Glioblastoma (GBM) prognosis has seen little improvement over the past two decades. While immunotherapy has revolutionized cancer treatment, its impact on GBM remains limited. To characterize the evolving research landscape and identify future directions in GBM immunotherapy, we conducted a comprehensive bibliometric review.

All literature related to immunotherapy in GBM from 1999 to 2024 was collected from the Web of Science Core Collection. CtieSpace and VOSviewer were used to conduct bibliometric analysis and visualize the data.

Bibliometric analysis identified 5038 publications authored by 23,335 researchers from 4699 institutions across 96 countries/regions, published in 945 journals. The United States produced the highest number of publications, while Switzerland achieved the highest average citation rate. Duke University led in institutional output and citations. John H Sampson was the most productive author, and Roger Stupp was the most cited. Frontiers in Immunology published the most papers, while Clinical Cancer Research was the most cited journal. Research focus centered on adoptive T cell therapy, particularly chimeric antigen receptor (CAR)-T cells with 572 dedicated publications. Within CAR-T research for GBM, the University of Pennsylvania was the leading institution, Frontiers in Immunology the predominant journal, and Christine E Brown (City of Hope National Medical Center) was the most prolific and cited author.

There has been a growing interest in GBM immunotherapy over past decades. The United States is the dominant contributor. CAR-T therapy represents the primary research focus. Emerging strategies like chimeric antigen receptor-modified natural killer (CAR-NK) cells, chimeric antigen receptor-engineered macrophages (CAR-M), and cytomegalovirus-specific T cell receptor (CMV-TCR) T cells are gaining prominence, aiming to address limitations in antigen recognition inherent to CAR-T therapy for GBM.

Gliomas are the most common primary tumors of the central nervous system. Multiparametric magnetic resonance imaging (mpMRI) is widely used for preliminary screening and plays a crucial role in auxiliary diagnosis, therapeutic efficacy, and prognostic evaluation. We aim to develop a fully automated system based on mpMRI for accurate glioma diagnosis and reliable prognostic assessment.

In this study, we collected a total of 1962 mpMRI samples and used them to develop a Glioma Multiparametric MRI Analysis System (GMMAS). This system leverages an uncertainty‐based semi‐supervised multitask learning architecture and simultaneously outputs a segmentation of the tumor region, the histological subtype of the glioma, the isocitrate dehydrogenase mutation genotype, and the status of 1p/19q chromosome disorder. Moreover, by utilizing a contrastive learning‐based adaptation module for cross‐modal feature extraction, GMMAS exhibits robustness when certain magnetic resonance imaging modalities are absent. Finally, based on the GMMAS analysis outputs, we created a user‐friendly platform for both doctors and patients. By integrating medical knowledge through the retrieval‐augmented generation technique, we introduced GMMAS‐generative pre‐trained transformer to generate personalized prognostic evaluations and offer treatment suggestions for glioma patients.

In the tumor segmentation task, the Dice values for the whole tumor, tumor core, and edema region reached 0.940 ± 0.037, 0.919 ± 0.092, and 0.870 ± 0.101, respectively. For glioma subtyping, the internal validation accuracies for differentiating glioblastoma from low grade glioma, predicting IDH mutation, and predicting 1p/19q co‐deletion were 0.941, 0.950, and 0.896, respectively. In the external validation cohorts, the average area under the curve values for these three prediction tasks were 0.905, 0.924, and 0.896, respectively.

GMMAS is a fully automated platform that delivers accurate and comprehensive diagnostic predictions and prognostic reports for glioma patients via non‐invasive approaches.