Interactive diabetes risk tools influence patient understanding and behavior
Interactive Machine Learning Interfaces for Disease Risk Prediction: Effects on Risk Perception and Behaviour
Human-Computer Interaction
Summary
Many health tools use machine learning to show people their risk of diseases like Type 2 Diabetes. The authors studied how people understand an interactive risk tool and if using it changes their thoughts about healthy habits. They found people often understood the tool better than they thought, but confusing words and unclear explanations still made it harder. The authors suggest clearer visuals and simpler language could help users trust and benefit more from these tools.
What this means in practice
- •For health app developers: Design patient-facing diabetes risk tools with clearer language and visuals to improve understanding and encourage behavior change.
- •For digital health product managers: Integrate guidelines for intuitive and familiar risk presentation to foster trust and perceived fairness in disease risk prediction tools.
Authors
Tiffany Ngai, Max Homm, Matthew Bradbury, Anamaria Crisan
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.