Development and Deployment of a Machine Learning Model to Triage the Use of Prostate MRI (ProMT-ML) in Patients With Suspected Prostate Cancer.
Authors
Affiliations (5)
Affiliations (5)
- Department of Urology, NYU Grossman School of Medicine, New York, New York, USA.
- Department of Radiology, NYU Grossman School of Medicine, New York, New York, USA.
- Courant Institute of Mathematical Sciences, New York University, New York, New York, USA.
- Department of Population Health, NYU Grossman School of Medicine, New York, New York, USA.
- Department of Urology, Bellevue Hospital, New York City Health and Hospitals, New York, New York, USA.
Abstract
Access to prostate MRI remains limited due to resource constraints and the need for expert interpretation. To develop machine learning (ML) models that enable risk-based triage for prostate MRI (ProMT-ML) in the evaluation of prostate cancer. Retrospective and prospective. A total of 11,879 retrospective MRI scans for suspected prostate cancer from a multi-hospital health system, divided into training (N = 9504) and test (N = 2375) sets. A total of 4551 records for prospective validation. 1.5T and 3T/Turbo-spin echo T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE). Prostate Imaging Reporting and Data System (PI-RADS) scores were retrieved from MRI reports. The Boruta algorithm was used to select final input features from candidate features. Two models were developed using supervised ML to estimate the likelihood of an abnormal MRI, defined as PI-RADS ≥ 3: Model A (with prostate volume) and Model B (without prostate volume). Models were compared to PSA. Prostate biopsy pathology was assessed to evaluate potential clinical impact. Area under the receiver operating characteristic curve (AUC) was the primary performance metric. A total of 5580 (46.9%) subjects had a PI-RADS score ≥ 3. After feature selection, Model A included age, PSA, body mass index, and prostate volume, while Model B included age, PSA, body mass index, and systolic blood pressure. Both models A (AUC 0.711) and B (AUC 0.616) significantly outperformed PSA (AUC 0.593). Compared to PSA threshold > 4 ng/mL, Model A demonstrated significantly improved specificity (28.3% vs. 21.9%) and no significant difference in sensitivity (89.0% vs. 86.7%). Among false negatives (Model A: 8.0% (62/776); Model B: 16.8% (130/776)), most (Model A: 87%; Model B: 69%) had benign or clinically insignificant disease on biopsy. On prospective validation, both versions of ProMT-ML significantly outperformed PSA. ProMT-ML provides personalized risk estimates of abnormal prostate MRI and can support triage of this test. Stage 4.