A Comparison of Systematic, Targeted, and Combined Biopsy Using Machine Learning for Prediction of Prostate Cancer Risk: A Multi-Center Study

• Published in: Medical principles and practice 2024-10, Vol.33 (5), p.491-500
• Main Authors: Arafa, Mostafa A., Omar, Islam, Farhat, Karim H., Elshinawy, Mona, Khan, Farrukh, Alkhathami, Faisal A., Mokhtar, Alaa, Althunayan, Abdulaziz, Rabah, Danny M., Badawy, Abdel-Hameed A.
• Format: Article
• Language: English
• Subjects: Accuracy; Age; Aged; Algorithms; Artificial intelligence; Biopsy; Body mass index; Humans; Image-Guided Biopsy; Machine Learning; Magnetic resonance imaging; Male; Middle Aged; Multiparametric Magnetic Resonance Imaging; Original Paper; Patients; Prostate - diagnostic imaging; Prostate - pathology; Prostate cancer; Prostate-Specific Antigen - blood; Prostatic Neoplasms - diagnosis; Prostatic Neoplasms - pathology; Retrospective Studies; Risk Assessment; Saudi Arabia - epidemiology; Ultrasonic imaging
• ISSN: 1011-7571; 1423-0151; 1423-0151
• DOI: 10.1159/000540425

Abstract Objectives: The aims of the study were to construct a new prognostic prediction model for detecting prostate cancer (PCa) patients using machine-learning (ML) techniques and to compare those models across systematic and target biopsy detection techniques. Methods: The records of the two main hospitals in Riyadh, Saudi Arabia, were analyzed for data on diagnosed PCa from 2019 to 2023. Four ML algorithms were utilized for the prediction and classification of PCa. Results: A total of 528 patients with prostate-specific antigen (PSA) greater than 3.5 ng/mL who had undergone transrectal ultrasound-guided prostate biopsy were evaluated. The total number of confirmed PCa cases was 234. Age, prostate volume, PSA, body mass index (BMI), multiparametric magnetic resonance imaging (mpMRI) score, number of regions of interest detected in MRI, and the diameter of the largest size lesion were significantly associated with PCa. Random Forest (RF) and XGBoost (XGB) (ML algorithms) accurately predicted PCa. Yet, their performance for classification and prediction of PCa was higher and more accurate for cases detected by targeted and combined biopsy (systematic and targeted together) compared to systematic biopsy alone. F1, the area under the curve (AUC), and the accuracy of XGB and RF models for targeted biopsy and combined biopsy ranged from 0.94 to 0.97 compared to the AUC of systematic biopsy for RF and XGB algorithms, respectively. Conclusions: The RF model generated and presented an excellent prediction capability for the risk of PCa detected by targeted and combined biopsy compared to systematic biopsy alone. ML models can prevent missed PCa diagnoses by serving as a screening tool.