Machine-learning Algorithm-based Risk Prediction and Screening-detected Prostate Cancer in A Benign Prostate Hyperplasia Cohort

Abstract

Background/Aim: Prostate cancer (PCa) is lethal. Our aim in this retrospective cohort study was to use machine learning-based methodology to predict PCa risk in patients with benign prostate hyperplasia (BPH), identify potential risk factors, and optimize predictive performance. Patients and Methods: The dataset was extracted from a clinical information database of patients at a single institute from January 2000 to December 2020. Patients newly diagnosed with BPH and prescribed alpha blockers/5-alpha-reductase inhibitors were enrolled. Patients were excluded if they had a previous diagnosis of any cancer or were diagnosed with PCa within 1 month of enrolment. The study endpoint was PCa diagnosis. The study utilized the extreme gradient boosting (XGB), support vector machine (SVM) and K-nearest neighbors (KNN) machine-learning algorithms for analysis. Results: The dataset used in this study included 5,122 medical records of patients with and without PCa, with 19 patient characteristics. The SVM and XGB models performed better than the KNN model in terms of accuracy and area under curve. Local interpretable model-agnostic explanation and Shapley additive explanations analysis showed that body mass index (BMI) and late prostate-specific antigen (PSA) were important features for the SVM model, while PSA velocity, late PSA, and BMI were important features for the XGB model. Use of 5-alpha-reductase inhibitor was associated with a higher incidence of PCa, with similar survival outcomes compared to non-users. Conclusion: Machine learning can enhance personalized PCa risk assessments for patients with BPH but more research is necessary to refine these models and address data biases. Clinicians should use them as supplementary tools alongside traditional screening methods.