AUTHOR=Lamichhane Bidhan , Daniel Andy G. S. , Lee John J. , Marcus Daniel S. , Shimony Joshua S. , Leuthardt Eric C. 

TITLE=Machine Learning Analytics of Resting-State Functional Connectivity Predicts Survival Outcomes of Glioblastoma Multiforme Patients

JOURNAL=Frontiers in Neurology

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2021.642241

DOI=10.3389/fneur.2021.642241

ISSN=1664-2295

ABSTRACT=Glioblastoma multiforme (GBM) is the most frequently occurring brain malignancy. Due to its poor prognosis with currently available treatments, there is a pressing need for easily accessible, noninvasive techniques to help inform pre-treatment planning, patient counselling, and improve outcomes. In this study: (i) we tested the correlation between resting state functional connectivity (rsFC) between pre-defined regions of interest and overall survival (OS), and (ii) we determined the feasibility of rsFC to classify GBM patients into short-term and long-term survival groups with respect to reported median survival (14.6 months). We used a support vector machine with rsFC between regions of interest as predictive features. We employed a novel hybrid feature method whereby filtering selected correlations between rsFC and OS with p<0.05, and then the established method of recursive feature elimination (RFE) selected optimal features. Leave-one subject-out cross-validation evaluated the performance of models. Classification between short and long term survival accuracy was 71.9%. Sensitivity and specificity were 77.1% and 65.5%, respectively. The area under the receiver operating characteristic curve was 0.752 (95% CI, 0.62–0.88). These findings suggest that highly specific features of rsFC are correlated with OS and may predict GBM survival. Taken together, the findings of this study support that resting state fMRI and machine learning analytics could enable a radiomic biomarker for GBM, augmenting care and planning for individual patients.