Artificial intelligence–based image analysis in clinical testing: lessons from cervical cancer screening

Author:

Egemen Didem1ORCID,Perkins Rebecca B2,Cheung Li C1,Befano Brian34ORCID,Rodriguez Ana Cecilia1,Desai Kanan1,Lemay Andreanne5,Ahmed Syed Rakin5678,Antani Sameer9ORCID,Jeronimo Jose1,Wentzensen Nicolas1ORCID,Kalpathy-Cramer Jayashree5,De Sanjose Silvia110,Schiffman Mark1ORCID

Affiliation:

1. Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health , Rockville, MD, USA

2. Department of Obstetrics and Gynecology, Boston Medical Center/Boston University School of Medicine , Boston, MA, USA

3. Information Management Services Inc , Calverton, MD, USA

4. Department of Epidemiology, School of Public Health, University of Washington , Seattle, WA, USA

5. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital , Boston, MA, USA

6. Harvard Graduate Program in Biophysics, Harvard Medical School, Harvard University , Cambridge, MA, USA

7. Massachusetts Institute of Technology , Cambridge, MA, USA

8. Geisel School of Medicine at Dartmouth, Dartmouth College , Hanover, NH, USA

9. National Library of Medicine, National Institutes of Health , Bethesda, MD, USA

10. ISGlobal , Barcelona, Spain

Abstract

Abstract Novel screening and diagnostic tests based on artificial intelligence (AI) image recognition algorithms are proliferating. Some initial reports claim outstanding accuracy followed by disappointing lack of confirmation, including our own early work on cervical screening. This is a presentation of lessons learned, organized as a conceptual step-by-step approach to bridge the gap between the creation of an AI algorithm and clinical efficacy. The first fundamental principle is specifying rigorously what the algorithm is designed to identify and what the test is intended to measure (eg, screening, diagnostic, or prognostic). Second, designing the AI algorithm to minimize the most clinically important errors. For example, many equivocal cervical images cannot yet be labeled because the borderline between cases and controls is blurred. To avoid a misclassified case-control dichotomy, we have isolated the equivocal cases and formally included an intermediate, indeterminate class (severity order of classes: case>indeterminate>control). The third principle is evaluating AI algorithms like any other test, using clinical epidemiologic criteria. Repeatability of the algorithm at the borderline, for indeterminate images, has proven extremely informative. Distinguishing between internal and external validation is also essential. Linking the AI algorithm results to clinical risk estimation is the fourth principle. Absolute risk (not relative) is the critical metric for translating a test result into clinical use. Finally, generating risk-based guidelines for clinical use that match local resources and priorities is the last principle in our approach. We are particularly interested in applications to lower-resource settings to address health disparities. We note that similar principles apply to other domains of AI-based image analysis for medical diagnostic testing.

Funder

National Institutes of Health

Publisher

Oxford University Press (OUP)

Subject

Cancer Research,Oncology

Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3