Tool Gauges a Patient’s Epilepsy Status From a Single Normal EEG
A newly developed tool uses algorithms trained on dynamic network models to identify hidden markers of epilepsy from a single routine scalp electroencephalogram (EEG), according to a study published in the Annals of Neurology.
"Even when EEGs appear completely normal, our tool provides insights that make them actionable," said researcher Sridevi V. Sarma, PhD, a biomedical engineering professor at Johns Hopkins University, Baltimore, Maryland. "We can get to the right diagnosis 3 times faster because patients often need multiple EEGs before abnormalities are detected, even if they have epilepsy.”
The EpiScalp model was trained on normal initial EEGs from 198 patients with suspected epilepsy from Johns Hopkins Hospital, Johns Hopkins Bayview Medical Center, and the University of Maryland Medical Center, Baltimore, Maryland; the University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania; and Thomas Jefferson University Hospital, Philadelphia, Pennsylvania. Among the patients, subsequent admissions to epilepsy monitoring units revealed 91 had epilepsy and the rest had conditions that mimicked epilepsy.
>>RELATED: Systematic Review Finds Problems With Epilepsy Outcome Prediction Models
The study also included a validation set of 20 patients: 8 with epilepsy and 12 with conditions mimicking epilepsy.
According to the study, EpiScalp demonstrated an area under the curve of 0.940, an accuracy of 0.904, a sensitivity of 0.835, and a specificity of 0.963 in classifying patients with and without epilepsy.
“This is where our tool makes a difference because it can help us uncover markers of epilepsy in EEGs that appear uninformative, reducing the risk of patients being misdiagnosed and treated for a condition they don't have," said researcher Khalil Husari, MD, an assistant professor of neurology at Johns Hopkins University.
The team has filed a patent for the EpiScalp technology and is currently conducting a larger prospective study to validate findings from the study.
“This may represent a paradigm shift in epilepsy diagnosis,” researchers wrote, “by deriving an objective measure of epilepsy likelihood from previously uninformative EEGs.”
References
