Research Reports - Prognostic models for predicting posttraumatic seizures during acute hospitalization, and at 1 and 2 years following traumatic brain injury
Epilepsia. 2016 Jul 19. doi: 10.1111/epi.13470. [Epub ahead of print]
Ritter AC(1,)(2), Wagner AK(2,)(3,)(4,)(5), Szaflarski JP(6), Brooks MM(1),
Zafonte RD(7), Pugh MJ(8,)(9), Fabio A(1), Hammond FM(10,)(11), Dreer LE(12),
Bushnik T(13), Walker WC(14), Brown AW(15), Johnson-Greene D(16), Shea T(17),
Krellman JW(18), Rosenthal JA(17).
OBJECTIVE: Posttraumatic seizures (PTS) are well-recognized acute and chronic
complications of traumatic brain injury (TBI). Risk factors have been identified,
but considerable variability in who develops PTS remains. Existing PTS prognostic
models are not widely adopted for clinical use and do not reflect current trends
in injury, diagnosis, or care. We aimed to develop and internally validate
preliminary prognostic regression models to predict PTS during acute care
hospitalization, and at year 1 and year 2 postinjury.
METHODS: Prognostic models predicting PTS during acute care hospitalization and
year 1 and year 2 post-injury were developed using a recent (2011-2014) 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 < 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).
RESULTS: The prognostic models identified sex, craniotomy, contusion load, and
pre-injury 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/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 (C) statistics were 0.599, 0.747,
and 0.716 for acute hospitalization, year 1, and year 2 models, respectively.
SIGNIFICANCE: 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. Cranial surgery, although medically necessary, requires ongoing
research regarding potential benefits of increased monitoring for signs of
epileptogenesis, PTS prophylaxis, and/or rehabilitation/social support. Future
studies should externally validate models and determine clinical utility.