High-grade inflammation in prostate cancer as a prognostic factor for biochemical recurrence after radical prostatectomy

Objectives: To develop a model to predict biochemical recurrence (BCR) after radical prostatectomy (RP), using artificial intelligence (AI) techniques. Patients and Methods: This study collected data from 7,128 patients with prostate cancer (PCa) who received RP at 3 tertiary hospitals. After preprocessing, we used the data of 6,755 cases to generate the BCR prediction model. There were 16 input variables with BCR as the outcome variable. We used a random forest to develop the model. Several sampling techniques were used to address class imbalances. Results: We achieved good performance using a random forest with synthetic minority oversampling technique (SMOTE) using Tomek links, edited nearest neighbors (ENN), and random oversampling: accuracy = 96.59%, recall = 95.49%, precision = 97.66%, F1 score = 96.59%, and ROC AUC = 98.83%. Conclusion: We developed a BCR prediction model for RP. The Dr. Answer AI project, which was developed based on our BCR prediction model, helps physicians and patients to make treatment decisions in the clinical follow-up process as a clinical decision support system.

Download Full-text

Comparison of functional and oncological outcomes of innovative “three-port” and traditional “four-port” laparoscopic radical prostatectomy in patients with prostate cancer

BMC Urology ◽

10.1186/s12894-021-00787-7 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Ben Xu ◽

Si-da Cheng ◽

Yi-ji Peng ◽

Qian Zhang

Keyword(s):

Prostate Cancer ◽

Radical Prostatectomy ◽

Biochemical Recurrence ◽

Laparoscopic Radical Prostatectomy ◽

Positive Surgical Margin ◽

Oncological Outcomes ◽

Estimated Blood Loss ◽

Significant Difference ◽

Group A ◽

Group B

Abstract Background To compare the functional and oncological outcomes between innovative “three-port” and traditional “four-port” laparoscopic radical prostatectomy (LRP) in patients with prostate cancer (PCa). Methods We retrospectively collected the data of PCa patients treated at our institutions from June 2012 to May 2016. According to the inclusion criteria, a total of 234 patients were included in the study, including 112 in group A (four-port) and 122 in group B (three-port). The perioperatively surgical characteristics, functional and oncological outcomes were compared between groups. Results There were no statistical differences in the baseline parameters between these two groups. Compared with group A, the operative time (OT) and estimated blood loss (EBL) were significantly less in group B. On follow-up, the rate of positive surgical margin (PSM), prostate specific antigen (PSA) biochemical recurrence and continence after LRP did not show any statistically significant difference between the groups. An identical conclusion was also received in comparison of overall survival (OS) and biochemical recurrence-free survival (BRFS) between both groups. Conclusions Innovative “three-port” LRP can significantly shorten the OT and reduce the EBL compared with the traditional “four-port” LRP. Meanwhile, it does not increase the rate of PSM and PSA biochemical recurrence. “Three-port” LRP could be popularized in the future in view of its superior surgical technique, considerably better functional outcomes and remarkable oncological control.

Download Full-text