0
0
By uncovering hidden epilepsy patterns in routine tests, Johns Hopkins researchers revolutionize diagnosis.
Epilepsy misdiagnoses could drop by up to 70% with the help of a groundbreaking tool that extracts hidden markers from routine electroencephalogram (EEG) tests, a new Johns Hopkins University study reveals. By leveraging innovative algorithms, the tool—named EpiScalp—can turn seemingly normal EEGs into precise predictors of epilepsy, potentially sparing countless patients from unnecessary treatments and life-altering restrictions.
“Even when EEGs appear completely normal, our tool provides insights that make them actionable,” said Dr. Sridevi V. Sarma, the study’s lead author and professor of biomedical engineering. “We can get to the right diagnosis three times faster because patients often need multiple EEGs before abnormalities are detected. Accurate early diagnosis means a quicker path to effective treatment.”
The study, recently published in the Annals of Neurology, underscores the potential of EpiScalp to address the global challenge of false-positive epilepsy diagnoses, which affect approximately 30% of cases. Misdiagnosed patients often endure side effects from anti-seizure medications, driving restrictions, and other quality-of-life disruptions.
A Revolutionary Approach to EEG Analysis
Epilepsy, characterized by recurrent, unprovoked seizures, is typically diagnosed using scalp EEG recordings. However, standard EEG tests often capture “noisy” brain signals, and seizures rarely occur during the brief recording period, making interpretation difficult and prone to error.
Sarma’s team hypothesized that even when seizures are absent, certain brain regions act as natural inhibitors, suppressing seizure activity. By analyzing the interaction between different brain regions, EpiScalp identifies hidden patterns in routine EEGs, revealing these inhibitory signals.
“When we looked at how nodes in the brain interact, we found a distinct pattern of activity suppression in epilepsy patients that doesn’t appear in healthy individuals,” explained Patrick Myers, first author and Johns Hopkins doctoral student.
In a study of 198 patients from five medical centers, EpiScalp reduced misdiagnoses from 54% to 17% by accurately distinguishing epilepsy cases from conditions that mimic it.
Implications for Patients and Clinicians
Misinterpretation of EEGs often leads to overdiagnosis, with clinicians opting to prescribe anti-seizure medication to avoid the dangers of a second seizure. However, in many cases, patients experience nonepileptic seizures that require non-epilepsy treatments, explained co-author Dr. Khalil Husari, assistant professor of neurology at Johns Hopkins.
“These patients suffered side effects of anti-seizure medication without any benefit,” said Dr. Husari. “With the correct diagnosis, we can address the root cause of their symptoms more effectively.”
EpiScalp builds on earlier research involving intracranial EEGs, adapting its methods to routine scalp EEGs. The tool’s innovative focus on brain network interactions marks a departure from traditional approaches that analyze individual brainwave signals.
The Road Ahead
The team is now conducting a larger study to validate EpiScalp across three epilepsy centers. A patent for the technology was filed in 2023, and researchers are optimistic about its potential to transform epilepsy diagnosis worldwide.
“EpiScalp represents a significant step forward in how we diagnose and treat epilepsy,” Sarma said. “It’s not just about reducing errors—it’s about improving patient care and quality of life.”
Disclaimer
The EpiScalp tool is currently undergoing further validation and is not yet available for widespread clinical use. Patients should consult their healthcare providers for personalized medical advice and diagnosis.
For more details, refer to the study: Patrick Myers et al., Diagnosing Epilepsy with Normal Interictal EEG Using Dynamic Network Models, Annals of Neurology (2025). DOI: 10.1002/ana.27168
