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

被引：358

作者：

Beede, Emma ^{[1
]}

Baylor, Elizabeth ^{[1
]}

Hersch, Fred ^{[2
]}

Iurchenko, Anna ^{[1
]}

Wilcox, Lauren ^{[1
]}

Ruamviboonsuk, Paisan ^{[3
]}

Vardoulakis, Laura M. ^{[1
]}

机构：

[1] Google Hlth, Palo Alto, CA 94301 USA

[2] Google Hlth, Singapore, Singapore

[3] Rajavithi Hosp, Bangkok, Thailand

来源：

PROCEEDINGS OF THE 2020 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI'20) | 2020年

关键词：

human-centered AI; health; deep learning; diabetes; CAD; TOOLS;

D O I：

10.1145/3313831.3376718

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

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 humancentered evaluative research alongside prospective evaluations of model accuracy.

引用

页数：12

共 40 条

[1] Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices [J].