Abstract
Purpose During MRI/US fusion biopsy targeted and systematic sampling is performed. Systematic sampling adds up to 14% to the cancer detection rate but increases the complication rates. Since, only the highest risk prostate cancer determines the treatment course, systematic sampling with lower risk cancer compared to the targeted sampling is redundant. Our aim is to develop a prediction model to predict which patient will harbor higher risk prostate cancer in the systematic compared to the targeted biopsy in prostate fusion biopsy.Methods We included all patients who underwent fusion biopsy. Clinical and radiographic variables were collected from patients records. The outcome of the model was higher risk prostate cancer in the systematic compared with targeted biopsies. Extreme Gradient boosting model was trained and tested. We evaluated variable importance and clinical benefit.Results Five hundred and twenty-nine patients were included. 82 (15.5%) patients had higher risk prostate cancer in the systematic biopsies. The area under the ROC curve and negative predictive value were 0.82 and 0.92, respectively. The 4 most important features for outcome prediction were prostate volume, PSAD, patient's age and PSA. The decision curve showed increased clinical benefit of our model at threshold probabilities of 0-0.5. Limitations include the retrospective design of the study and lack of external validation of the model.Conclusions We developed a prediction model able to accurately predict which patient must undergo systematic and targeted biopsy. This prediction model has the potential to help in the decision whether to perform SB and thus may lower adverse event rate while keeping high detection rate.