Electrographic Seizure Detection and Forecasting for People with Epilepsy

About fifty million people worldwide suffer from epilepsy, a neurological disorder marked by sudden, recurrent episodes of abnormal electrical activity in the brain, potentially causing sensory disturbances, convulsions and/or loss of consciousness. Seizure diaries that record the start and end times of each seizure, along with associated information are important in the management of the disease. However, video electroencephalogram (EEG) systems available in epilepsy monitoring units and at home ambulatory monitoring units are bulky and unwieldy for continuously monitoring patients during activities of their everyday life. In this talk, I will describe ongoing efforts to address this issue by utilizing single channel, wireless and wearable EEG sensors, and a machine learning approach to continuously monitor persons with epilepsy to detect and characterize electrographic seizures. In addition to explaining the basic approach to automated seizure analysis, I will discuss: (1) an approach to generalizing the method so that systems trained on one set of patients can be used to monitor other patients; (2) an approach to enhancing the training of the machine learning system when sufficient amount of data is not available; (3) a probabilistic method for determining the type of seizure; (4) our approaches to converting intermediate, segment-level decisions to seizure event-level decisions; and (5) a personalized algorithm for seizure forecasting to warn patients of impending seizures. I will illustrate the viability of our algorithms using data collected in a multi-center study.

Speaker : V John Mathews

Biography : 

V John Mathews is a professor in the School of Electrical Engineering and Computer Science at the Oregon State University and Prof. Satish Dhawan (IoE) Visiting Chair Professor at the Indian Institute of Science, Bangalore. He received his Ph.D. and M.S. degrees in electrical and computer engineering from the University of Iowa, Iowa City, Iowa in 1984 and 1981, respectively, and the B.E. (Hons.) degree in electronics and communication engineering from the Regional Engineering College (now National Institute of Technology), Tiruchirappalli, India in 1980.

His research interests are in nonlinear and adaptive signal processing and application of signal processing and machine learning techniques in neural engineering, biomedicine, and structural health management. Mathews is a Fellow of the IEEE. He has served in many leadership positions of the IEEE Signal Processing Society.