An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation

TL;DR

This paper introduces an LLM-powered agent that effectively analyzes physiological time-series data, specifically PPG signals, for accurate heart rate estimation, bridging the gap between LLMs and traditional analytical tools.

Contribution

We develop an open-source LLM-based agent that integrates analytical tools with large language models for physiological data analysis, demonstrating improved accuracy in heart rate estimation from PPG signals.

Findings

The agent outperforms benchmark models in heart rate estimation accuracy.

It achieves lower error rates compared to GPT-4o and GPT-4o-mini.

The implementation is publicly available on GitHub.

Abstract

Large language models (LLMs) are revolutionizing healthcare by improving diagnosis, patient care, and decision support through interactive communication. More recently, they have been applied to analyzing physiological time-series like wearable data for health insight extraction. Existing methods embed raw numerical sequences directly into prompts, which exceeds token limits and increases computational costs. Additionally, some studies integrated features extracted from time-series in textual prompts or applied multimodal approaches. However, these methods often produce generic and unreliable outputs due to LLMs' limited analytical rigor and inefficiency in interpreting continuous waveforms. In this paper, we develop an LLM-powered agent for physiological time-series analysis aimed to bridge the gap in integrating LLMs with well-established analytical tools. Built on the OpenCHA, an open-source LLM-powered framework, our agent powered by OpenAI's GPT-3.5-turbo model features an orchestrator that integrates user interaction, data sources, and analytical tools to generate accurate health insights. To evaluate its effectiveness, we implement a case study on heart rate (HR) estimation from Photoplethysmogram (PPG) signals using a dataset of PPG and Electrocardiogram (ECG) recordings in a remote health monitoring study. The agent's performance is benchmarked against OpenAI GPT-4o-mini and GPT-4o, with ECG serving as the gold standard for HR estimation. Results demonstrate that our agent significantly outperforms benchmark models by achieving lower error rates and more reliable HR estimations. The agent implementation is publicly available on GitHub.