ChatPPG.
Paper

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data (CoDaS)

Yubin Kim, Salman Rahman, Samuel Schmidgall, Chunjong Park, A. Ali Heydari, Ahmed A. Metwally +3 more
arXiv 2604.146152026wearable daily metricsText
arXiv Cite
PreprintFirst posted: Apr 16, 2026Added to atlas: Oct 11, 2026Source
Citations—Not available
GitHub stars—Not available
HF downloads—Not available

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

CoDaS is an AI co-data-scientist that proposes and checks candidate biomarkers from wearable data, combining multiple agents, fixed statistical tests, adversarial validation and literature grounding under human oversight. Across three cohorts with 9,279 participant-observations it flagged sleep-variability signals linked to depression and a steps-to-resting-heart-rate fitness index linked to insulin resistance (ρ = -0.374). In a review by 12 clinicians, validity ratings matched CoDaS confidence tiers (ρ = 0.67).

  • Data: 3 wearable cohorts, 9,279 participant-observations
  • Result: sleep-duration variability vs depression ρ = 0.252 (DWB)
  • Result: steps/resting HR vs insulin resistance ρ = -0.374
  • Evaluation: 12-clinician review
At a glance
Venue
arXiv 2604.14615 (2026-04-16; v2)
Published
2026
DOI
Not reported
arXiv
2604.14615 (opens in a new tab)
PMID
Not reported
Licence
Not reported
Signals
wearable daily metricsText
Form factor
Not reported
Subjects
Not reported
Code
Not reported
Added
Oct 11, 2026

Abstract

Wearable devices generate continuous physiological and behavioral data, but converting these signals into clinically reviewable biomarker hypotheses remains labor-intensive. We introduce CoDaS, an AI co-data-scientist that integrates multi-agent hypothesis generation, deterministic statistical analysis, adversarial validation and literature-grounded interpretation under human oversight. Across three wearable cohorts comprising 9,279 participant-observations, CoDaS prioritized candidate associations for mental-health and metabolic endpoints after internal checks for replication, stability, robustness and leakage. The system identified related circadian-instability signals associated with depression, including sleep-duration variability in DWB ( = 0.252, p < 0.001) and sleep-onset variability in GLOBEM ( = 0.126, p < 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate; = -0.374, p < 0.001). Adding these features to demographic models produced modest gains ( R^2 = 0.040 for depression, 0.021 for insulin resistance). In a 12-clinician review totaling approximately 25 active hours, clinician validity judgments aligned with CoDaS confidence tiers ( = 0.67, p = 0.005), whereas added clinical value and confidence to act were rated lower. CoDaS supports traceable, hypothesis-generating prioritization of wearable candidate biomarkers.

Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)

An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data (CoDaS): ChatPPG research summary card

How it works

How Method works: Setup → Method → ResultSetup: Data (3 wearable cohorts, 9,279 participant-observations). Method: Method (Language-aligned). Result: Result (sleep-duration variability vs depression ρ = 0.252 (DWB)); Result (steps/resting HR vs insulin resistance ρ = -0.374); Evaluation (12-clinician review).SetupData: 3 wearable cohorts, 9,279 participant-observationsData3 wearable cohorts, 9,279…MethodMethodLanguage-alignedResultResult: sleep-duration variability vs depression ρ = 0.252 (DWB)Resultsleep-duration variability vs…Result: steps/resting HR vs insulin resistance ρ = -0.374Resultsteps/resting HR vs insulin resistance…Evaluation: 12-clinician reviewEvaluation12-clinician review

Cite

@article{codasaicodatascientistwe2026,
  title = {{An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data (CoDaS)}},
  author = {Yubin Kim and Salman Rahman and Samuel Schmidgall and Chunjong Park and A. Ali Heydari and Ahmed A. Metwally and Hong Yu and Xin Liu and et al.},
  year = {2026},
  journal = {arXiv 2604.14615 (2026-04-16; v2)},
  eprint = {2604.14615}
}

History

  1. Added to the ChatPPG research hub

More on ChatPPG