Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Prediction
This addresses the need for healthcare professionals to effectively use and validate AI systems in clinical settings, though it is incremental as it builds on existing visualization and conversational agent methods.
The paper tackled the problem of making AI-driven clinical decision support systems more understandable and trustworthy for healthcare professionals by developing an integrated system with interactive visualizations and a conversational agent for explaining diabetes risk assessments. The result was that in a study with 30 healthcare professionals, the system helped build clear understanding and calibrated trust, with most participants reporting support for risk evaluation and recommendations.
Healthcare professionals need effective ways to use, understand, and validate AI-driven clinical decision support systems. Existing systems face two key limitations: complex visualizations and a lack of grounding in scientific evidence. We present an integrated decision support system that combines interactive visualizations with a conversational agent to explain diabetes risk assessments. We propose a hybrid prompt handling approach combining fine-tuned language models for analytical queries with general Large Language Models (LLMs) for broader medical questions, a methodology for grounding AI explanations in scientific evidence, and a feature range analysis technique to support deeper understanding of feature contributions. We conducted a mixed-methods study with 30 healthcare professionals and found that the conversational interactions helped healthcare professionals build a clear understanding of model assessments, while the integration of scientific evidence calibrated trust in the system's decisions. Most participants reported that the system supported both patient risk evaluation and recommendation.