Biom-66. establishment of a prognostic model for glioblastoma multiforme magnetic resonance imaging based on imbalanced classes, classification, and kaplan-meier survival curve learning algorithms

Glioblastoma multiforme (GBM) is a rapidly invasive brain tumor with a high mortality rate. It is accompa-nied by peripheral edema. Physicians use magnetic resonance imaging (MRI) to diagnose each patient’s con-dition in clinical practice. The current use of machine learning to classify brain tumors has an accuracy of about 90% in most studies. Therefore, this study aimed to improve its prediction accuracy using machine learning models to predict GBM patient survival or non-survival. The study used MRI T1-related and T2-related sequences to obtain GBM tumor and edema area attributes. It then divided them into four da-tasets: maximum tumor area, maximum edema area, total tumor volume, and total edema volume. These four datasets were used as inputs for classification models based on support vector machines, decision tree algo-rithms, random forest algorithms, and multilayer perceptron (MLP) to predict patient survival. A confusion matrix was used to evaluate each model and determine the most suitable models for each dataset based on their accuracy. MLP was the most appropriate for predicting the overall edema volume dataset, with the highest accuracy in predicting GBM patient survival or non-survival at 96.97%. Hopefully, this study can assist physicians in assessing and diagnosing GBM patients’ survival status in the future. Keywords: Classification Models; Glioblastoma Multiforme; KaplanMeier Curve; Magnetic Resonance Imaging; Peritumoral Edema