GradWise: A Novel Application of a Rank-Based Weighted Hybrid Filter and Embedded Feature Selection Method for Glioma Grading with Clinical and Molecular Characteristics

SIMPLE SUMMARY: Glioma tumor aggressiveness is expressed as tumor grading which is crucial in guiding treatment decisions and clinical trial participation. Accurate and standardized grading systems are essential to optimize care and improve outcomes. However, integrating molecular and clinical information in the grading process has the potential to expose molecular markers that have gained importance in understanding tumor biology as a means of identifying druggable targets. In this study, a novel approach called GradWise is introduced with the goal of enhancing feature selection performance while employing various machine learning models of glioma grading. GradWise combines a rank-based weighted hybrid filter (mRMR) and an embedded feature selection method (LASSO) to select the most relevant features from clinical and molecular predictors and was evaluated using two commonly employed public biomedical datasets, TCGA and CGGA, utilizing two feature selection methods and five supervised models. The findings support existing evidence and provide pioneering results for glioma-specific biomarkers, highlighting the effectiveness of the approach and future directions for biological mechanisms of glioma progression to higher grades. ABSTRACT: Glioma grading plays a pivotal role in guiding treatment decisions, predicting patient outcomes, facilitating clinical trial participation and research, and tailoring treatment strategies. Current glioma grading in the clinic is based on tissue acquired at the time of resection, with tumor aggressiveness assessed from tumor morphology and molecular features. The increased emphasis on molecular characteristics as a guide for management and prognosis estimation underscores is driven by the need for accurate and standardized grading systems that integrate molecular and clinical information in the grading process and carry the expectation of the exposure of molecular markers that go beyond prognosis to increase understanding of tumor biology as a means of identifying druggable targets. In this study, we introduce a novel application (GradWise) that combines rank-based weighted hybrid filter (i.e., mRMR) and embedded (i.e., LASSO) feature selection methods to enhance the performance of feature selection and machine learning models for glioma grading using both clinical and molecular predictors. We utilized publicly available TCGA from the UCI ML Repository and CGGA datasets to identify the most effective scheme that allows for the selection of the minimum number of features with their names. Two popular feature selection methods with a rank-based weighting procedure were employed to conduct comprehensive experiments with the five supervised models. The computational results demonstrate that our proposed method achieves an accuracy rate of 87.007% with 13 features and an accuracy rate of 80.412% with five features on the TCGA and CGGA datasets, respectively. We also obtained four shared biomarkers for the glioma grading that emerged in both datasets and can be employed with transferable value to other datasets and data-based outcome analyses. These findings are a significant step toward highlighting the effectiveness of our approach by offering pioneering results with novel markers with prospects for understanding and targeting the biologic mechanisms of glioma progression to improve patient outcomes.