# An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data

arXiv: https://arxiv.org/abs/2604.14615 · HTML: https://mlsanity.com/paper/2604.14615/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 73 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 27 of 27)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [DiscoveryBench: Towards Data-Driven Discovery with Large Language Models](https://mlsanity.com/paper/2407.01725/) (2024)
- [Medical Hallucinations in Foundation Models and Their Impact on Healthcare](https://mlsanity.com/paper/2503.05777/) (2025)
- [From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery](https://mlsanity.com/paper/2505.13259/) (2025)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data](https://mlsanity.com/paper/2401.06866/) (2024)
- [DataSciBench: An LLM Agent Benchmark for Data Science](https://mlsanity.com/paper/2502.13897/) (2025)
- [CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis](https://mlsanity.com/paper/2407.09811/) (2024)
- [The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems](https://mlsanity.com/paper/2509.08713/) (2025)
- [Towards a Personal Health Large Language Model](https://mlsanity.com/paper/2406.06474/) (2024)
- [The Anatomy of a Personal Health Agent](https://mlsanity.com/paper/2508.20148/) (2025)
- [SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents](https://mlsanity.com/paper/2505.23559/) (2025)
- [DSGym: A Holistic Framework for Evaluating and Training Data Science Agents](https://mlsanity.com/paper/2601.16344/) (2026)
- [HEARTS: Benchmarking LLM Reasoning on Health Time Series](https://mlsanity.com/paper/2603.06638/) (2026)
- [The Need for Verification in AI-Driven Scientific Discovery](https://mlsanity.com/paper/2509.01398/) (2025)
- [Towards a Medical AI Scientist](https://mlsanity.com/paper/2603.28589/) (2026)
- [VocalAgent: Large Language Models for Vocal Health Diagnostics with Safety-Aware Evaluation](https://mlsanity.com/paper/2505.13577/) (2025)
- [Research Protocol for the Google Health Digital Well-being Study](https://mlsanity.com/paper/2307.05795/) (2023)

## Built on by (most cited first, 1 of 1)

- [Accelerating Scientific Research with Gemini in the Real-World](https://mlsanity.com/paper/2608.26701/) (2026)

## Abstract (arXiv)

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 (ρ = 0.252, p < 0.001) and sleep-onset variability in GLOBEM (ρ = 0.126, p < 0.001), and derived a wearable cardiovascular-fitness index associated with insulin resistance (steps/resting heart rate; ρ = -0.374, p < 0.001). Adding these features to demographic models produced modest gains (Delta R2 = 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 (ρ = 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.