Purpose: To explore the role of artificial intelligence and machine learning (ML) techniques in oncological urology. In recent years, our group investigated the prostate cancer gene 3 (PCA3) score, prostate-specific antigen (PSA), and free-PSA predictive role for prostate cancer (PCa), using the classical binary logistic regression (LR) modeling. In this research, we approached the same clinical problem by several different ML algorithms, to evaluate their performances and feasibility in a real-world evidence PCa detection trial. Materials and Methods: The occurrence of a positive biopsy has been studied in a large cohort of 1,246 Italian men undergoing first or repeat biopsy. Seven supervised ML algorithms were selected to build biomarkers-based predictive models: generalized linear model, gradient boosting machine, eXtreme gradient boosting machine (XGBoost), distributed random forest/ extremely randomized forest, multilayer artificial Deep Neural Network, naïve Bayes classifier, and an automatic ML ensemble function. Results: All the ML models showed better performances in terms of area under curve (AUC) and accuracy, when compared to LR model. Among them, an XGBoost model tuned by the autoML function reached the best metrics (AUC, 0.830), well overtaking LR results (AUC, 0.738). In the variable importance ranking coming from this XGBoost model (accuracy, 0.824), the PCA3 score importance was 3-fold and 4-fold larger, when compared to that of free-PSA and PSA, respectively. Conclusions The ML approach proved to be feasible and able to achieve good predictive performances with reproducible results: it may thus be recommended, when applied to PCa prediction based on biomarkers fluctuations.

Purpose: To explore the role of artificial intelligence and machine learning (ML) techniques in oncological urology. In recent years, our group investigated the prostate cancer gene 3 (PCA3) score, prostate-specific antigen (PSA), and free-PSA predictive role for prostate cancer (PCa), using the classical binary logistic regression (LR) modeling. In this research, we approached the same clinical problem by several different ML algorithms, to evaluate their performances and feasibility in a real-world evidence PCa detection trial. Materials and Methods: The occurrence of a positive biopsy has been studied in a large cohort of 1,246 Italian men undergoing first or repeat biopsy. Seven supervised ML algorithms were selected to build biomarkers-based predictive models: generalized linear model, gradient boosting machine, eXtreme gradient boosting machine (XGBoost), distributed random forest/ extremely randomized forest, multilayer artificial Deep Neural Network, naïve Bayes classifier, and an automatic ML ensemble function. Results: All the ML models showed better performances in terms of area under curve (AUC) and accuracy, when compared to LR model. Among them, an XGBoost model tuned by the autoML function reached the best metrics (AUC, 0.830), well overtaking LR results (AUC, 0.738). In the variable importance ranking coming from this XGBoost model (accuracy, 0.824), the PCA3 score importance was 3-fold and 4-fold larger, when compared to that of free-PSA and PSA, respectively. Conclusions The ML approach proved to be feasible and able to achieve good predictive performances with reproducible results: it may thus be recommended, when applied to PCa prediction based on biomarkers fluctuations.

Objective To analyze the safety and effectiveness of robot-assisted laparoscopic partial nephrectomy(RLPN) for cT2 renal tumors in international multi-centers.Methods This study was conducted to collect information on surgical procedures performed by RLPN and robot assisted laparoscopic radical nephrectomy (RRN) in nineteen international urological centers from January 2012 to December 2017.RLPN were performed in 159 patients (118 males and 41 females),with the average age of (59.3 ± 13.2) years,body mass index(BMI) of (28.7 ± 5.4)kg/m2,preoperative GFR of (77.3 ± 22.1) ml/min.RRN were performed in 219 patients,with the average age of (62.0 ± 12.9) years,BMI of (28.7 ±6.1) kg/m2,preoperative GFR of (71.4 ± 20.3) ml/min.There was no statistical difference between the two groups in gender and BMI.The age of the patients in RLPN group was younger than that in RRN group,and the preoperative GFR was better.The patient's baseline demographics,perioperative data,tumor pathology,oncologic outcomes,and renal function (GFR) were recorded.Results All 378 cases underwent successful surgery.The operation time of RLPN was 150 min(65-353 min),which was shorter than that of RRN [180 min(85-361 min),P ＜ 0.001].The intra-operative blood loss of RLPN was more than that of RRN [150 ml (40-3 000 ml) vs.100 ml (10-1 100 ml),P ＜ 0.001].The incidence of intra-operative complications were not statistically different between the two groups [5.7％ (9/159) vs.3.2％ (7/219),P =0.240].The incidence of postoperative complications was higher in the RLPN group than that in RRN group [19.5％ (31/159) vs.10.5％ (23/219),P =0.014],but there was no significant difference in the incidence of complications of grade 3 or above [4.4％ (7/159) vs.2.3％ (5/219),P =0.246].The recurrence-free survival rate of RLPN group was higher than that of RRN group [91.4％ (117/128) vs.81.9％ (167/204),P =0.013],and RLPN group was more conducive to renal function protection (P ＜ 0.001).Conclusions RLPN for cT2 tumors can obtain effective tumor control rate and better renal function preservation.It could be an acceptable alternative for surgical management of cT2 tumors.