Integration of Artificial Intelligence in Predicting Radiotherapy Outcomes for Glioblastoma Multiforme (GBM)
Year: 2025
Type: article
Study design: Systematic Review
Abstract: Glioblastoma multiforme (GBM) is an aggressive and lethal brain tumorwith limited treatment options and a poor prognosis. Radiotherapy is acornerstone of GBM management, yet predicting treatment responseremains a challenge due to tumor heterogeneity. Artificial intelligence(AI), particularly machine learning (ML) and deep learning (DL), hasemerged as a promising tool for enhancing predictive accuracy andpersonalizing treatment strategies. This systematic review evaluates thecurrent advancements in AI-driven models for predicting radiotherapyoutcomes in GBM patients. A comprehensive search of PubMed,Scopus, and Web of Science identified 35 relevant studies employing various AI methodologies, including ML, DL, and hybrid approaches. Theresults indicate that convolutional neural networks (CNNs) and hybrid AImodels incorporating radiomics and genetic biomarkers achieved thehighest predictive performance, with accuracy rates ranging from 75%to 92% and area under the curve (AUC) values up to 0.91. Despite theseadvancements, challenges such as data heterogeneity, small samplesizes, and model interpretability remain significant barriers to clinicalimplementation. Future research should focus on large-scalemulticenter collaborations, the integration of multi-omics data, and thedevelopment of explainable AI (XAI) models to enhance transparencyand clinical applicability.
Authors: Shikhar Bindal, Shahil Hussain, Ahmed Belal, Parasa Leela Sai Srinivas, Christian Oko
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4411470716