Utility of Machine Learning Models to Predict Lymph Node Metastasis of Japanese Localized Prostate Cancer.

Abstract

Background/objectives: Extended pelvic lymph node dissection is a crucial surgical technique for managing intermediate to high-risk prostate cancer. Accurately predicting lymph node metastasis before surgery can minimize unnecessary lymph node dissections and their associated complications. This study assessed the efficacy of various machine learning models for predicting lymph node metastasis in a cohort of Japanese patients who underwent robot-assisted laparoscopic radical prostatectomy.

Methods: Data from 625 patients who underwent extended pelvic lymph node dissection or standard dissection with lymph node metastasis between October 2010 and February 2023 were analyzed. Four machine learning models-Random Forest, Light Gradient-Boosting Machine, Logistic Regression, and Support Vector Machine-were used to predict lymph node metastasis. Their performance was assessed using receiver operating characteristic curves, a decision curve analysis, and predictive values at different thresholds.

Results: Lymph node metastasis was observed in 34 patients (5.4%). The Light Gradient-Boosting Machine had the highest AUC of 0.924, followed by the Random Forest model with an AUC of 0.894. The decision curve analysis indicated substantial net benefits for both models, particularly at low threshold probabilities. The Light Gradient-Boosting Machine demonstrated superior accuracy, achieving 95.6% at the 0.05 threshold and 96.7% at the 0.10 threshold, outperforming other models and conventional nomograms in the validation dataset.

Conclusion: Machine learning models, especially Light Gradient-Boosting Machine and Random Forest, show significant potential for predicting lymph node metastasis in prostate cancer, thereby aiding in reducing unnecessary surgical interventions.