Scalability of Scalp EEG as a Tool for Epilepsy Surgery Outcomes: Lara Jehi, MD, MHCDS

WATCH TIME: 4 minutes

"The reason we focused on scalp EEG is because it’s universally available, even in underprivileged and low-resource settings. Intracranial EEG, functional MRI, and advanced imaging are cost-prohibitive in many places, but scalp EEG is routinely done everywhere."

As epilepsy surgery becomes safer and more widely used, the need for accurate prediction tools to identify patients likely to have recurrent postoperative seizures becomes even more critical. A recently published study patients who underwent temporal lobe resection for seizures revealed that machine learning classifiers can make accurate predictions of postoperative seizure outcome using 5 minutes of peri-ictal scalp EEG data that is part of universal presurgical evaluation (area under the operating curve, 0.98; out-of-group testing accuracy >90%).

The study included 294 surgical patients who underwent a preoperative scalp EEG evaluation during an inpatient stay in the Cleveland Clinic Epilepsy Monitoring Unit with a recorded seizure during that time. Across the relevant range of probability thresholds, the EEG-augmented approach would decrease the number of unnecessary surgeries by approximately 40% compared to a “treat all” strategy and approximately 20% compared with an approach based on the clinical variables nomogram. Led by Lara Jehi, MD, MHCDS, this was the first published research on seizure outcome prediction that employed a routine non-invasive preoperative study (scalp EEG) with accuracy range likely to translate into a clinical tool.

Following the publication, Jehi, an epilepsy specialist and Cleveland Clinic’s Chief Research and Information Officer, sat down with NeurologyLive® to discuss the scalability of scalp EEG as a diagnostic tool. In the discussion, she highlighted its accessibility in low-resource settings compared with resource-intensive techniques like intracranial EEG or functional MRI. Furthermore, she touched on the potential for global implementation of the algorithm, technical hurdles for integration into software or portable devices, and the goal of creating universally accessible tools for surgical prediction.

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