GPTCoach: Towards LLM-Based Physical Activity Coaching

2024-05-09

AI Summary

To address the lack of personalized physical activity guidance in mobile health applications, this study proposes the first large language model (LLM)-based health coaching framework integrating Motivational Interviewing (MI) strategies, real-time wearable sensor time-series data, and evidence-based health coaching protocols (e.g., CDC MOVE!). Built upon GPT-series models, the system establishes a closed-loop human–AI collaboration paradigm enabling dynamic exercise plan adaptation and behavior-change-oriented conversational interventions. Its key innovation lies in the first deep integration of MI-informed dialogue modeling with authentic wearable-derived physiological and behavioral data within an LLM coaching architecture. Laboratory evaluation with 16 participants demonstrated high user willingness to disclose sensitive health concerns, high-quality, contextually grounded exercise recommendations, and perceived support and interaction comfort approaching that of human coaches.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Mobile health applications show promise for scalable physical activity promotion but are often insufficiently personalized. In contrast, health coaching offers highly personalized support but can be prohibitively expensive and inaccessible. This study draws inspiration from health coaching to explore how large language models (LLMs) might address personalization challenges in mobile health. We conduct formative interviews with 12 health professionals and 10 potential coaching recipients to develop design principles for an LLM-based health coach. We then built GPTCoach, a chatbot that implements the onboarding conversation from an evidence-based coaching program, uses conversational strategies from motivational interviewing, and incorporates wearable data to create personalized physical activity plans. In a lab study with 16 participants using three months of historical data, we find promising evidence that GPTCoach gathers rich qualitative information to offer personalized support, with users feeling comfortable sharing concerns. We conclude with implications for future research on LLM-based physical activity support.

Problem

• Addressing insufficient personalization in mobile health apps
• Exploring LLMs for scalable, personalized physical activity coaching
• Developing GPTCoach to provide tailored activity plans using wearable data

Innovation

• LLM-based chatbot for personalized health coaching
• Incorporates wearable data for activity plans
• Uses motivational interviewing conversational strategies