AI-enabled Consumer-facing Health Technology
Oct 5, 2021
Overview
This project aims to understand the socio-technical implications of AI-enabled consumer-facing health technology. We have three papers published and one paper under preparation.
Paper 1
The Medical Authority of AI: A Study of AI-enabled Consumer-Facing Health Technology | Paper
Yue You, Yubo Kou, Xianghua Ding, Xinning Gui
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2021 (CHI 2021)
Research question:
How users perceive and understand medical authority with the emergence of consumer-facing AI health technologies
Method:
Semi-structured interviews
Presentation_chi 2021 copy.pptxPaper 2
Exploring and Promoting Diagnostic Transparency and Explainability in Online Symptom Checkers | Paper
Chun-Hua Tsai, Yue You, Xinning Gui, Yubo Kou, John M. Carroll
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems 2021 (CHI 2021)
Research question:
How explanations could be used to promote diagnostic transparency of online symptom checkers
Methods: A mixed study
(1) Semi-structured interviews: to specify user needs for explanations from users of existing symptom checkers
(2) A lab-controlled experiment: designed a prototype with different explanation styles to explore what kind of and whether explanation can improve user experience
Paper 3
Self-Diagnosis through Chatbot-based Symptom Checkers: User Experiences and Design Considerations | Paper
Yue You, Xinning Gui
Proceedings of American Medical Informatics Association 2020 Annual Symposium
(AMIA 2020)
Research question:
To understand how users perceive the effectiveness of chatbot-based symptom checker applications
Methods:
(1) App feature analysis: to shed light on the feature design of the chatbot-based symptom checker apps
(2) App review analysis and semi-structured interviews: to acquire in-depth insights as to how users perceive chatbot-based symptom checker apps
Paper 4
This paper aims to understand how users perceive the efficiency and human-like features of symptom checkers.
Methods: A mixed study
(1) Semi-structured interviews
(2) A lab-controlled experiment