SePA: A Search-enhanced Predictive Agent for Personalized Health Coaching

Melik Ozolcer, Sang Won Bae

Confirmation: I have read and agree with the IEEE BHI 2025 conference submission's policy on behalf of myself and my co-authors.

Keywords: Large Language Models, Personalized Health, Wearable Sensors, Predictive Modeling

TL;DR: We present an LLM-health coach that proactively predicts daily health risks from wearable data and uses these forecasts to power a trusted web search for personalized, evidence-based advice.

Abstract: This paper introduces SePA (Search-enhanced Predictive AI Agent), a novel LLM health coaching system that integrates personalized machine learning and retrieval-augmented generation to deliver adaptive, evidence-based guidance. SePA combines: (1) Individualized models predicting daily stress, soreness, and injury risk from wearable sensor data (28 users, 1260 data points); and (2) A retrieval module that grounds LLM-generated feedback in expert-vetted web content to ensure contextual relevance and reliability. Our predictive models, evaluated with rolling-origin cross-validation and group 4-fold cross-validation show that personalized models outperform generalized baselines. In a pilot expert study (n=4), SePA's retrieval-based advice was preferred over a non-retrieval baseline, yielding meaningful practical effect (Cliff's $\delta$=0.3, p=0.05). We also quantify latency performance trade-offs between response quality and speed, offering a transparent blueprint for next-generation, trustworthy personal health informatics systems.

Track: 1. Biomedical Sensor Informatics

Registration Id: RRNSSXZDXV8

Submission Number: 174