Exploring Human-AI Interaction with Patient-Generated Health Data Sensemaking for Cardiac Risk Reduction

TL;DR

This paper presents INSIGHT, a dashboard integrating patient-generated health data and AI to support healthcare professionals in cardiac risk reduction through enhanced data understanding and personalized analysis.

Contribution

It introduces a co-designed dashboard that combines multi-modal PGHD with LLMs for improved data sensemaking in cardiac rehabilitation.

Findings

Enhanced data exploration capabilities for healthcare professionals

Effective summarization and insights generation using LLMs

Potential for AI to augment clinical decision-making in cardiac care

Abstract

Patient-generated health data (PGHD) allows healthcare professionals to have a holistic and objective view of their patients. However, its integration in cardiac risk reduction remains unexplored. Through co-design with experienced healthcare professionals (n=5) in cardiac rehabilitation, we designed a dashboard, INSIGHT (INvestigating the potentialS of PatIent Generated Health data for CVD Prevention and ReHabiliTation), integrating multi-modal PGHD to support healthcare professionals in physical activity planning in cardiac risk reduction. To further augment healthcare professionals' (HCPs') data sensemaking and exploration capabilities, we integrate large language models (LLMs) for generating summaries and insights and for using natural language interaction to perform personalized data analysis. The aim of this integration is to explore the potential of AI in augmenting HCPs' data sensemaking and analysis capabilities.