Artificial Intelligence in Medicine: How One Doctor Uses AI For Prostate Cancer
Starting over a decade ago, I collaborated on research into MRI imaging features that lend themselves to Artificial Intelligence training sets for the detection/diagnosis of prostate cancer (PCa). As an early AI contributor, I’m always happy to learn how other PCa physicians integrate AI into their practice.
I was delighted when CancerNetwork (home of the journal Oncology) posted a brief video interview with Dr. Wayne Brisbane, an assistant professor of urology at UCLA school of medicine. For Dr. Brisbane, AI’s use begins when patients come to his practice because of a rise in PSA. Since an elevated PSA could mean a variety of things, his practice turns to multiparametric MRI (mpMRI) to rule PCa in or out.
However, not all MRI scans are qualitatively equal; some are better than others. In addition, not all readers are equally experienced. Therefore, he uses AI to interpret the MRI results. The human eye may not be able to perceive very minute imaging features that are signs of disease. Dr. Brisbane’s practice uses a commercial AI prostate mapping system called Unfold AI, which has demonstrated a 96.9% sensitivity for modeling clinically significant tumor margins and outperforms conventional reading.[i]
Dr. Brisbane’s confidence in using the efficiency and accuracy of AI as a “partner” to human interpretation as recently confirmed by the American Medical Association’s assignment of a category III CPT code to Unfold AI. This means it’s recognized as a method of data collection to track the utilization of emerging technologies, services and procedures. In this case, the AMA is affirming Unfold AI’s role in prostate cancer mapping.
For Dr. Brisbane, AI’s value goes beyond diagnosis. Because it can accurately define a tumor’s location and extent, it enhances treatment planning, assuring the best likelihood of a successful outcome. This mirrors our own experience with AI at the Sperling Prostate Center. Thank you, Dr. Brisbane, for sharing your experience and vote of confidence for AI’s service to PCa patients.
NOTE: This content is solely for purposes of information and does not substitute for diagnostic or medical advice. Talk to your doctor if you are experiencing pelvic pain, or have any other health concerns or questions of a personal medical nature.
[i] Priester A, Fan RE, Shubert J, Rusu M, Vesal S, Shao W, Khandwala YS, Marks LS, Natarajan S, Sonn GA. Prediction and Mapping of Intraprostatic Tumor Extent with Artificial Intelligence. Eur Urol Open Sci. 2023 Jun 13;54:20-27.