CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors
Abstract
Scientific discovery in digital health requires converting continuous physiological signals from wearable devices into clinically actionable biomarkers. We introduce CoDaS (AI Co-Data-Scientist), a multi-agent system that structures biomarker discovery as an iterative process combining hypothesis generation, statistical analysis, adversarial validation, and literature-grounded reasoning with human oversight using large-scale wearable datasets. Across three cohorts totaling 9,279 participant-observations, CoDaS identified 41 candidate digital biomarkers for mental health and 25 for metabolic outcomes, each subjected to an internal validation battery spanning replication, stability, robustness, and discriminative power. Across two independent depression cohorts, CoDaS surfaced circadian instability-related features in both datasets, reflected in sleep duration variability (DWB, \rho = 0.252, p < 0.001) and sleep onset variability (GLOBEM, \rho = 0.126, p < 0.001). In a metabolic cohort, CoDaS derived a cardiovascular fitness index (steps/resting heart rate; \rho = -0.374, p < 0.001), and recovered established clinical associations, including the hepatic function ratio (AST/ALT; \rho = -0.375, p < 0.001), a known correlate of insulin resistance. Incorporating CoDaS-derived features alongside demographic variables led to modest but consistent improvements in predictive performance, with cross-validated \Delta R^2 increases of 0.040 for depression and 0.021 for insulin resistance. These findings suggest that CoDaS enables systematic and traceable hypothesis generation and prioritization for biomarker discovery from large-scale wearable data.
Keywords
Cite
@article{arxiv.2604.14615,
title = {CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors},
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 Xuhai Xu and Yuzhe Yang and Maxwell A. Xu and Zhihan Zhang and Cynthia Breazeal and Tim Althoff and Petar Sirkovic and Ivor Rendulic and Annalisa Pawlosky and Nicolas Stroppa and Juraj Gottweis and Elahe Vedadi and Alan Karthikesalingam and Pushmeet Kohli and Vivek Natarajan and Mark Malhotra and Shwetak Patel and Hae Won Park and Hamid Palangi and Daniel McDuff},
journal= {arXiv preprint arXiv:2604.14615},
year = {2026}
}