Glioblastoma multiforme (GBM), the most common form of glioma, is a malignant tumor with a high risk of mortality. By providing accurate survival estimates, prognostic models have been identified as promising tools in clinical decision support. In this study, we produced and validated two machine learning-based models to predict survival time for GBM patients. Publicly available clinical and genomic data from The Cancer Genome Atlas (TCGA) and Broad Institute GDAC Firehouse were obtained through cBioPortal. Random forest and multivariate regression models were created to predict survival. Predictive accuracy was assessed and compared through mean absolute error (MAE) and root mean square error (RMSE) calculations. 619 GBM patients were included in the dataset. There were 381 (62.9%) cases of recurrence/progression and 53 (8.7%) cases of disease-free survival. The MAE and RMSE values were 0.553 and 0.887 years respectively for the random forest regression model, and they were 1.756 and 2.451 years respectively for the multivariate regression model. Both models accurately predicted overall survival. Comparison of models through MAE, RMSE, and visual analysis produced higher accuracy values for random forest than multivariate linear regression. Further investigation on feature selection and model optimization may improve predictive power. These findings suggest that using machine learning in GBM prognostic modeling will improve clinical decision support. *Co-first authors.

No abstract

Background: Elevated systolic blood pressure (SBP) has been linked to pre-procedural rebleeding risk and poor outcome in patients with aneurysmal subarachnoid hemorrhage (aSAH). However, the relationship between blood pressure parameters including mean arterial pressure (MAP) with rebleeding both prior to and during aneurysm securement remains unclear. This study seeks to determine the association between BP parameters and rebleeding events and outcomes in patients with aSAH. Design/Methods: We performed a retrospective analysis of a prospectively collected cohort of consecutive patients with aSAH admitted to an academic center between July 2016 and March 2021. All BP parameters, which were recorded on an hourly basis from admission, were reviewed. Per our institutional protocol, the SBP target is <140 mmHg for all unsecured aSAH patients. Rebleeding was defined as radiographic worsening of hemorrhage prior to or immediately following aneurysm securement, as seen on imaging and determined by a radiologist. Binary regression analysis was used to determine association between maximum recorded BP parameters and outcomes including rebleeding and poor functional outcome defined as modified Rankin Scale 4-6 at 3 months post-discharge. Results: The cohort included 295 patients (mean age 57 years [SD 13.4], 61% female, 87% received endovascular treatments, 13% surgical clipping). Two or more consecutive SBP values >140 were seen in 41% and >160 in 15% of patients. Rebleeding prior or during securing aneurysms including intra-procedural bleeding occurred in 53 patients (18%). There was no association between either maximum recorded SBP (169.7 mmHg [36.2] vs. 166.9 [32.7], p=0.57) or MAP (121 mmHg [22.9] vs. 117.8 [22.9], p=0.42) and rebleeding. However, maximum recorded MAP was associated with poor outcome (OR 1.01 for 1 mmHg increase in MAP, 95% CI: 1.006-1.02, p=0.039). Conclusions: Elevated MAP peri-securement of a ruptured cerebral aneurysm can be associated with poor outcome. Multicenter prospective studies should further examine the association between MAP cut offs and outcomes to be considered in guidelines.