Feasibility and efficacy of ai-guided personalized precision radiation therapy in newly diagnosed glioblastoma: a matched-control study

Abstract PURPOSE The aim of this study was to evaluate the feasibility and efficacy of AI-guided personalized precision radiation therapy (PPRT) in improving outcomes for patients with newly diagnosed glioblastoma. METHODS In an open-label trial conducted at the University of Pennsylvania (NCT03477513), between August 2018 and April 2021, 17 patients with IDH-wildtype glioblastoma who underwent maximal safe resection were enrolled. They were matched with a cohort of glioblastoma patients based on age, sex, extent of resection (EOR), O6-methylguanine-DNA methyltransferase promoter (MGMTp) methylation status, and IDH status. Propensity Score Matching (PSM) was employed to assess the impact of the intervention on the likelihood of survival, using logistic regression to estimate the propensity score. Four patients were disqualified based on exclusion criteria. The PPRT group received personalized radiation dose escalation guided by AI-based predictive modeling of recurrence, along with concomitant and maintenance temozolomide chemotherapy. The control group received standard-of-care chemoradiotherapy between 2012 and 2020. In this study, we utilized a previously published and evaluated (retrospectively and prospectively) predictive AI model, which accurately estimated neoplastic cell infiltration and predicted future tumor recurrence using preoperative, multi-parametric MRIs. RESULTS Median overall survival was 24.4 months in the PPRT-temozolomide group and 17.9 months in the standard-of-care treatment group (hazard ratio, 0.34; 95% CI: 0.15-0.77; p = 0.009). PPRT was well-tolerated, with low-grade adverse events during radiation. Radiation necrosis occurred in 54% of the PPRT-temozolomide group and 36% of the standard-of-care group. CONCLUSION AI-guided PPRT in newly diagnosed glioblastoma patients demonstrated feasibility in routine clinical practice and led to a statistically significant improvement in overall survival compared to matched controls receiving standard-of-care treatment. These findings highlight the potential of personalized precision radiation therapy, with focused dose escalation, in enhancing outcomes for glioblastoma patients and emphasize the need for prospective validation in a randomized controlled clinical trial.