Clinical Report: Mapping Seizure Propagation Patterns Using Artificial Intelligence
Overview
This study investigates the use of artificial intelligence to quantify seizure spread patterns in patients with refractory epilepsy. By analyzing intracranial EEG data, the research aims to correlate seizure spread characteristics with patient outcomes and brain connectivity.
Background
Epilepsy affects millions globally, and accurate localization of seizure onset zones is crucial for effective treatment planning. Despite advances in surgical techniques, seizure freedom rates have not significantly improved over the past few decades. Understanding seizure propagation patterns may enhance treatment strategies.
Data Highlights
Parameter
Value
Number of patients
71
Mean age
33 ± 12 years
Number of seizures captured
275
Mean seizure length
85 ± 94 seconds
Mean number of seizures per patient
3.9 ± 3.8
Patients with Engel outcome scores
58
Key Findings
Seizure spread patterns may correlate with patient outcomes.
The timing of seizure spread is related to the structural connectivity of the brain.
Low-dimensional embeddings of seizure spread patterns can reveal clusters of patients and seizure attributes.
Seventy-one patients with treatment-resistant epilepsy were included in the study.
Inter-rater and intra-rater reliability of human evaluations of intracranial EEG is poor.
Clinical Implications
The findings indicate that incorporating AI to analyze seizure propagation may improve the identification of epileptogenic circuits.
Conclusion
Utilizing AI to map seizure propagation patterns offers a new approach for understanding refractory epilepsy.
by Andrew Y. Revell, Marc Jaskir, Akash R. Pattnaik, William K. S. Ojemann, Erin Conrad, Nishant Sinha, Brittany H. Scheid, Alfredo Lucas, John M. Bernabei, John Beckerle, Joel M. Stein, Sandhitsu R. Das, Brian Litt, Kathryn A. Davis
