Predicting Post-Traumatic Epilepsy with Automated Contusion Measurements using Acute CT Images: A Competing Risk Approach
Year: 2025
Type: preprint
Study design: Observational Study
Abstract: Objective: This study evaluates contusion volume and location as predictors of PTE while considering mortality as a competing risk using automated segmentation of acute CT images. Methods: Adult TBI patients who visited our center (2014-2025) were identified and categorized into three outcome groups: PTE, post-TBI mortality, and event-free. Clinical covariates were extracted from health records, and CT scans were processed using the BLAST-CT algorithm to segment intraparenchymal hemorrhage (IPH), edema, intraventricular (IVH), and extra-axial hemorrhage (EAH). Five-fold nested cross-validation was performed, with L1-regularized regression used for feature selection within each training fold and model performance evaluated in the corresponding test fold. Within each fold, the selected features were then used to fit separate cause-specific multivariable Cox models for PTE and mortality. Contusion location associations were assessed using both multivariable Cox and sparse canonical correlation analysis. Results: Of 1017 identified patients, 6.1% developed PTE, 10.5% died, and 83.4% had no event. In multivariable analysis, total contusion volumes (p<0.001) were independently predicted both PTE and mortality, meanwhile and EAH volume (p<0.01) predicted mortality only. When regionalized, frontal (p<0.01) and temporal (p<0.01) contusions independently predicted PTE, whereas frontal (p=0.04) contusions also independently predicted mortality. Sparse canonical correlation analysis identified an association of frontotemporal and insular contusions with PTE but not mortality. Interpretation: Automatically measured contusion segmentation from acute CT imaging could help predict post-traumatic epilepsy. A competing risk framework highlighted that contusion volume is associated with both PTE and mortality risk, whereas unique contusion location patterns may aid in post-traumatic epilepsy assessment in a broad TBI population.
Source: medRxiv
Authors: B. Berke Ayvaz, Justin R. Wheelock, Daniel S. Jin, Jenna Appleton, Samuel B. Snider, Victor Torres-Lopez, Neha Shrishail, William Sanders, Daniel Doherty, Khai Theeng Chow, Jisoo Kim, Jisoo Kim, Maia Schlecter, Lawrence J. Hirsch, Adithya Sivaraju, M. Brandon Westover, Sahar F. Zafar, Aaron F. Struck, Kevin N. Sheth, Sacit Bulent Omay, Brian L. Edlow, Emily J. Gilmore, Jennifer A. Kim, Jennifer A. Kim
Language: English
Subfield: Neurology
Field: Medicine
Domain: Health Sciences
Open Access status: green
Funders: National Science Foundation, Yale University, National Institutes of Health, National Institute on Aging, National Heart, Lung, and Blood Institute, National Institute of Neurological Disorders and Stroke, National Institute of Biomedical Imaging and Bioengineering, National Institute on Minority Health and Health Disparities
Awards: G1737395127, EEG and MRI Biomarkers to Predict Post-traumatic Epilepsy, G2145263961, SCH: INT: Collaborative Research: DeepSense: Interpretable Deep Learning for Zero-effort Phenotype Sensing and Its Application to Sleep Medicine, Comparative effectiveness of EEG-guided anti-seizure treatment in acute brain injury, G3473390913, G4190739716, Establishing a Brain Health Index, G580858672, G6230834768, G6315715174, Late-onset Unexplained Epilepsy as a Risk Factor for Dementia, G751880428, Integrative Motor Activity Biomarker for the Risk of Alzheimer's Risk, G9000038524, G9000042137, G9000066320, G9000081834, G9000228600, G9000281784, ELECTRO-BOOST: Electroencephalography for cerebral trauma recovery and oxygenation, Portable, Low Field Brain Magnetic Resonance Imaging (MRI) for Acute Stroke, Yale-METRO Metropolitan Emergency Trial netwoRK to advance patient Outcomes, Data-Driven Sleep Biomarkers of Brain Health, Heart Health, and Mortality, Prospective Validation of Neurophysiologic Outcome Prediction in Acute Brain Injury
OpenAlex ID: W4416801297