Analyzing Intracranial EEG in Pharmacoresistant Epilepsy Patients Using Hidden Markov Models and Time Series Forecasting
- PDF / 3,531,649 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 104 Downloads / 228 Views
ORIGINAL RESEARCH
Analyzing Intracranial EEG in Pharmacoresistant Epilepsy Patients Using Hidden Markov Models and Time Series Forecasting Methods Ashok Bhowmick1 · Mucahit Cevik1 · Ayse Basar1 Received: 20 July 2020 / Accepted: 22 September 2020 © Springer Nature Singapore Pte Ltd 2020
Abstract Various brain activities can be captured by electroencephalographic signals, which can then be used to detect epilepsy considering that the epileptic seizures are caused by a disturbance in the electrophysiological activity of the brain. Accordingly, epileptic seizure prediction usually requires a careful analysis of electroencephalography (EEG) records. In this study, we examined a large intracranial EEG dataset obtained from five pharmacoresistant epilepsy patients. Specifically, we first applied hidden Markov models to parse the amplitude under a probabilistic description considering the observed data as the outcome of either one of the three hidden states, namely, normal, subclinical (seizure) and clinical (seizure), which is in line with the setup proposed in previous studies. Our results indicate that there are indeed a maximum of 1.7% subclinical and about 1% clinical events, which comply with the observations from other studies. Next, we assumed EEG signals to form complex time series, and considered time-series prediction methods to forecast the future events. Such predictions are of interest to predetermine the possibility of a seizure onset and taking a preventive strategy. This task was performed within a deterministic framework by applying deep learning methods. An ensemble model was created using one-dimensional convolution net in conjunction with long short-term memory units and deep neural networks. We observe that the proposed time series prediction method is highly accurate as indicated by the low mean absolute error values and the high conformity of the predictions to the ground truth values. Keywords Intracranial EEG · Hidden Markov models · Time series prediction · Machine learning · Epilepsy
Introduction Epilepsy is a dynamical disease associated with unpredictable seizure attacks in brain. Understanding the underlying cause of epilepsy as well as the solution to it is still a mystery. Effects of epilepsy are prevalent over fifty million people worldwide [11, 57] which still suffers from unfortunate social stigmas adding another dimension to the challenge of treatment [33]. Pharmacoresistant or drug-resistant epilepsy is the clinically intractable type which in most cases * Ashok Bhowmick [email protected] Mucahit Cevik [email protected] Ayse Basar [email protected] 1
Data Science Lab, Mechanical Industrial Engineering Department, Ryerson University, Toronto, ON M5B 2K3, Canada
require surgery as a mandatory part of the treatment. The seizure onset (SOZ) within the epileptogenic zone (EL), a part of the brain tissue, needs to be identified for successful resection [27]. Invasive electroencephalography (iEEG) by intracranial procedures in this regard, is conducted to acquire a det
Data Loading...
