A Human-Centered Evaluation of a Deep Learning System Deployed in Clinics for the Detection of Diabetic Retinopathy

要旨

Deep learning algorithms promise to improve clinician workflows and patient outcomes. However, these gains have yet to be fully demonstrated in real world clinical settings. In this paper, we describe a human-centered study of a deep learning system used in clinics for the detection of diabetic eye disease. From interviews and observation across eleven clinics in Thailand, we characterize current eye-screening workflows, user expectations for an AI-assisted screening process, and post-deployment experiences. Our findings indicate that several socio-environmental factors impact model performance, nursing workflows, and the patient experience. We draw on these findings to reflect on the value of conducting human-centered evaluative research alongside prospective evaluations of model accuracy.

受賞
Honorable Mention
キーワード
Human-Centered AI
Health
Deep Learning
Diabetes
著者
Emma Beede
Google Health, Palo Alto, CA, USA
Elizabeth Baylor
Google Health, Palo Alto, CA, USA
Fred Hersch
Google Health, Singapore, Singapore
Anna Iurchenko
Google Health, Palo Alto, CA, USA
Lauren Wilcox
Google Health, Palo Alto, CA, USA
Paisan Ruamviboonsuk
Rajavithi Hospital, Bangkok, Thailand
Laura M. Vardoulakis
Google Health, Palo Alto, CA, USA
DOI

10.1145/3313831.3376718

論文URL

https://doi.org/10.1145/3313831.3376718

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Health information & advice

Paper session
314 LANA'I
5 件の発表
2020-04-29 18:00:00
2020-04-29 19:15:00
日本語まとめ
読み込み中…