|
|||||
|
|
Automated diagnosis of epilepsy using EEG power spectrum |
|
| Authors: | Wesley T. Kerr Ariana Anderson Edward P. Lau Andrew Y. Cho Hongjing Xia Jennifer Bramen Pamela K. Douglas Eric S. Braun John M. Stern Mark S. Cohen |
| Affiliation: | 1. Medical Scientist Training Program and Department of Biomathematics, University of California at Los Angeles, Los Angeles, California, U.S.A.;2. Neuropsychiatric Institute, University of California at Los Angeles, Los Angeles, California, U.S.A.;3. Department of Biomedical Engineering, University of California at Los Angeles, Los Angeles, California, U.S.A.;4. Department of Urban Planning, University of California at Los Angeles, Los Angeles, California, U.S.A.;5. Department of Neurology, University of California at Los Angeles, Los Angeles, California, U.S.A. |
| Abstract: | Interictal electroencephalography (EEG) has clinically meaningful limitations in its sensitivity and specificity in the diagnosis of epilepsy because of its dependence on the occurrence of epileptiform discharges. We have developed a computer‐aided diagnostic (CAD) tool that operates on the absolute spectral energy of the routine EEG and has both substantially higher sensitivity and negative predictive value than the identification of interictal epileptiform discharges. Our approach used a multilayer perceptron to classify 156 patients admitted for video‐EEG monitoring. The patient population was diagnostically diverse; 87 were diagnosed with either generalized or focal seizures. The remainder of the patients were diagnosed with nonepileptic seizures. The sensitivity was 92% (95% confidence interval [CI] 85–97%) and the negative predictive value was 82% (95% CI 67–92%). We discuss how these findings suggest that this CAD can be used to supplement event‐based analysis by trained epileptologists. |
| Keywords: | Epilepsy Machine learning Prediction Nonepileptic seizure Computer‐aided diagnostics |