Planning an artificial intelligence diabetic retinopathy screening program: a human-centered design approach

Frontiers in Medicine

Medicine

Ariel Leifer¹  R. V. Paul Chan²  Angelica C. Scanzera²  Patricia Bai²  Archit V. Potharazu³  Hugh Musick³  Cameron Beversluis³  David Yuzhou Du⁴  Emily Cole⁵ 

[1] Department of Family and Community Medicine, University of Illinois at Chicago, Chicago, IL, United States;Department of Ophthalmology and Visual Sciences, Illinois Eye and Ear Infirmary, University of Illinois Chicago, Chicago, IL, United States;Institute for Healthcare Delivery Design, Office of Population Health Sciences, University of Illinois Chicago, Chicago, IL, United States;Segal Design Institute, Northwestern University, Evanston, IL, United States;W.K. Kellogg Eye Center, University of Michigan, Ann Arbor, MI, United States;

关键词: diabetic retinopathy;    screening;    artificial intelligence;    human-centered design;    implementation;   

DOI  :  10.3389/fmed.2023.1198228

 received in 2023-04-04, accepted in 2023-06-16,  发布年份 2023

来源: Frontiers

【 摘 要 】

Diabetic retinopathy (DR) is a leading cause of vision loss in the United States and throughout the world. With early detection and treatment, sight-threatening sequelae from DR can be prevented. Although artificial intelligence (AI) based DR screening programs have been proven to be effective in identifying patients at high risk of vision loss, adoption of AI in clinical practice has been slow. We adapted the United Kingdom Design Council’s Double-Diamond model to design a strategy for care delivery which integrates an AI-based screening program for DR into a primary care setting. Methods from human-centered design were used to develop a strategy for implementation informed by context-specific barriers and facilitators. The purpose of this community case study is to present findings from this work in progress, including a system of protocols, educational documents and workflows created using key stakeholder input.

【 授权许可】

Unknown   
Copyright © 2023 Scanzera, Beversluis, Potharazu, Bai, Leifer, Cole, Du, Musick and Chan.