Artificial intelligence in medicine: mitigating risks and maximizing benefits via quality assurance, quality control, and acceptance testing
Usman Mahmood, Amita Shukla‐Dave, Heang‐Ping Chan, Karen Drukker, Ravi K. Samala, Quan Chen, Daniel Vergara, Hayit Greenspan, Nicholas Petrick, Berkman Sahiner, Zhimin Huo, Ronald M. Summers, Kenny H Cha, Georgia D. Tourassi, Thomas M. Deserno, Kevin Grizzard, Janne J. Näppi, Hiroyuki Yoshida, Daniele Regge, Richard Mazurchuk, Kenji Suzuki, Lia Morra, Henkjan Huisman, Samuel G. Armato, Lubomir M. Hadjiiski
Abstract
The adoption of artificial intelligence (AI) tools in medicine poses challenges to existing clinical workflows. This commentary discusses the necessity of context-specific quality assurance (QA), emphasizing the need for robust QA measures with quality control (QC) procedures that encompass (1) acceptance testing (AT) before clinical use, (2) continuous QC monitoring, and (3) adequate user training. The discussion also covers essential components of AT and QA, illustrated with real-world examples. We also highlight what we see as the shared responsibility of manufacturers or vendors, regulators, healthcare systems, medical physicists, and clinicians to enact appropriate testing and oversight to ensure a safe and equitable transformation of medicine through AI.