New Epilepsy Tool Cuts Misdiagnoses by 70% Using Routine EEGs

Standard diagnostic practice includes scalp electroencephalogram (EEG) recordings, which monitor brainwave patterns through electrodes placed on the scalp. These recordings help diagnose epilepsy and guide decisions about anti-seizure treatments. However, EEGs can be difficult to interpret due to noisy signals and the rare occurrence of seizures during the typical 20 to 40 minutes of recording. This makes diagnosing epilepsy subjective and prone to error, even for experts. Now, a new tool is set to reduce epilepsy misdiagnoses by up to 70% by transforming routine EEG tests that appear normal into highly accurate predictors of epilepsy.

Developed by researchers at Johns Hopkins Medicine (Baltimore, MD, USA), the tool, called EpiScalp, detects hidden epilepsy signatures in seemingly normal EEGs, significantly reducing false positives, which affect around 30% of global cases. This can spare patients from unnecessary medications, driving restrictions, and other challenges related to misdiagnosis. EpiScalp uses algorithms based on dynamic network models to map brainwave patterns and identify epilepsy signs from a single routine EEG. The research team previously studied epileptic brain networks using intracranial EEGs and found that during non-seizure periods, the seizure onset zone is inhibited by neighboring brain regions. EpiScalp builds on this research, identifying these patterns in routine scalp EEGs.

While traditional methods of improving EEG interpretation often focus on individual signals or electrodes, EpiScalp analyzes interactions between different brain regions through complex neural pathways. In their new study, published in Annals of Neurology, the researchers analyzed 198 patients from five major medical centers, including 91 with epilepsy and the rest with non-epileptic conditions. When the team reanalyzed the initial EEGs using EpiScalp, the tool correctly identified 96% of false positives, reducing misdiagnoses from 54% to just 17%. A larger prospective study is underway to further validate these findings, and the research team has filed a patent for the EpiScalp technology.

"Even when EEGs appear completely normal, our tool provides insights that make them actionable," said Sridevi V. Sarma, a Johns Hopkins biomedical engineering professor who led the work. "We can get to the right diagnosis three times faster because patients often need multiple EEGs before abnormalities are detected, even if they have epilepsy. Accurate early diagnosis means a quicker path to effective treatment."