Purpose: To perform a systematic review and network meta-analysis to compare the efficacy and safety of currently available docetaxel-based systemic triplet therapies for metastatic hormone-sensitive prostate cancer (mHSPC).Methods: We searched for eligible publications in PubMed, Embase, and Cochrane CENTRAL. Improvements in overall survival (OS) and radiographic progression-free time (rPFS) were compared indirectly using network meta-analysis and evaluated using the surface under the cumulative ranking curve (SUCRA). Other secondary endpoints, such as time to castration-resistant prostate cancer and/or adverse events (AEs), were also compared and evaluated.Results: Five trials were selected and analyzed using a network meta-analysis. Compared to androgen deprivation therapy (ADT) plus docetaxel, darolutamide (hazard ratio [HR]: 0.68, 95% credible interval [CrI]: 0.57–0.80) and abiraterone (HR: 0.75, 95% CrI: 0.59–0.95) triplet therapy had significantly longer OS, and darolutamide triplet therapy was the first treatment ranked. Abiraterone (HR: 0.49, 95% CrI: 0.39–0.61) and enzalutamide (HR: 0.52, 95% CrI: 0.30–0.89) had significantly better rPFS than ADT plus docetaxel; however, all three therapies, including abiraterone, apalutamide, and enzalutamide, were the best options with a similar SUCRA. At most secondary endpoints, systemic triplet therapy was superior to ADT plus docetaxel. The risk of any AEs in darolutamide or abiraterone triplet therapy was comparable with ADT plus docetaxel (odds ratio [OR]: 2.53, 95% credible interval [CrI]: 0.68–12.63; OR: 1.07, 95% CrI: 0.03–36.25). Abiraterone triplet therapy had an increased risk of grade≥3 AEs (OR: 1.56, 95% CrI: 1.15–2.11).Conclusion: Systemic triplet therapy was more effective than ADT plus docetaxel for mHSPC. Of the triplet therapy regimens, darolutamide ranked first in terms of improved OS. Abiraterone and enzalutamide triplet ranked first in terms of rFPS, however, it did not confer a statistically difference among all triplet regimens. The overall risk of AEs was comparable. More studies are required for current and potential combinations of systemic triplet therapy.

PurposePSA is currently the most commonly used screening indicator for prostate cancer. However, it has limited specificity for the diagnosis of prostate cancer. We aim to construct machine learning-based models and enhance the prediction of prostate cancer.MethodsThe data of 551 patients who underwent prostate biopsy were retrospectively retrieved and divided into training and test datasets in a 3:1 ratio. We constructed five PCa prediction models with four supervised machine learning algorithms, including tPSA univariate logistic regression (LR), multivariate LR, decision tree (DT), random forest (RF), and support vector machine (SVM). The five prediction models were compared based on model performance metrics, such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, calibration curve, and clinical decision curve analysis (DCA).ResultsAll five models had good calibration in the training dataset. In the training dataset, the RF, DT, and multivariate LR models showed better discrimination, with AUCs of 1.0, 0.922 and 0.91, respectively, than the tPSA univariate LR and SVM models. In the test dataset, the multivariate LR model exhibited the best discrimination (AUC=0.918). The multivariate LR model and SVM model had better extrapolation and generalizability, with little change in performance between the training and test datasets. Compared with the DCA curves of the tPSA LR model, the other four models exhibited better net clinical benefits.ConclusionThe results of the current retrospective study suggest that machine learning techniques can predict prostate cancer with significantly better AUC, accuracy, and net clinical benefits.

No abstract