CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors

2026-04-16

AI Summary

This study addresses the challenge of systematically and reliably discovering clinically meaningful digital biomarkers from continuous physiological signals captured by wearable devices. To this end, we propose CoDaS, a multi-agent collaborative framework that, for the first time, integrates hypothesis generation, statistical analysis, adversarial validation, and literature-based knowledge reasoning into an iterative, human-supervised workflow. This approach enables automated biomarker discovery that is traceable, verifiable, and grounded in domain expertise. Evaluated on a cohort of 9,279 participants, CoDaS identified 41 candidate biomarkers associated with mental health and 25 linked to metabolic function. It significantly replicated the association between circadian rhythm instability and depression (ρ = 0.252 and 0.126 in two cohorts) and improved predictive performance for both depression and insulin resistance (ΔR² = 0.040 and 0.021, respectively).

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Application Domains: Humanities & Computational Social Science
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

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, ρ= 0.252, p < 0.001) and sleep onset variability (GLOBEM, ρ= 0.126, p < 0.001). In a metabolic cohort, CoDaS derived a cardiovascular fitness index (steps/resting heart rate; ρ= -0.374, p < 0.001), and recovered established clinical associations, including the hepatic function ratio (AST/ALT; ρ= -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 ΔR^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.

Problem

• digital biomarker
• wearable sensors
• biomarker discovery
• mental health
• metabolic outcomes

Innovation

• multi-agent system
• digital biomarker discovery
• wearable sensors
• adversarial validation
• hypothesis generation