New agentic system uses wearables for auditable N-of-1 athlete physiology experiments

Researchers have developed EpiCoach, an agentic system designed for individualized physiological monitoring and experimental design using data from consumer wearables. This system treats athletes as subjects of N-of-1 science, with claims about their physiology logged in an auditable hypothesis registry. EpiCoach infers a digital twin from heart rate, GPS, and barometric altitude data to make probabilistic predictions about future training sessions and prescribes weekly experiments to maximize information gain while adhering to load and safety constraints. An eighteen-month evaluation showed the system's predictive capabilities and its potential for auditable, falsifiable personalization in digital health. AI

IMPACT Introduces a novel framework for auditable and falsifiable personalization in digital health using LLM agents and wearable data.

RANK_REASON Academic paper detailing a novel system for physiological monitoring and experimental design. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• barometric altitude
• EpiCoach
• Global Positioning System
• heart rate
• Hugging Face
• N-of-1 trial

• paper
• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →