Performance of GPT-4 for automated prostate biopsy decision-making based on mpMRI: a multi-center evidence study.

Authors

Shi MJ,Wang ZX,Wang SK,Li XH,Zhang YL,Yan Y,An R,Dong LN,Qiu L,Tian T,Liu JX,Song HC,Wang YF,Deng C,Cao ZB,Wang HY,Wang Z,Wei W,Song J,Lu J,Wei X,Wang ZC

Affiliations (15)

  • Department of Urology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China.
  • Institute of Urology, Beijing Municipal Health Commission, Beijing, 101313, China.
  • Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China.
  • Department of Ultrasound, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China.
  • Department of Radiology, Beijing Chaoyang Hospital, Capital Medical University, Beijing, 100020, China.
  • Department of Pathology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China.
  • Department of Urology, Peking University Third Hospital, Beijing, 100083, China.
  • Department of Urology, Beijing Fuxing Hospital, Capital Medical University, Beijing, 100039, China.
  • Department of Urology, Beijing Miyun District Traditional Chinese Medicine Hospital, Beijing, 101500, China.
  • Division of Science and Technology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China.
  • Department of Urology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. [email protected].
  • Institute of Urology, Beijing Municipal Health Commission, Beijing, 101313, China. [email protected].
  • Department of Urology, Peking University Third Hospital, Beijing, 100083, China. [email protected].
  • Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. [email protected].
  • Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China. [email protected].

Abstract

Multiparametric magnetic resonance imaging (mpMRI) has significantly advanced prostate cancer (PCa) detection, yet decisions on invasive biopsy with moderate prostate imaging reporting and data system (PI-RADS) scores remain ambiguous. To explore the decision-making capacity of Generative Pretrained Transformer-4 (GPT-4) for automated prostate biopsy recommendations, we included 2299 individuals who underwent prostate biopsy from 2018 to 2023 in 3 large medical centers, with available mpMRI before biopsy and documented clinical-histopathological records. GPT-4 generated structured reports with given prompts. The performance of GPT-4 was quantified using confusion matrices, and sensitivity, specificity, as well as area under the curve were calculated. Multiple artificial evaluation procedures were conducted. Wilcoxon's rank sum test, Fisher's exact test, and Kruskal-Wallis tests were used for comparisons. Utilizing the largest sample size in the Chinese population, patients with moderate PI-RADS scores (scores 3 and 4) accounted for 39.7% (912/2299), defined as the subset-of-interest (SOI). The detection rates of clinically significant PCa corresponding to PI-RADS scores 2-5 were 9.4, 27.3, 49.2, and 80.1%, respectively. Nearly 47.5% (433/912) of SOI patients were histopathologically proven to have undergone unnecessary prostate biopsies. With the assistance of GPT-4, 20.8% (190/912) of the SOI population could avoid unnecessary biopsies, and it performed even better [28.8% (118/410)] in the most heterogeneous subgroup of PI-RADS score 3. More than 90.0% of GPT-4 -generated reports were comprehensive and easy to understand, but less satisfied with the accuracy (82.8%). GPT-4 also demonstrated cognitive potential for handling complex problems. Additionally, the Chain of Thought method enabled us to better understand the decision-making logic behind GPT-4. Eventually, we developed a ProstAIGuide platform to facilitate accessibility for both doctors and patients. This multi-center study highlights the clinical utility of GPT-4 for prostate biopsy decision-making and advances our understanding of the latest artificial intelligence implementation in various medical scenarios.

Topics

Prostatic NeoplasmsMultiparametric Magnetic Resonance ImagingDecision MakingJournal ArticleMulticenter Study

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.