TY - JOUR
T1 - Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy
AU - Varatharajah, Yogatheesan
AU - Berry, Brent
AU - Cimbalnik, Jan
AU - Kremen, Vaclav
AU - Van Gompel, Jamie
AU - Stead, Matt
AU - Brinkmann, Benjamin
AU - Iyer, Ravishankar
AU - Worrell, Gregory
N1 - Funding Information:
The authors would like to acknowledge Cindy Nelson and Karla Crockett for their technical support, Jenny Applequist, Frances Baker, and Steve Nelson for editing the manuscript, and Michal Kucewicz and Hari Guragain for their useful feedback. This research was partly supported by Mayo Clinic and Illinois Alliance Fellowship for Technology-based Healthcare Research; National Institutes of Health grants, NINDS-R01-NS92882, NINDS-UH2-NS095495-01, R01-NS063039, and R01-NS078136; National Science Foundation grants CNS-1337732 and CNS-1624790; an IBM faculty award to Ravishankar K. Iyer; a Mayo Clinic Discovery Translation Grant; institutional resources for research of the Czech Technical University in Prague, Czech Republic, ALISI–NPU (LO1212) and VES15 II–LH15047; Project no. LQ1605 from the National Program of Sustainability II (MEYS CR); Ministry of Youth and Sports of the Czech Republic project no. LH15047 (KONTAKT II); and The European Regional Development Fund: FNUSA-ICRC (No. CZ.1.05/1.1.00/02.0123).
Funding Information:
This research was partly supported by Mayo Clinic and Illinois Alliance Fellowship for Technology-based Healthcare Research; National Institutes of Health grants, NINDSR01-NS92882, NINDS-UH2-NS095495-01, R01-NS063039, and R01-NS078136; National Science Foundation grants CNS-1337732 and CNS-1624790.
PY - 2018/6/27
Y1 - 2018/6/27
N2 - Objective. An ability to map seizure-generating brain tissue, i.e. the seizure onset zone (SOZ), without recording actual seizures could reduce the duration of invasive EEG monitoring for patients with drug-resistant epilepsy. A widely-adopted practice in the literature is to compare the incidence (events/time) of putative pathological electrophysiological biomarkers associated with epileptic brain tissue with the SOZ determined from spontaneous seizures recorded with intracranial EEG, primarily using a single biomarker. Clinical translation of the previous efforts suffers from their inability to generalize across multiple patients because of (a) the inter-patient variability and (b) the temporal variability in the epileptogenic activity. Approach. Here, we report an artificial intelligence-based approach for combining multiple interictal electrophysiological biomarkers and their temporal characteristics as a way of accounting for the above barriers and show that it can reliably identify seizure onset zones in a study cohort of 82 patients who underwent evaluation for drug-resistant epilepsy. Main results. Our investigation provides evidence that utilizing the complementary information provided by multiple electrophysiological biomarkers and their temporal characteristics can significantly improve the localization potential compared to previously published single-biomarker incidence-based approaches, resulting in an average area under ROC curve (AUC) value of 0.73 in a cohort of 82 patients. Our results also suggest that recording durations between 90 min and 2 h are sufficient to localize SOZs with accuracies that may prove clinically relevant. Significance. The successful validation of our approach on a large cohort of 82 patients warrants future investigation on the feasibility of utilizing intra-operative EEG monitoring and artificial intelligence to localize epileptogenic brain tissue. Broadly, our study demonstrates the use of artificial intelligence coupled with careful feature engineering in augmenting clinical decision making.
AB - Objective. An ability to map seizure-generating brain tissue, i.e. the seizure onset zone (SOZ), without recording actual seizures could reduce the duration of invasive EEG monitoring for patients with drug-resistant epilepsy. A widely-adopted practice in the literature is to compare the incidence (events/time) of putative pathological electrophysiological biomarkers associated with epileptic brain tissue with the SOZ determined from spontaneous seizures recorded with intracranial EEG, primarily using a single biomarker. Clinical translation of the previous efforts suffers from their inability to generalize across multiple patients because of (a) the inter-patient variability and (b) the temporal variability in the epileptogenic activity. Approach. Here, we report an artificial intelligence-based approach for combining multiple interictal electrophysiological biomarkers and their temporal characteristics as a way of accounting for the above barriers and show that it can reliably identify seizure onset zones in a study cohort of 82 patients who underwent evaluation for drug-resistant epilepsy. Main results. Our investigation provides evidence that utilizing the complementary information provided by multiple electrophysiological biomarkers and their temporal characteristics can significantly improve the localization potential compared to previously published single-biomarker incidence-based approaches, resulting in an average area under ROC curve (AUC) value of 0.73 in a cohort of 82 patients. Our results also suggest that recording durations between 90 min and 2 h are sufficient to localize SOZs with accuracies that may prove clinically relevant. Significance. The successful validation of our approach on a large cohort of 82 patients warrants future investigation on the feasibility of utilizing intra-operative EEG monitoring and artificial intelligence to localize epileptogenic brain tissue. Broadly, our study demonstrates the use of artificial intelligence coupled with careful feature engineering in augmenting clinical decision making.
KW - artificial intelligence in neurological applications
KW - epilepsy surgery
KW - high-frequency oscillation
KW - interictal epileptiform discharge
KW - phase-amplitude coupling
KW - seizure onset zone
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=85049825162&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85049825162&partnerID=8YFLogxK
U2 - 10.1088/1741-2552/aac960
DO - 10.1088/1741-2552/aac960
M3 - Article
C2 - 29855436
AN - SCOPUS:85049825162
VL - 15
JO - Journal of Neural Engineering
JF - Journal of Neural Engineering
SN - 1741-2560
IS - 4
M1 - 046035
ER -