measure years added to or removed from your life. A daily change does not establish irreversible aging, rejuvenation, or a change in lifespan.
Three connected perspectives
Adaptive BioAge brings together Behavioral Adaptation, Recovery, and Cardiometabolic contributions. Keeping the domains visible helps distinguish a recorded behavior from a physiological response and a more persistent pattern.
Behavioral Adaptation
Activity, nutrition, light exposure, alcohol, mindfulness, and related logged behaviors describe proximal exposures. A recorded behavior can change immediately; any physiological association may be delayed, nonlinear, bidirectional, or confounded.
Daily exposures
patterns across weeks
Recovery
Heart rate variability, resting heart rate, sleep, and aerobic fitness provide complementary context about autonomic regulation, restoration, and functional reserve. Some readings change from day to day; fitness generally requires a longer view.
Daily variation
with longer-term context
Cardiometabolic Anchors
Body mass index, systolic blood pressure, and a glucose anchor provide a longer-horizon reference for the daily model. Individual readings can vary, but their meaning is strongest when interpreted as repeated observations and trajectory over time. Together, they provide cardiometabolic context alongside faster-changing recovery and behavioral signals.
Repeated observations
over weeks and months
These are interpretation guides, not fixed biological deadlines. Measurement conditions and the specific input matter.
Under the model
The daily Cardiometabolic model uses a Klemera–Doubal-style approach with age-regressed, sex-aware parameters. It compares the input pattern with age-related relationships in a reference population.
Recovery and Behavioral Adaptation use weighted, standardized comparisons with reference values, including sex-stratified and age-band context. They are not themselves age-regression clocks. Their index contributions are translated into the app’s common Δ-years reporting language.
Relative weighting reflects the importance assigned to different inputs in the model. Outcome evidence can inform model rationale, but a published hazard ratio, relative risk, or intervention effect is not transferred directly into a BioMIR coefficient. A model weight is a design parameter, not a personal disease-risk percentage or causal effect estimate.
Data Confidence (shown as Completeness in ABA Trends) summarizes the weighted availability of expected daily inputs. CMA Freshness summarizes the recency of the BMI, systolic blood pressure, and glucose observations supporting the cardiometabolic estimate. High overall completeness can therefore coexist with older cardiometabolic anchors. Neither metric represents device accuracy, statistical confidence, or diagnostic certainty. In period views, BioMIR summarizes these data-quality measures separately from the selected clock statistic.
Reference-population differences, missing inputs, measurement error, observation recency, and model choices can affect the result. A precise-looking number should always be read with its contributors, Data Confidence, and CMA Freshness.
A separate laboratory perspective
These published methods add context from periodic laboratory records. They remain separate from the daily wearable and behavioral composite. Always check the laboratory date and underlying values.
KDM combines age-related information across a biomarker panel while accounting for statistical variation. Its output summarizes a physiological profile relative to a reference population.
Read the original methodClinical Phenotypic Age combines chronological age with nine laboratory biomarkers using an outcome-linked model. It is distinct from DNAm PhenoAge, the related DNA methylation model.
Read the PhenoAge researchEvidence for an established method does not automatically validate BioMIR’s implementation, daily composite, classifications, or changes in Δ-years. Those require separate evaluation.
Read the evidence in layers
Studies examine associations, mechanisms, and interventions under specific conditions. Their populations, endpoints, and study designs determine what can be concluded.
Reference selection, weighting, transformations, and aggregation shape the output. Scientific plausibility and a transparent design are valuable; external validation is a separate task.
N=1 observations can reveal repeatable personal patterns. They do not, by themselves, prove causation. Changes in devices, coverage, routines, and measurement timing can also explain a trend.
Compare the same input, time window, and statistic. Check Data Confidence, whether cardiometabolic values are current or carried forward, and the original measurement date. Look for a sustained pattern before attributing a result to an action.
Continue exploring