Problem
Research questions and friction points this paper is trying to address.
Interactive Machine Learning
Disease Risk Prediction
Risk Perception
Patient-facing Interfaces
Explainability
Interactive Machine Learning Interfaces for Disease Risk Prediction: Effects on Risk Perception and Behaviour
🤖 AI Summary
This study addresses the challenge of patient comprehension regarding machine learning (ML) risk model outputs. Using a Type 2 diabetes interface as the application context, we employed an exploratory mixed-methods approach—incorporating qualitative interviews and interactive prototype testing—to systematically examine how visual design and information framing influence patient cognition and behavior. Our findings reveal a significant discrepancy between perceived and actual understanding, identifying ambiguous terminology and framing inconsistencies as primary barriers. Accordingly, this work proposes design guidelines for patient-facing ML interfaces, emphasizing that intuitive visual representations and clear explanations are essential for fostering user trust. Ultimately, this research provides empirical evidence to enhance the usability and transparency of healthcare AI systems.
📝 Abstract
Machine learning risk models are increasingly being used in patient-facing health tools, but it remains unclear how well users understand the information these systems present. In this work, we study how people interpret an interactive Type 2 Diabetes (T2D) risk interface and whether interacting with it influences their attitudes toward behavioural change. Through an exploratory mixed-methods study with 15 participants, we compare participants' perceived understanding with their actual understanding and identify key themes from qualitative interviews. We find that participants often understood the interface better than they initially believed, but still faced important barriers related to unclear terminology, ambiguous risk framing, and limited explanations of model inputs. Finally, we propose relevant design guidelines and discuss broader issues surrounding trust and fairness. Our findings highlight the importance of intuitive visual design, familiar presentation, and clear explanations in patient-facing ML interfaces.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Interactive Machine Learning
Disease Risk Prediction
Risk Perception
Human-Computer Interaction
Explainable AI
🔎 Similar Papers
No similar papers found.
