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

TL;DR

Cardiac risk reduction can benefit from holistic patient-generated health data, but integration into clinician workflows remains challenging. The authors present INSIGHT, a co-designed dashboard that aggregates multi-modal PGHD and uses large language models to generate summaries and enable natural-language exploration, aiming to augment HCP data sensemaking and physical activity planning. The work details a multi-stage design process and a Plotly Dash-based prototype with a Chat with Data interface that explicitly avoids automated medical recommendations. If validated, INSIGHT has potential to reduce data overload, improve workflow alignment, and support personalized cardiac rehabilitation strategies.

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.

Figures (2)

• Figure 1: Diagram illustrating the system's architecture
• Figure 2: Chat With Data Interface showing response to HCP's query asking for a comparison between sedentary time and physical activity minutes