AI2030 Responsible AI Tools Marketplace

Key Takeaways

One-size-fits-all explanations don't work: The study found that users' demographics, personality traits, and the type of explanation all significantly impact how people prefer AI systems to communicate with them, meaning healthcare apps need customizable explanation approaches rather than uniform designs.
Three distinct user types require different explanation strategies: The research identified three prototypical personas—power-oriented users (who want detailed technical information), casual users (who prefer simple summaries), and privacy-oriented users (who prioritize data protection)—suggesting that effective XAI design must account for these different user needs.
Explainability alone doesn't solve the "black box" problem: Even when AI systems provide explanations, users may still not understand or trust them if the explanation style doesn't match their preferences and needs, highlighting that explainability is necessary but insufficient without human-centered design.
User-centered design is essential for practical AI in healthcare: The study demonstrates that involving actual end-users (patients and clinicians) in XAI design through methods like persona development is critical for creating AI systems that people will actually use and trust in real-world healthcare settings.

Abstract

In healthcare, AI systems support clinicians and patients in diagnosis, treatment, and monitoring, but many systems' poor explainability remains challenging for practical application. Overcoming this barrier is the goal of explainable AI (XAI). However, an explanation can be perceived differently and, thus, not solve the black-box problem for everyone. The domain of Human-Centered AI deals with this problem by adapting AI to users. We present a user-centered persona concept to evaluate XAI and use it to investigate end-users preferences for various explanation styles and contents in a mobile health stress monitoring application. The results of our online survey show that users' demographics and personality, as well as the type of explanation, impact explanation preferences, indicating that these are essential features for XAI design. We subsumed the results in three prototypical user personas: power-, casual-, and privacy-oriented users. Our insights bring an interactive, human-centered XAI closer to practical application.

Key Takeaways

One-size-fits-all explanations don't work: The study found that users' demographics, personality traits, and the type of explanation all significantly impact how people prefer AI systems to communicate with them, meaning healthcare apps need customizable explanation approaches rather than uniform designs.
Three distinct user types require different explanation strategies: The research identified three prototypical personas—power-oriented users (who want detailed technical information), casual users (who prefer simple summaries), and privacy-oriented users (who prioritize data protection)—suggesting that effective XAI design must account for these different user needs.
Explainability alone doesn't solve the "black box" problem: Even when AI systems provide explanations, users may still not understand or trust them if the explanation style doesn't match their preferences and needs, highlighting that explainability is necessary but insufficient without human-centered design.
User-centered design is essential for practical AI in healthcare: The study demonstrates that involving actual end-users (patients and clinicians) in XAI design through methods like persona development is critical for creating AI systems that people will actually use and trust in real-world healthcare settings.

Abstract

What Do End-Users Really Want? Investigation of Human-Centered XAI for Mobile Health Apps

Key Takeaways

Abstract

Paper Info

Responsible AI Topics

Links

What Do End-Users Really Want? Investigation of Human-Centered XAI for Mobile Health Apps

Key Takeaways

Abstract

Paper Info

Responsible AI Topics

Links