Background: Our objective is to build a model based on Prostate Imaging Reporting and Data System version 2 (PI-RADs v2) and assess its accuracy by internal validation. Methods: Patients who took prostate biopsy from 2014 to 2015 were retrospectively collected to compose training cohort according to the inclusion criteria and patients in 2016 composing validation cohort. Diagnostic performance was evaluated by analyzing the area under the curve (AUC), calibration curves, and decision curves. Results: Of the 441 patients involved, the clinically significant prostate cancer (csPCa) detection rate were 40.6% (114/281) and 43.8% (70/160) in the training and validation cohort, respectively. Meanwhile, PCa detection rate were 50.2% (141/281) and 53.8% (86/160). Age, prostate-specific antigen density (PSAD)* 10 and PI-RADs v2 score composed the model for PCa (model 1) and csPCa (model 2). The area under the curve of models 1 and 2 was 0.870 (95% CI 0.827-0.912) and 0.753 (95% CI 0.717-0.828) in the training cohort, while 0.845 (95% CI 0.786-0.904) and 0.834 (95% CI 0.787-0.882) in the validation cohort. Both models illustrated good calibration, and decision curve analyses showed good performance in predicting PCa or csPCa when the threshold was 0.35 or above. Conclusions: The model based on age, PSAD*10 and PI-RADs v2 score showed internally validated high predictive value for both PCa and csPCa. It could be used to improve the diagnostic performance of suspicious PCa.