AI for prognosis and treatment stratification in glioblastoma neurosurgery: a systematic review.

Clinical Snapshot

Key Findings

• P Value: Not reported at review level

• Effect Size: No pooled effect size calculable; narrative synthesis only. Survival-focused tasks predominated (20/30 studies, 66.7%). Radiomics plus conventional ML was the most common model family (13/30, 43.3%), followed by deep learning (8/30, 26.7%) and hybrid DL+radiomics (4/30, 13.3%)

• Primary Outcome: Descriptive synthesis of AI model performance across prognosis, risk stratification, treatment-response assessment, post-treatment classification, recurrence/progression prediction, and molecular prediction in GBM

• Nnt Or Sensitivity: Individual study performance metrics (AUC, C-index, accuracy) not synthesised at review level; external validation achieved in only 5/30 studies (16.7%), limiting any estimate of real-world model sensitivity or specificity

• Confidence Interval: Not applicable — no meta-analytic pooling performed

Clinical Application

Currently limited. AI tools for GBM prognosis and stratification are predominantly research-grade, lacking prospective validation, regulatory approval, and integration into clinical workflows. The 16.7% external validation rate indicates most models are not ready for clinical deployment. Implementation would require institutional MRI standardisation, prospective validation cohorts, and clinician training. In Australia, GBM management follows NHMRC-aligned and international guidelines, with standard-of-care comprising maximal safe surgical resection followed by Stupp protocol (temozolomide plus radiotherapy). No AI-based prognostic or stratification tools for GBM are currently TGA-approved or PBS-subsidised. The RACGP and relevant specialist colleges (RACS, RANZCR) have not yet issued guidance on AI integration in neuro-oncology. Australian neuro-oncology centres (e.g., Royal Melbourne Hospital, RBWH, RPAH) conducting GBM research may find this review useful for framing future prospective AI validation studies. The relatively small Australian GBM patient population (~1,500 new diagnoses annually) underscores the importance of multi-centre and international data sharing for adequate external validation. Adult patients with confirmed GBM (WHO Grade 4 IDH-wildtype glioma) being considered for or having undergone neurosurgical resection, where prognostic stratification, treatment planning, or post-treatment surveillance decisions are clinically relevant

Abstract

BACKGROUND: Glioblastoma (GBM) remains one of the most lethal adult primary brain tumors, and neurosurgical decision-making increasingly depends on integrating imaging, molecular, perioperative, and post-treatment data. Artificial intelligence (AI) methods have been proposed for several clinically relevant GBM tasks, but the literature remains heterogeneous and difficult to translate into practice. METHODS: We performed a PROSPERO-registered systematic review of AI, machine learning, and deep learning studies using MRI-derived and/or multimodal perioperative data in GBM for prognosis, risk stratification, treatment-response assessment, post-treatment classification, recurrence/progression prediction, and molecular prediction. Risk of bias was assessed using PROBAST-informed criteria. RESULTS: Thirty studies were included. Survival-focused tasks predominated (20/30, 66.7%), with radiomics plus conventional machine learning as the most common model family (13/30, 43.3%), followed by deep learning (8/30, 26.7%) and hybrid deep learning plus radiomics approaches (4/30, 13.3%). Validation was predominantly internal, and external validation was uncommon (5/30, 16.7%). CONCLUSIONS: AI shows promise for prognosis and treatment stratification in GBM neurosurgery, but current evidence is limited by heterogeneity, incomplete external validation, and inconsistent methodological reporting. CLINICAL TRIAL NUMBER: Not applicable.

References

1. 1.Reyes, J. S., Snyder, M. H., Roguski, M., & Hadjipanayis, C. G. (2026). AI for prognosis and treatment stratification in glioblastoma neurosurgery: a systematic review. Journal of Neuro-Oncology. https://doi.org/10.3389/fonc.2026.1837357