Year, Volume, Issue, Page(s):16, , ,
Study developed and internally validated preliminary prognostic regression models to predict Posttraumatic seizures (PTS) during acute care hospitalization, and at 1 year and 2 years after traumatic brain injury (TBI). Prognostic models predicting PTS during acute care hospitalization and year 1 and year 2 post-injury were developed using a recent cohort from the TBI Model Systems National Database. Potential PTS predictors were selected based on previous literature and biologic plausibility. Bivariable logistic regression identified variables with a p-value less than 0.20 that were used to fit initial prognostic models. Multivariable logistic regression modeling with backward-stepwise elimination was used to determine reduced prognostic models and to internally validate using 1,000 bootstrap samples. Fit statistics were calculated, correcting for overfitting (optimism). The prognostic models identified sex, craniotomy, contusion load, and preinjury limitation in learning/remembering/concentrating as significant PTS predictors during acute hospitalization. Significant predictors of PTS at year 1 were subdural hematoma (SDH), contusion load, craniotomy, craniectomy, seizure during acute hospitalization, duration of posttraumatic amnesia, preinjury mental health treatment or psychiatric hospitalization, and preinjury incarceration. Year 2 significant predictors were similar to those of year 1: SDH, intraparenchymal fragment, craniotomy, craniectomy, seizure during acute hospitalization, and preinjury incarceration. Corrected concordance statistics were 0.599, 0.747, and 0.716 for acute hospitalization, year 1, and year 2 models, respectively. The prognostic model for PTS during acute hospitalization did not discriminate well. Year 1 and year 2 models showed fair to good predictive validity for PTS. Future studies should externally validate the models and determine clinical utility.