The Science

A number you can audit.

Your Physical Signal Score and CogniScore are deterministic fusion, not a black box — and we tell you exactly which parts are computed, estimated, or merely narrated.

Deterministic fusion

Domain signals are normalized, weighted, and combined by a fixed formula. The same inputs always produce the same two scores — independently verifiable.

InputsNormalized signalsEach domain scaled to a common 0–1 range with device-level provenance retained.
Fusion weighted sumFixed, published weights map signals → Physical + Cognitive sub-scores.
OutputTwo scores + R/A/GA Physical Signal Score and a CogniScore, each 0–100, each with a traffic light from published thresholds.

Biological-age context

Each employee receives a Physical Biological Age and a Brain Age alongside their two scores. Both use published, research-grounded methods — Klemera-Doubal (2006) and DunedinPACE (2022) — applied to measured inputs, never to a self-reported questionnaire. General-wellness context only; non-diagnostic, and never a clinical finding.

What's computed, estimated, or narrated

Every figure in the app carries its epistemic status. You always know how much to trust a number — and where the model's judgment begins and ends.

Deterministic

Deterministic

Computed by a fixed formula. Reproducible to the bit. No model judgment.

Physical Signal Score · CogniScore · R/A/G threshold

Estimated

Estimated

Statistical inference with a stated confidence band. Updates as data arrives.

Aerobic capacity estimate · age-norm percentile

Narrated

Narrated

Plain-language explanation of the numbers above. The LLM describes, it never decides.

Monthly summary · trend narration

The LLM only narrates. It turns the deterministic and estimated numbers into plain language. It cannot change a score, move a traffic light, or raise an alarm — those are computed, not generated.

Methodology you can put in front of a clinician.