Predicting Post-Traumatic Epilepsy with Automated Contusion Measurements using Acute CT Images: A Competing Risk...

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.

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.

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.

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.