Predictive model of positive surgical margins after radical prostatectomy based on Bayesian network analysis

TL;DR

This study developed a Bayesian network model to predict positive surgical margins after prostate cancer surgery, showing better accuracy than traditional methods.

Contribution

A novel Bayesian network-based predictive model for positive surgical margins after radical prostatectomy is proposed and validated.

Findings

The TAN Bayesian model achieved an AUC of 80.80%, outperforming the nomogram model (AUC 73.80%).

Key predictors included PSA density, Gleason scores, and MRI characteristics like abnormal signal location.

The model demonstrated high accuracy and clinical utility for predicting positive surgical margins.

Abstract

This study aimed to analyze the independent risk factors for marginal positivity after radical prostatectomy and to evaluate the clinical value of the predictive model based on Bayesian network analysis.

We retrospectively analyzed the clinical data from 238 patients who had undergone radical prostatectomy, between June 2018 and May 2022. The general clinical data, prostate specific antigen (PSA)–derived indicators, puncture factors, and magnetic resonance imaging (MRI) characteristics were included as predictive variables, and univariate and multivariate analyses were conducted. We established a nomogram model based on the independent predictors and adopted BayesiaLab software to generate tree-augmented naive (TAN) and naive Bayesian models based on 15 predictor variables.

Of the 238 patients included in the study, 103 exhibited positive surgical margins. Univariate analysis revealed that PSA density (PSAD) (P = 0.02), Gleason scores for biopsied tissue (P = 0.002) and the ratio of positive biopsy cores (P < 0.001), preoperative T staging (P < 0.001), and location of abnormal signals (P = 0.002) and the side of the abnormal signal (P = 0.009) were all statistically significant. The area under curve (AUC) of the established nomogram model based on independent predictors was 73.80%, the AUC of the naive Bayesian model based on 15 predictors was 82.71%, and the AUC of the TAN Bayesian model was 80.80%.

The predictive model of positive resection margin after radical prostatectomy based on Bayesian network demonstrated high accuracy and usefulness.

Figures