Development and validation of a preoperative grading system incorporating MRI and clinicopathological features to predict positive surgical margins in robot-assisted laparoscopic prostatectomy

To develop a grading system integrating MRI and clinicopathological features for predicting positive surgical margin (PSM) following robotic-assisted laparoscopic prostatectomy (RALP) among patients with prostate cancer. Patients undergoing RALP were retrospectively included with consecutive MRI examinations collected from two centers (center 1 and center 2). The train cohort included patients at center 1 between January 2020 and December 2021, and the validation cohort comprised those between January 2022 and December 2022. Patients from center 2 were assigned to the test cohort. MRI and clinicopathological features associated with PSM were assessed. A logistic regression model was used to develop the grading system. The prediction and calibration performance were evaluated by area under the receiver operating characteristic curves (AUCs) and Hosmer-Lemeshow goodness-of-fit test. AUC values were compared by Delong test. A total of 396 patients and 29.2% (64/219), 37.6% (26/69) and 38.0% (41/108) of patients in the train, validation and test cohorts exhibited PSMs, respectively. The grading system comprised clinical risk stratification (ESMO-risk) and MRI features. The PSM grading system demonstrated good prediction performance (AUC 0.79, 95% CI: 0.70, 0.86) and showed good calibration (P = 0.82) in the test cohorts. When compared with ESMO-risk (AUC: 0.70, 95% CI: 0.60, 0.78), Park’s model (AUC: 0.72, 95% CI: 0.63, 0.81) and Xu’s model (AUC: 0.70, 95% CI: 0.60, 0.78) in the test cohort, our PSM grading system demonstrated higher AUC value (P < 0.05). The PSM grading system integrating MRI and clinicopathological features can assess the likelihood of PSM after RALP.