Recommendations for the safe, effective use of adaptive CDS in the US healthcare system: an AMIA position paper

Carolyn Petersen; Jeffery Smith; Robert R Freimuth; Kenneth W Goodman; Gretchen Purcell Jackson; Joseph Kannry; Hongfang Liu; Subha Madhavan; Dean F Sittig; Adam Wright

doi:10.1093/jamia/ocaa319

Recommendations for the safe, effective use of adaptive CDS in the US healthcare system: an AMIA position paper

J Am Med Inform Assoc. 2021 Mar 18;28(4):677-684. doi: 10.1093/jamia/ocaa319.

Authors

Affiliations

¹ Division of Biomedical Statistics and Informatics, Mayo Clinic, Rochester, Minnesota, USA.
² The Office of the National Coordinator for Health Information Technology, Washington, DC, USA.
³ Division of Digital Health Sciences, Center for Individualized Medicine, Mayo Clinic, Rochester, Minnesota, USA.
⁴ Institute for Bioethics and Health Policy, University of Miami Miller School of Medicine, Miami, Florida, USA.
⁵ IBM Watson Health, Cambridge, Massachusetts, USA.
⁶ Department of Pediatric Surgery, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
⁷ Mount Sinai Health System, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
⁸ Division of Digital Health Sciences, Mayo Clinic, Rochester, Minnesota, USA.
⁹ Department of Oncology, Georgetown Lombardi Comprehensive Cancer Center, Innovation Center for Biomedical Informatics, Georgetown University Medical Center, Washington, DC, USA.
¹⁰ School of Biomedical Informatics, The University of Texas Health Science Center at Houston, UT-Memorial Hermann Center for Healthcare Quality & Safety, Houston, Texas, USA.
¹¹ Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.

Abstract

The development and implementation of clinical decision support (CDS) that trains itself and adapts its algorithms based on new data-here referred to as Adaptive CDS-present unique challenges and considerations. Although Adaptive CDS represents an expected progression from earlier work, the activities needed to appropriately manage and support the establishment and evolution of Adaptive CDS require new, coordinated initiatives and oversight that do not currently exist. In this AMIA position paper, the authors describe current and emerging challenges to the safe use of Adaptive CDS and lay out recommendations for the effective management and monitoring of Adaptive CDS.

Keywords: artificial intelligence; clinical decision support; health policy; machine learning; software as a medical device.

MeSH terms

Algorithms
Artificial Intelligence
Decision Support Systems, Clinical / standards*
Delivery of Health Care
Health Policy
Humans
Machine Learning / standards*
Medical Informatics* / education
Organizational Policy*
Societies, Medical*
United States