Accurate histopathological grading of gliomas is critical for clinical management but remains dependent on subjective pathological assessment. This study developed a machine learning framework to predict glioma grade from clinicogenomic features in the TCGA cohort. A multimodal feature set was constructed, comprising demographic variables, mutation status of glioma-associated genes, and derived statistical features. Six machine learning algorithms—Logistic Regression, Random Forest, Support Vector Machine, k-Nearest Neighbors, Gradient Boosting, and a Multilayer Perceptron—were systematically evaluated. After hyperparameter optimization of the top-performing models, an ensemble model was implemented to improve predictive stability. The final ensemble achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.935 on an independent test set. Feature importance analysis identified mutations in IDH1 and TP53, alongside patient age at diagnosis, as the strongest predictive features, consistent with established neuro-oncological knowledge. Model robustness was confirmed through bootstrap validation. This work establishes a reproducible computational workflow that integrates multi-algorithm comparison, systematic hyperparameter tuning, and interpretable feature analysis, providing a framework to support objective glioma grading and the potential translation of genomic biomarkers into clinical practice.

Zhang Yucheng, Zhang Lu, Luo Shunan. Multi-Model Comparison and Feature Importance Analysis in Machine Learning-Based Glioma Grade Prediction. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 1: 103-109. https://doi.org/10.25236/AJCIS.2026.090113.

[1] Yuanzi Liang,Junqi Hu,Tianhui Wu,Dong Bai,Zhiqun Wang.Development and validation of multiple machine learning algorithms for differentiating primary central nervous system lymphoma from adult-type diffuse glioma: an interpretable and multicenter study[J].Frontiers in Oncology,2026,1713099.

[2] Amir Mahmoud Ahmadzadeh,Amirhossein Jafarnezhad,Danial Elyassirad,Mahsa Vatanparast, Benyamin Gheiji,Shahriar Faghani.Improving radiomics-based isocitrate dehydrogenase 1 prediction in glioma patients using semi-supervised machine learning models.[J].BMC medical imaging, 2025,26(1):31.

[3] Chen Yang,JieFei Ma,RanZe Cai,Hong Gao,Fan Hu,QiuPing Li.Integrating of Machine Learning to Characterize Tumor-Infiltrating Immune Cell-Related Signature for Enhancing Prognosis for Glioma Patients[J].Biological Procedures Online,2025,27(1):46.

[4] Khashayar Namdar,Matthias W. Wagner,Min Sheng,Peter Dirks,Kristen W. Yeom,Cynthia Hawkins, Uri Tabori,Birgit B. Ertl Wagner,Farzad Khalvati.Multiclass machine learning models for molecular subtype identification of pediatric low-grade glioma using bi-institutional MRIs for precision medicine[J]. npj Precision Oncology,2025,9(1):357.

[5] Linda Tang ,Yuncong Mao ,Melanie Alfonzo Horowitz ,Saket Myneni ,Julian Gendreau ,Jacob Gould ,A Karim Ahmed ,Jordina Rincon Torroella ,Chetan Bettegowda ,Jon Weingart ,Christopher Jackson ,Gary Gallia ,Debraj Mukherjee.INNV-47. Development and validation of a machine learning model for predicting grade IV glioma recurrence[J].Neuro-Oncology,2025,27(Supplement_5):v235-v236.

[6] Zeyu Ma,Chaoli Zhang,Yang Guo,Yinhua Li,Zilong Wang,Yanmei Hu,Xueping Zhang,Mengjiao Duan, Weiwei Wang,Dongming Yan,Xianzhi Liu,Jingliang Cheng,Jinqiao Zhou,Zhenyu Zhang,Jing Yan. Improving radiomics-based differentiation of supratentorial malignant brain tumors preoperatively with diffusion-weighted imaging: A three-class machine learning algorithm.[J].European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology,2025,51(12):110533.

[7] Mohammadreza Elhaie,Abolfazl Koozari,Hossein Koohi,Salman Mohammed Albeshan.Amide proton transfer imaging with machine learning and deep learning for malignant tumor diagnosis: a systematic review[J].Journal of Medical Imaging and Interventional Radiology,2025,12(1):33.

[8] Xu Zheng,Jianpeng Liu,Jiheng Zhang.Pan-cancer and machine learning reveal the role of cell adhesion molecules in prognosis, immune remodeling, and anti-tumour therapy in lower-grade gliomas.[J].Discover oncology,2025,16(1):1842.

[9] Hanqin Du,Chayanit Piyawajanusorn,Ghita Ghislat,Pedro J. Ballester.Predicting temozolomide response in low-grade glioma patients with large-scale machine learning[J].BMC Methods, 2025, 2(1):25.

[10] Shunichi Koriyama,Yutaka Matsui,Takahiro Shioyama,Mikoto Onodera,Manabu Tamura,Tatsuya Kobayashi,Buntou Ro,Kenta Masui,Takashi Komori,Yoshihiro Muragaki,Takakazu Kawamata.High-precision intraoperative diagnosis of gliomas: integrating imaging and intraoperative flow cytometry with machine learning[J].Frontiers in Neurology,2025,1647009.

[11] Guanfu Li,Chunyou Ye,Weiwei Chen,Peiyao Hao,Fang He,Jijun Han.Measurement and classification of dielectric properties in human brain tissues: differentiating glioma from normal tissues using machine learning.[J].Physical and engineering sciences in medicine,2025,(prepublish):1-12.