Multi-Modal Machine Learning Framework for Predicting Early Recurrence of Brain Tumors Using MRI and Clinical Biomarkers
This work addresses a clinical problem for brain tumor patients, but it is incremental as it applies existing machine learning methods to a new multimodal dataset.
The study tackled the challenge of predicting early recurrence in brain tumor patients after surgery by integrating structural MRI features with clinical biomarkers, achieving promising performance with metrics like C-index and time-dependent AUC.
Accurately predicting early recurrence in brain tumor patients following surgical resection remains a clinical challenge. This study proposes a multi-modal machine learning framework that integrates structural MRI features with clinical biomarkers to improve postoperative recurrence prediction. We employ four machine learning algorithms -- Gradient Boosting Machine (GBM), Random Survival Forest (RSF), CoxBoost, and XGBoost -- and validate model performance using concordance index (C-index), time-dependent AUC, calibration curves, and decision curve analysis. Our model demonstrates promising performance, offering a potential tool for risk stratification and personalized follow-up planning.