Predictive Power of Combined Inflammatory Markers and MRI Features for Glioma Prognosis Using Machine Learning

Motivation: Exploring the differential ability of MR combined with inflammatory markers for glioma grading. Goal(s): Predicting the prognosis of glioma by integrating inflammatory markers and MRI characteristics through machine learning models. Approach: A total of 179 patients diagnosed with glioma were included in the analysis. Key MRI-derived features were examined alongside inflammatory markers. We evaluated various machine learning classifiers, using metrics such as AUC, accuracy, and F1 score. Results: The RF model exhibited superior predictive performance, achieving an AUC of 0.90 and an F1 score of 0.997, highlighting its efficacy in accurately distinguishing between high-grade and low-grade gliomas. Impact: 1.Key MRI-derived features and inflammatory markers were both used to train a model. 2.The models showed superior predictive performance. 3.The models can be used for distinguishing between high-grade and low-grade gliomas.