Interpretable machine learning for prostate biopsy: Cohort study.

333 Background: The objective of this study is to develop prediction models and provide diagnostic results for prostate biopsy among patients. Methods: This paper presents an improved tree model, called the Light gradient boosting machine model, for building a prostate cancer (PCa) risk prediction model. The research data used in this study (Waves 2008-2022) are obtained from 1987 patients who underwent transperineal biopsy at West China Hospital. All patients had biopsy indications (high levels of prostate specific antigen (PSA), suspect lesions in magnetic resonance imaging (MRI) suspect lesions). A total of 13 baseline variables were considered as candidate features, and eight machine learning models were compared in the experiment. Shapley additive explanations (SHAP) was used for explaining the prediction model. Results: The Light gradient boosting machine model demonstrated the best performance, achieving an area under the receiver operating characteristic (ROC) curve of 0.76 (CatBoost=0.71, KNN=0.65, LDA=0.61, CART=0.67, SVM=0.64, NB=0.55, XGBoost=0.71). According to the interpretable analysis, the apparent diffusion coefficient (ADC) of MRI was identified as the most important feature in the prediction model. Other important features included prostate volume, red blood cell count, neutrophil count, and platelet count. Conclusions: This study suggests that optimal models show promise in screening out patients at high risk for PCa in prostate biopsies. The decisions regarding prostate biopsies should specifically focus on the ADC of MRI, prostate volume, and blood routine indices such as RBC count, platelet count, and neutrophil count. Baseline characteristic of all patients. Mean (SD) Pca (n=1001) Non-Pca (n=986) P Age (years) 68.68(9.29) 67.99(9.32) 0.901 Blood routine RBC (10 12 /L) 4.66(0.62) 4.65(0.61) 0.56 Hemoglobin (g/L) 141.46(19.72) 141.84(17.21) 0.149 Platelet (10 9 /L) 188.49(64.65) 193.46(69.12) 0.02 WBC (10 9 /L) 6.76(6.36) 6.6(1.95) 0.56 Neutrophil count (10 9 /L) 4.15(1.52) 4.19(1.71) 0.026 Lymphocyte count (10 9 /L) 1.89(5.73) 1.75(0.76) 0.405 Monocyte count (10 9 /L) 0.48(0.16) 0.47(0.17) 0.626 Eosinophil count (10 9 /L) 0.16(0.16) 0.15(0.16) 0.781 Basophil Cell Count (10 9 /L) 0.25(1.21) 0.36(1.47) <0.001 PSA (ng/ml) 65.02(346.16) 11.32(23.01) <0.001 Prostate volume (ml) 43.96(27.66) 51.24(26.85) 0.007 PSAD (ng/ml 2 ) 1.82(12.88) 0.28(0.544) 0.001 ADC 733.13(172.09) 756.93(181.31) 0.004