Research
BioMIR’s research program asks whether interpretable, multidomain longitudinal measurement can characterize personal health trajectories more usefully between episodic assessments—and what evidence is required before stronger claims are justified.
Core research objectives
These are research questions, not established product claims. BioMIR separates scientific plausibility, implementation specification, and independent validation so each can be evaluated on its own evidence.
Determine whether sustained within-person changes in BioMIR trajectories can be distinguished from short-term biological and measurement variation, and whether those changes show prespecified relationships with independent physiological or clinical measures.
Test whether an interpretable longitudinal trajectory, contributor-level attribution, and visible data-quality context improve awareness of modifiable risk factors, sustained engagement, and preventive behavior without implying clinical efficacy.
Evaluate whether people can distinguish transient fluctuation from persistent trajectory, identify what is driving a change, and determine whether the framework adds useful information beyond isolated measurements and conventional risk-factor views.
Research architecture
The deterministic BioMIR engines remain the authoritative scientific computation. Future personalization and interpretive AI are downstream research layers and must demonstrate incremental value without obscuring provenance or changing the validated core.
Current research priority
Evaluate implementation fidelity, reliability, calibration, longitudinal responsiveness, missingness and freshness robustness, subgroup performance, and external validity using locked model versions and prespecified analyses.
Future research layer
Test whether downstream on-device or privacy-preserving federated learning adds reproducible value beyond the locked deterministic baseline while preserving provenance, drift control, privacy, and rollback.
Future research layer
Evaluate whether language-model and semantic interfaces can explain deterministic outputs with numerical fidelity, explicit provenance, safe handling of missing or stale data, and graceful fallback when AI is unavailable.
Go deeper
Validation
Review evidence boundaries, the current validation stage, public artifacts, validation questions, roadmap, and proposed independent study designs.
Research & ValidationCollaboration
Explore suitable cohorts, methods expertise, prospective studies, human-factors work, governance expectations, and ways to propose a research collaboration.
Research CollaborationBioMIR pairs a modeled age-equivalent contribution with a longitudinal persistence index: the proportion of qualified modeled days in High or Highest tiers, with fitted trends across prespecified periods. This is descriptive context, not disease probability or a validated clinical threshold. Independent studies must test repeatability, responsiveness and incremental information beyond the latest measurement and conventional averages, while separating held inputs from original observations and accounting for correlated repeated days. A 9 October 2026 draft amendment to the working v1.3 protocol specifies analytical checks, independent participant/time-forward evaluation, freshness sensitivity and human-factors endpoints; clinical and biostatistical review, preregistration and study execution remain pending.
The study plan freezes tiers, windows, denominator and version lineage. Clinical utility and any future referral thresholds require separate evidence and approval. Research collaborators can propose independently measured endpoints, acquisition schedules and participant-level external evaluation designs.