Glioblastoma multiforme (GBM) is a particularly aggressive and deadly brain tumor that presents major challenges for diagnosis, therapeutic intervention, and prediction of patient outcomes. The discovery of reliable biomarkers remains essential to improve therapeutic outcomes, as patients survive an average of 14–16 months despite intensive treatments. Although genomic and proteomic studies have led to important biomarker discoveries, these traditional approaches often lack sufficient predictive ability to support clinical treatment decisions.Deep learning represents a transformative approach that enables effective molecular profiling, radiomic assessment, and integration of multi-omics data to improve biomarker discovery. Computational methods facilitate the identification of novel biomarkers, improve patient stratification, and support better treatment decisions. The combination of convolutional neural networks (CNNs) and graph neural networks (GNNs) allows researchers to investigate complicated biological data for advanced subtype analyses and phenotype-genotype relationship understanding of GBM.The review evaluates modern deep learning techniques for GBM biomarker exploration through assessments of subtype detection and biomarker detection from imaging data and model assessments between drugs and biomarkers while providing explanations about AI systems. The promising nature of these techniques faces major obstacles which consist of GBM variability and the need for inter-dataset confirmation and the transfer of algorithm-generated findings to real-world medical practice The successful translation of deep learning discoveries into improved patient care and treatment strategies depends on addressing these current limitations.
Tetik et al. (Tue,) studied this question.