Related Experiment Video
Updated: May 18, 2026
07:13
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Predicting Positive Surgical Margins in Robot-Assisted Prostatectomy Using Machine Learning Models
Gen Fan1, Haochuan Chen2, Yang Li1
1Department of Urology, School of Clinical Medicine, North Sichuan Medical College, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China.
Summary
A machine learning model can predict positive surgical margins (PSM) after robot-assisted radical prostatectomy (RARP). The artificial neural network (ANN) shows promise for risk stratification, but requires further validation before clinical use.
Area of Science:
- Urology
- Oncology
- Artificial Intelligence
Background:
- Positive surgical margins (PSM) are a concern in robot-assisted radical prostatectomy (RARP).
- Accurate prediction of PSM can aid in surgical planning and patient counseling.
Purpose of the Study:
- To develop and evaluate machine learning (ML) models for predicting PSM after RARP.
- Identify key predictors of PSM in this patient cohort.
Main Methods:
- Retrospective analysis of 301 RARP patients.
- Feature selection using the Boruta algorithm, followed by development and evaluation of seven ML models.
- Optimal model interpretation using SHAP (SHapley Additive exPlanations).
Main Results:
- PSM incidence was 42.0%.
- The artificial neural network (ANN) model achieved the highest performance (AUC 0.808, accuracy 0.811).
- Key predictors included clinical T stage and biopsy percentage; neoadjuvant therapy was protective.
Conclusions:
- The developed ANN model shows potential for predicting PSM in RARP.
- The model can serve as an exploratory tool for risk stratification.
- External validation is necessary before clinical implementation.
