Deep Learning for Survival Prediction in Glioblastoma: Time-dependent Model Interpretability Using MRI, Clinical, and Molecular Data.

Purpose To develop a multimodal model for survival prediction and time-dependent model interpretability in glioblastoma by integrating preoperative MRI with clinical and molecular variables. Materials and Methods This retrospective multicenter study included two institutional cohorts (February 2007-December 2024) and two public external test sets. A deep learning-based prognostic index (DPI) was generated from preoperative multiparametric MRI using a vision transformer. The DPI was integrated with clinical variables (age, sex, Karnofsky performance status, extent of resection), molecular markers (isocitrate dehydrogenase [IDH] mutation, O6-methylguanine-DNA methyltransferase [MGMT] promoter methylation), histopathology, and World Health Organization (WHO) grade using a random survival forest model. Model performance was evaluated using the C index, and time-dependent model interpretability was assessed using survival Shapley Additive Explanations (SurvSHAP[t]). Associations between DPI and clinical and molecular variables were evaluated using correlation and group-wise statistical tests. Results A total of 1883 patients (mean age, 57.7 years ± 14.8 [SD]; 983 female) were included. The multimodal model integrating MRI and clinical and molecular variables achieved C indexes of 0.77, 0.73, and 0.63 for the internal test set and two external test sets, respectively. In comparison, the image-only model achieved C indexes of 0.73, 0.65, and 0.60 across the same cohorts. SurvSHAP(t) analysis showed that prognostic influence peaked at approximately 12 months for extent of resection and 24 months for MGMT promoter methylation, whereas IDH mutation and WHO grade increased in importance over time. The imaging-derived DPI consistently ranked among the strongest predictors of survival and showed moderate correlations with age, Karnofsky performance status, IDH mutation status, and WHO grade. Conclusion The multimodal model showed good performance for glioblastoma survival prediction and enabled time-dependent model interpretability, identifying the imaging-derived prognostic index as a complementary biomarker with sustained prognostic importance over time. Keywords: MRI, Neuro-Oncology, Central Nervous System, Brain, Brain Stem, Primary Neoplasms, Comparative Studies, Prognosis, Random Survival Forest, Feature Detection, Radiology-Pathology Integration Supplemental material is available for this article. © RSNA, 2026.