XGBoost Improves Classification of MGMT Promoter Methylation Status in IDH1 Wildtype Glioblastoma

• Published in: Journal of personalized medicine Vol. 10; no. 3; p. 128
• Main Authors: Le, Nguyen Quoc Khanh, Do, Duyen Thi, Chiu, Fang-Ying, Yapp, Edward Kien Yee, Yeh, Hui-Yuan, Chen, Cheng-Yu
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 15-09-2020; MDPI
• Subjects: Algorithms; Biomarkers; Brain cancer; Chemoresistance; Chemotherapy; Diagnosis; DNA methylation; DNA methyltransferase; Feature selection; Genetic aspects; Glioblastoma; Glioblastomas; Health aspects; Image processing; Machine learning; Magnetic resonance imaging; Medical imaging; Methylation; Methylguanine; Methyltransferases; Mutation; O6-methylguanine-DNA methyltransferase; Oxidoreductases; Patients; Performance evaluation; Physiological aspects; Precision medicine; Radiomics; Temozolomide; Tumors; Taiwan
• ISSN: 2075-4426; 2075-4426
• DOI: 10.3390/jpm10030128

Approximately 96% of patients with glioblastomas (GBM) have IDH1 wildtype GBMs, characterized by extremely poor prognosis, partly due to resistance to standard temozolomide treatment. O6-Methylguanine-DNA methyltransferase (MGMT) promoter methylation status is a crucial prognostic biomarker for alkylating chemotherapy resistance in patients with GBM. However, MGMT methylation status identification methods, where the tumor tissue is often undersampled, are time consuming and expensive. Currently, presurgical noninvasive imaging methods are used to identify biomarkers to predict MGMT methylation status. We evaluated a novel radiomics-based eXtreme Gradient Boosting (XGBoost) model to identify MGMT promoter methylation status in patients with IDH1 wildtype GBM. This retrospective study enrolled 53 patients with pathologically proven GBM and tested MGMT methylation and IDH1 status. Radiomics features were extracted from multimodality MRI and tested by F-score analysis to identify important features to improve our model. We identified nine radiomics features that reached an area under the curve of 0.896, which outperformed other classifiers reported previously. These features could be important biomarkers for identifying MGMT methylation status in IDH1 wildtype GBM. The combination of radiomics feature extraction and F-core feature selection significantly improved the performance of the XGBoost model, which may have implications for patient stratification and therapeutic strategy in GBM.