TITLE:
Advancing Glioblastoma Prognosis: A Review of Machine Learning, Radiomics, and Multi-Omics Integration for Survival Prediction and Subtyping
AUTHORS:
Muna Awel, Rushit Dave, Mansi Bhavsar
KEYWORDS:
GBM, Survival Prediction, Machine Learning (ML), Deep Learning (DL), Radiomics, Multi-Omics, Feature Engineering Clustering
JOURNAL NAME:
Journal of Computer and Communications,
Vol.13 No.5,
May
23,
2025
ABSTRACT: Glioblastoma (GBM) is known for its poor prognosis and aggressive nature, driving the need for advanced models that provide survival prediction to improve patient prognosis. This literature review synthesizes 20 studies employing machine learning (ML), deep learning (DL), radiomics, and clustering to enhance GBM prognosis using clinical, imaging, and molecular data. The review is grouped into five thematic groups based on their methodology and data type. Studies within these groups explore the predictive accuracy of models, evaluation metrices, and data types of implementations. The research also highlights the limitations which include small datasets, sparse clinical variables, computational complexity, and hindering scalability and generalizability. This review provides a clear understanding of the various studies that are aimed at enhancing patient prognosis in glioblastoma through advanced predictive and subtyping methodologies.