Log In

Forgot Password?
Create New Account

Loading... please wait

Abstract Details

Combining Machine-detected EEG Epileptiform Abnormalities and Quantitative EEG Spectral Features Predicts Post Traumatic Epilepsy
Epilepsy/Clinical Neurophysiology (EEG)
S7 - Epilepsy and Clinical Neurophysiology (EEG) 1 (3:42 PM-3:54 PM)
002

EAs, including early seizures, sporadic epileptiform discharges (ED), lateralized or generalized periodic discharges (LPD, GPD), and lateralized rhythmic delta activity (LRDA), are more frequently present in PTE than non-PTE patients. In contrast, qEEG spectral analyses (rhythmicity, FFT Power, suppression) provide a comprehensive evaluation of electrophysiological brain signatures after traumatic brain injury (TBI). We hypothesize that combining early post-TBI EAs and spectral features predicts first-year PTE.

To determine whether combining epileptiform abnormality (EA) identification and quantitative electroencephalography (qEEG) spectral analyses predicts post-traumatic epilepsy (PTE).

We conducted a multi-site, retrospective, case-control study of 56 PTE and 56 non-PTE patients matched by admission TBI severity, age and gender. We analyzed EEGs within 14 days post-TBI. EAs and qEEG features were computed using two independent algorithms – Persyst 14 and a novel EA detector (Westover lab, unpublished). We performed bivariate analyses to identify EEG risk factors for PTE, controlling for recording duration. We also performed multivariate analyses leveraging forward model selection techniques and LASSO-regularization (8-fold cross-validated) for feature selection.

In bivariate analyses, FFT sub-band (delta, theta, beta) power variability (PDV, PTV, PBV), LRDA-GRDA ratio, and LPD significantly increase PTE risk (p<0.05). Rhythmicity delta asymmetry, suppression asymmetry, and GPD trend toward significant (p<0.1). Multivariate logistic regression including LRDA-GRDA ratio (p<0.01), GPD (p<0.05), and PBV (p<0.05) yields an AUC of 0.733 (95%CI 0.640-0.826). The resulting accuracy is 68% (sensitivity-70%, specificity-64%). LASSO-regularized logistic regression identifies a broader range of features (LRDA-GRDA ratio, GPD, PBV, suppression asymmetry, seizures). Adding PTE mechanism (penetrating) improves performance (Delong p=0.0575) with an AUC of 0.775 (95%CI 0.687-0.863), and an accuracy (also sensitivity, specificity) of 75%.

Our data suggest that combining machine-detected EAs and qEEG spectral features identifies patients at risk for PTE. Our results highlight the potential benefit of early EEG assessments in TBI patients.

Authors/Disclosures
Yilun Chen (Yale University)
PRESENTER
Ms. Chen has nothing to disclose.
No disclosure on file
Hsin Yi Chen Miss Chen has nothing to disclose.
No disclosure on file
Alison Herman Ms. Herman has nothing to disclose.
Safa Kaleem (NewYork-Presbyterian Weill Cornell Medical Center) Dr. Kaleem has nothing to disclose.
Kan Ding (UT Southwestern Medical Center) The institution of Dr. Ding has received research support from National Institute of Aging. The institution of Dr. Ding has received research support from NINDS.
Gamaleldin Osman (Mayo Clinic) Dr. Osman has nothing to disclose.
Christa Swisher (Duke University Medical Center) Dr. Swisher has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for UCB.
Christine Smith (UFHealth) Dr. Smith has nothing to disclose.
Carolina Maciel Dr. Maciel has received research support from American Heart Association. Dr. Maciel has received research support from National Institute of Health.
Ayham Alkhachroum (Columbia University Medical Center) The institution of Dr. Alkhachroum has received research support from Miami CTSI.
Jong Lee (Brigham and Women's Hospital) Dr. Lee has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Bigoen. Dr. Lee has received stock or an ownership interest from Soterya. The institution of Dr. Lee has received research support from NIH. The institution of Dr. Lee has received research support from Epilepsy Foundation. The institution of Dr. Lee has received research support from Engage Therapeutics. Dr. Lee has received personal compensation in the range of $5,000-$9,999 for serving as a Contract work with Bioserenity. Dr. Lee has received personal compensation in the range of $10,000-$49,999 for serving as a Contract work with Teladoc.
Monica Dhakar (Xenon Pharmaceuticals) The institution of Dr. Dhakar has received research support from NIH. The institution of Dr. Dhakar has received research support from UCB Biopharma. The institution of Dr. Dhakar has received research support from Marinus Pharmaceuticals.
Emily Gilmore (Yale University School of Medicine) Dr. Gilmore has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for carpl.ai. Dr. Gilmore has received personal compensation in the range of $0-$499 for serving as a Consultant for AAN. Dr. Gilmore has received research support from NIH.
No disclosure on file
Brian Edlow Dr. Edlow has received research support from NIH.
M. Westover (MGH) Dr. Westover has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Beacon Biosignals. Dr. Westover has stock in Beacon Biosignals. The institution of Dr. Westover has received research support from NIH. Dr. Westover has received publishing royalties from a publication relating to health care. Dr. Westover has a non-compensated relationship as a cofounder with Beacon Biosignals that is relevant to AAN interests or activities.
Jennifer Kim (Yale University School of Medicine) Dr. Kim has nothing to disclose.