Generative AI helps customize personal health dashboards with user input
Personalizing Personal Health Interfaces: Co-Design with Generative AI
Human-Computer InteractionArtificial IntelligenceComputers and Society
Summary
People often find health apps hard to personalize because customizing needs technical skills. The authors studied how using generative AI can help regular users redesign health interfaces to better fit their needs. They found AI helped users turn vague ideas into real designs but also limited them by default AI styles and delays. The study showed that AI makes it easier to focus on making data understandable and accountable but less so on privacy or emotional safety. This approach blurs the lines between what users want and what AI tools automatically suggest.
What this means in practice
- •For health app designers: Create more personalized health data dashboards by directly involving users with AI-assisted co-design tools adapting to their specific needs.
- •For digital wellbeing product teams: Develop interactive health interfaces that incorporate AI-generated design elements to support users’ future health planning in intuitive ways.
Authors
Karthik S. Bhat, Vidhi Shah, Vedika Agnihotri, Dong Whi Yoo, Koustuv Saha
Abstract
Personal health interfaces present wellbeing data through standardized dashboards that rarely fit how people interpret or act on it. Personalizing them to what people would like to see for themselves often requires design and technical expertise, a barrier that generative AI may potentially lower. Therefore, we ask what designs emerge and how it enables and constrains the design process. We conducted a co-design study where 14 participants redesigned Google and Apple Health interfaces using Figma Make. Participants reimagined interfaces that supported personal context, future planning, and interactive experiences, yet conversational AI designs converged around chat-window conventions. AI helped materialize loosely articulated ideas, but model defaults and generation latency shaped iteration. The process more readily operationalized interpretability and accountability than privacy, trust, and emotional safety. Generative co-design let participants create interfaces directly, blurring the boundary between intentions and model defaults. We discuss implications for preserving agency and flexible user-directed interfaces.