Skip to main content
News

Algorithm Predicts Seizure Control Outcomes After Brain Resection Surgery

A machine learning algorithm predicted seizure control after temporal lobe resection using just 5 minutes of peri-ictal data from a scalp electroencephalogram (EEG) that is already part of the standard universal presurgical evaluation, according to a study published online in Scientific Reports.

“Decision curve analysis (DCA) shows that compared to the prevalent clinical-variable based nomogram, use of the EEG-augmented approach could decrease the rate of unsuccessful brain resections by 20%,” wrote first author Shehryar R. Sheikh, MD, of the Departments of Neurosurgery and Molecular Medicine at the Cleveland Clinic, Cleveland, Ohio, and study coauthors.

Researchers hypothesized that the time immediately before and after a seizure—the peri-ictal window—would be uniquely informative for predicting clinical outcomes based on results from preclinical models and observations from intracranial EEG in humans. They conducted machine learning model-building experiments using a dataset of 294 patients who underwent temporal lobe resection for seizures.

With 5 minutes of peri-ictal scalp EEG data, machine learning classifiers accurately predicted postoperative seizure outcomes in patients, reporting an area under the curve of 0.98 and an out-of-group testing accuracy above 90%.

The EEG-augmented approach would reduce the number of unnecessary surgeries by approximately 40% compared with a treat-all strategy and 20% compared with a clinical-variable based nomogram, the study found.

“The approach that we document in this report (ie, the use of peri-ictal scalp EEGderived features in a machine learning-enabled predictive framework) overcomes [previous] limitations and thus has the potential to achieve clinical translation into a useful presurgical tool,” researchers concluded.

Reference

Sheikh SR, McKee ZA, Ghosn S, et al. Machine learning algorithm for predicting seizure control after temporal lobe resection using peri-ictal electroencephalography. Sci Rep. 2024;14(1):21771. doi:10.1038/s41598-024-72249-7