Leveraging Artificial Intelligence to Enhance Peer Review: Missed Liver Lesions on Computed Tomography Pulmonary Angiography
Journal of the American College of Radiology
To utilize artificial intelligence to facilitate peer review for detection of missed suspicious liver lesions (SLLs) on CT pulmonary angiography (CTPA).
Authors: Sarah P. Thomas, MD; Tyler J. Fraum, MD; Lawrence Ngo, MD, PhD; Robert Harris, PhD; Elie Balesh, MD; Mustafa R. Bashir, MD; Benjamin Wildman-Tobriner, MD
Peer review is one of the main mechanisms of ensuring quality and safety in diagnostic radiology, typically performed via periodic random sampling of a small percentage of a radiologist’s interpreted examinations for blinded secondary review for agreement or disagreement.
However, in an environment where imaging volume is steeply rising but reimbursement is falling, and the shortage of radiologists is deepening, the resource-intensive exercise of peer review is at risk of being deprioritized in practice.
Given these conditions, artificial intelligence may find valuable product-market fit when used as a second reader in a well-structured quality assurance program. When visual classifier and natural language processing algorithm dyads are applied to particular clinical use cases, radiologist error may be mitigated in a relatively frictionless and cost-effective workflow.
In a multi-institutional collaborative research project examining miss rates of incidental suspicious liver lesions on CT pulmonary angiography, it was demonstrated that AI significantly reduced the burden of identifying such lesions by approximately 85% or more. Such real-world efficiency gains demonstrate the immediate value which can be unlocked by AI and with its anticipated positive impact on oncologic outcomes in cases where a missed liver lesion can dramatically alter disease staging and treatment options.
Click here to read the full article.
Journal of the American College of Radiology (JACR) The official journal of the American College of Radiology, JACR informs its readers of timely, pertinent, and important topics affecting the practice of diagnostic radiologists, interventional radiologists, medical physicists, and radiation oncologists. In so doing, JACR improves its practices and helps optimize its role in the health care system. By providing a forum for informative, well-written articles on health policy, clinical practice, practice management, data science, and education, JACR engages readers in a dialogue that ultimately benefits patient care.
Elie Balesh, MD
Dr. Balesh is a double board-certified, dual fellowship-trained diagnostic and interventional radiologist with postdoctoral expertise in digital health and medical device innovation. In his role as Medical Director for Ferrum Health, he leads the development of artificial intelligence clinical use cases, practice implementation, and real-world research.