The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Conceptual Cardiac Rehabilitation Setting

2024-02-13

AI Summary

Traditional just-in-time adaptive interventions (JITAI) in digital health suffer from poor scalability and weak contextual adaptability. Method: This study proposes a novel LLM-based JITAI paradigm, validated in the domain of cardiac rehabilitation to promote physical activity. We developed a GPT-4–driven framework integrating five-dimensional contextual modeling (e.g., symptoms, affect, environment), multi-persona simulation, and human–AI double-blind evaluation. Contribution/Results: Across appropriateness, appeal, effectiveness, and professionalism, GPT-4 generated 450 JITAI messages significantly outperformed recommendations from 10 laypersons and 10 clinical professionals. This is the first empirical demonstration that LLMs can surpass human experts in core JITAI decision-making and personalized message generation—establishing their feasibility and superiority as next-generation, context-aware health intervention engines.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

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
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

We evaluated the viability of using Large Language Models (LLMs) to trigger and personalize content in Just-in-Time Adaptive Interventions (JITAIs) in digital health. As an interaction pattern representative of context-aware computing, JITAIs are being explored for their potential to support sustainable behavior change, adapting interventions to an individual's current context and needs. Challenging traditional JITAI implementation models, which face severe scalability and flexibility limitations, we tested GPT-4 for suggesting JITAIs in the use case of heart-healthy activity in cardiac rehabilitation. Using three personas representing patients affected by CVD with varying severeness and five context sets per persona, we generated 450 JITAI decisions and messages. These were systematically evaluated against those created by 10 laypersons (LayPs) and 10 healthcare professionals (HCPs). GPT-4-generated JITAIs surpassed human-generated intervention suggestions, outperforming both LayPs and HCPs across all metrics (i.e., appropriateness, engagement, effectiveness, and professionalism). These results highlight the potential of LLMs to enhance JITAI implementations in personalized health interventions, demonstrating how generative AI could revolutionize context-aware computing.

Problem

• Utilizing LLMs for JITAIs in digital health
• Personalizing interventions for cardiac rehabilitation
• Overcoming scalability in traditional JITAI models

Innovation

• LLMs for JITAIs
• GPT-4 in healthcare
• AI surpasses human interventions