Predicting the Molecular Subtypes of 2021 WHO Grade 4 Glioma by a Multiparametric MRI-Based Machine Learning Model

Motivation: Accurately predict the molecular subtypes of 2021 WHO grade 4 glioma Goal(s): To develop and validate a machine learning (ML) model using multiparametric MRI for the preoperative differentiation of grade 4 astrocytoma and glioblastoma (GBM) (Task 1), and to stratify grade 4 astrocytoma to distinguish isocitrate dehydrogenase-mutant (IDH-mut) from IDH-wild-type (IDH-wt) (Task 2). Additionally, to evaluate the model's prognostic value Approach: retrospectively study Results: The combined model and the optimal ML model significantly outperformed the clinical model in both the training and validation sets. Survival analysis showed the combined model performed similarly to molecular subtype in both tasks. Impact: l The multiparametric MRI machine learining model can accurately predict molecular subtypes of 2021 WHO grade 4 glioma, offers substantial prognostic value and provides a new perspective for clinical decision-making.