Conversational AI in health: Design considerations from a Wizard-of-Oz dermatology case study with users, clinicians and a medical LLM

被引：4

作者：

Li, Brenna ^{[1
,2
]}

Wang, Amy ^{[1
,3
]}

Strachan, Patricia ^{[1
]}

Seguin, Julie Anne ^{[1
]}

Lachgar, Sami ^{[1
]}

Schroeder, Karyn ^{[1
]}

Fleck, Mathias ^{[1
]}

Wong, Renee ^{[1
]}

Karthikesalingam, Alan ^{[1
]}

Natarajan, Vivek ^{[1
]}

Matias, Yossi ^{[1
]}

Corrado, Greg S. ^{[1
]}

Webster, Dale R. ^{[1
]}

Liu, Yun ^{[1
]}

Hammel, Naama ^{[1
]}

Sayres, Rory ^{[1
]}

Semturs, Christopher ^{[1
]}

Schaekermann, Mike ^{[1
]}

机构：

[1] Google, Via YoGiYo 2GROW, Mountain View, CA 94043 USA

[2] Univ Toronto, Toronto, ON, Canada

[3] McMaster Univ, Hamilton, ON, Canada

来源：

EXTENDED ABSTRACTS OF THE 2024 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, CHI 2024 | 2024年

关键词：

Artificial Intelligence; Large Language Models; Chatbot; Medical; Dermatology; Wizard-of-Oz;

D O I：

10.1145/3613905.3651891

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Although skin concerns are common, access to specialist care is limited. Artificial intelligence (AI)-assisted tools to support medical decisions may provide patients with feedback on their concerns while also helping ensure the most urgent cases are routed to dermatologists. Although AI-based conversational agents have been explored recently, how they are perceived by patients and clinicians is not well understood. We conducted a Wizard-of-Oz study involving 18 participants with real skin concerns. Participants were randomly assigned to interact with either a clinician agent (portrayed by a dermatologist) or an LLM agent (supervised by a dermatologist) via synchronous multimodal chat. In both conditions, participants found the conversation to be helpful in understanding their medical situation and alleviate their concerns. Through qualitative coding of the conversation transcripts, we provide insight on the importance of empathy and effective information-seeking. We conclude with design considerations for future AI-based conversational agents in healthcare settings.

引用

页数：10

共 1 条

[1] The intensive care unit environment from the perspective of medical, allied health and nursing clinicians: A qualitative study to inform design of the 'ideal' bedspace
Tronstad, Oystein
Flaws, Dylan
Lye, India
Fraser, John F.
Patterson, Sue
AUSTRALIAN CRITICAL CARE, 2021, 34 (01) : 15 - 22

← 1 →