CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915940292100096 |
|---|---|
| author | Kim, Yubin Rahman, Salman Schmidgall, Samuel Park, Chunjong Heydari, A. Ali Metwally, Ahmed A. Yu, Hong Liu, Xin Xu, Xuhai Yang, Yuzhe Xu, Maxwell A. Zhang, Zhihan Breazeal, Cynthia Althoff, Tim Sirkovic, Petar Rendulic, Ivor Pawlosky, Annalisa Stroppa, Nicolas Gottweis, Juraj Vedadi, Elahe Karthikesalingam, Alan Kohli, Pushmeet Natarajan, Vivek Malhotra, Mark Patel, Shwetak Park, Hae Won Palangi, Hamid McDuff, Daniel |
| author_facet | Kim, Yubin Rahman, Salman Schmidgall, Samuel Park, Chunjong Heydari, A. Ali Metwally, Ahmed A. Yu, Hong Liu, Xin Xu, Xuhai Yang, Yuzhe Xu, Maxwell A. Zhang, Zhihan Breazeal, Cynthia Althoff, Tim Sirkovic, Petar Rendulic, Ivor Pawlosky, Annalisa Stroppa, Nicolas Gottweis, Juraj Vedadi, Elahe Karthikesalingam, Alan Kohli, Pushmeet Natarajan, Vivek Malhotra, Mark Patel, Shwetak Park, Hae Won Palangi, Hamid McDuff, Daniel |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14615 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors Kim, Yubin Rahman, Salman Schmidgall, Samuel Park, Chunjong Heydari, A. Ali Metwally, Ahmed A. Yu, Hong Liu, Xin Xu, Xuhai Yang, Yuzhe Xu, Maxwell A. Zhang, Zhihan Breazeal, Cynthia Althoff, Tim Sirkovic, Petar Rendulic, Ivor Pawlosky, Annalisa Stroppa, Nicolas Gottweis, Juraj Vedadi, Elahe Karthikesalingam, Alan Kohli, Pushmeet Natarajan, Vivek Malhotra, Mark Patel, Shwetak Park, Hae Won Palangi, Hamid McDuff, Daniel Artificial Intelligence 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. |
| title | CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.14615 |