Applying Change Point Detection to the Seizure Prediction and Detection Problem
Abstract number :
2.077
Submission category :
3. Neurophysiology / 3G. Computational Analysis & Modeling of EEG
Year :
2022
Submission ID :
2205104
Source :
www.aesnet.org
Presentation date :
12/4/2022 12:00:00 PM
Published date :
Nov 22, 2022, 05:28 AM
Authors :
Madeline Fields, – Department of Neurology, Icahn School of Medicine At Mount Sinai, New York, NY; Koyuncu Deniz, BS – Rensselaer Polytechnique Institute; li zan, BS – Rensselaer Polytechnique Institute; Kyongmin Yeo, PhD – IBM research; Wesley Gifford, PhD – IBM research; Singh Anuradha, MD – Icahn School of Medicine at Mount Sinai; Jiyeoun Yoo, MD – Icahn School of Medicine at Mount Sinai; Lizbeth Nunez Martinez, BS, BA – Icahn School of Medicine at Mount Sinai; Saadi Ghatan, MD – Icahn School of Medicine at Mount Sinai; Ignacio Saez, PhD – Icahn School of Medicine at Mount Sinai; fedor Panov, MD – Icahn School of Medicine at Mount Sinai; Ali Tajer, PhD – Rensselaer Polytechnique Institute; Bulent Yener, PhD – Rensselaer Polytechnique Institute; Lara Marcuse, MD – Icahn School of Medicine at Mount Sinai
Rationale: In individuals with drug-resistant epilepsy (DRE), seizures are unpredictable, often occurring with little or no warning. The unpredictability causes anxiety and much of the morbidity and mortality of seizures. Recently, machine learning (ML) models have been developed to predict seizures 10 minutes before they happen with high accuracy using high-dimensional electroencephalography (EEG) recordings. One reason for this success is the ability to identify a pre-seizure period, which is not detectable by electroencephalographers but can be by advanced ML models such as deep learning (DL) algorithms. As a result, seizures can be predicted by detecting the transition from the non-seizure epoch to the pre-seizure epoch.
Methods: In this work, we formulate the seizure prediction problem as an instance of a change point detection (CPD) problem and consider several variants under different settings, including the quickest CPD, transient CPD, and retrospective CPD frameworks. The EEG data is discretized to 1 second windows, but instead of treating the data as a bag of windows, we remain faithful to the temporal order of the windows. Our approach to CPD is based on estimating the probability density ratios using ML algorithms without explicitly computing the ratios. We can analytically establish that density ratios are sufficient statistics for performing CPD.
Results: We show the feasibility in simulations and apply the methods to Intracranial EEG recordings with simultaneous scalp EEG of 102 seizures of mesial temporal lobe onset from 19 patients with DRE. We compare different frameworks and the associated penalty functions on the experimental data.
Conclusions: The CPD-based approach to seizure prediction captures the temporal information in the EEG signal; it is sensitive to temporal fluctuations and can detect the changes with minimal delay after the change point. This is a promising approach for real-time deployment.
Funding: None
Neurophysiology