eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2025-09-30 18 3 2014 2023 10.13005/bpj/3233 67353 article Virendra Singh Kushwah 1 Sivaneasan Bala Krishnan 2 Kamal Upreti 3 Pravin Kshirsagar 4 Manoj Kumar 5 Uma Shankar 6 Department of CSE and AI, VIT Bhopal University, Sehore, Madhya Pradesh, Indi Department. of Electrical and Electronics Engineering, Singapore Institute of Technology, Singapore Department of Computer Science, Christ University, Delhi NCR Campus, Ghaziabad, India Department of Electronics and Telecommunication Engineering, J D College of Engineering and Management, Nagpur, India Department of Mathematics and Statistics, Gurukula Kangri University, Haridwar, Uttarakhand, India Department of Management and Social Sciences, Qaiwan International University, Sulaimanyah, Kurdistan, Iraq. Early detection, therapeutic stratification, and precision medicine all rely on the precise classification of brain cancer subtypes.   To categorize brain tumor subtypes, we examine the application of ensemble machine learning models—Random Forest, XGBoost, and LightGBM—using high-dimensional gene expression data from the GSE50161 dataset (CuMiDa).   The top 1000 genes were selected using variance thresholding, and models were then trained and evaluated on a stratified split of the dataset.   Despite the availability of models achieving similar accuracies (~95–96%) in existing works, our framework integrates SHAP-based interpretability to identify biologically significant genes, such as CDK4, EGFR, and TP53, offering dual benefits of high predictive power and explainability. The use of SHAP (SHapley Additive exPlanations) values to assess model predictions and identify physiologically important gene features revealed that key gene probes, including as CDK4, EGFR, and TP53, were significant across different tumor subtypes. This study demonstrates how SHAP and interpretable ensemble learning may be used to diagnose brain tumors with excellent classification accuracy and physiologically meaningful gene identification. https://biomedpharmajournal.org/vol18no3/gene-expression-data-based-interpretable-machine-learning-framework-for-classifying-brain-cancer-subtypes/ Brain Cancer Biomarker Identification Cell Lines Gene-expression Machine Learning Microarray Data