A Self-Learning Methodology for Epileptic Seizure Detection with Minimally-Supervised Edge Labeling
(2019) 22nd Design, Automation and Test in Europe Conference and Exhibition, DATE 2019 p.764-769- Abstract
Epilepsy is one of the most common neurological disorders and affects over 65 million people worldwide. Despite the continuing advances in anti-epileptic treatments, one third of the epilepsy patients live with drug resistant seizures. Besides, the mortality rate among epileptic patients is 2 - 3 times higher than in the matching group of the general population. Wearable devices offer a promising solution for the detection of seizures in real time so as to alert family and caregivers to provide immediate assistance to the patient. However, in order for the detection system to be reliable, a considerable amount of labeled data is required to train it. Labeling epilepsy data is a costly and time-consuming process that requires manual... (More)
Epilepsy is one of the most common neurological disorders and affects over 65 million people worldwide. Despite the continuing advances in anti-epileptic treatments, one third of the epilepsy patients live with drug resistant seizures. Besides, the mortality rate among epileptic patients is 2 - 3 times higher than in the matching group of the general population. Wearable devices offer a promising solution for the detection of seizures in real time so as to alert family and caregivers to provide immediate assistance to the patient. However, in order for the detection system to be reliable, a considerable amount of labeled data is required to train it. Labeling epilepsy data is a costly and time-consuming process that requires manual inspection and annotation of electroencephalogram (EEG) recordings by medical experts. In this paper, we present a self-learning methodology for epileptic seizure detection without medical supervision. We propose a minimally-supervised algorithm for automatic labeling of seizures in order to generate personalized training data. We demonstrate that the median deviation of the labels from the ground truth is only 10.1 seconds or, equivalently, less than 1% of the signal length. Moreover, we show that training a real-time detection algorithm with data labeled by our algorithm produces a degradation of less than 2.5% in comparison to training it with data labeled by medical experts. We evaluated our methodology on a wearable platform and achieved a lifetime of 2.59 days on a single battery charge.
(Less)
- author
- Pascual, Damián ; Aminifar, Amir LU and Atienza, David
- publishing date
- 2019-05-14
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the 2019 Design, Automation and Test in Europe Conference and Exhibition, DATE 2019
- article number
- 8714995
- pages
- 6 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 22nd Design, Automation and Test in Europe Conference and Exhibition, DATE 2019
- conference location
- Florence, Italy
- conference dates
- 2019-03-25 - 2019-03-29
- external identifiers
-
- scopus:85066627674
- ISBN
- 9783981926323
- DOI
- 10.23919/DATE.2019.8714995
- language
- English
- LU publication?
- no
- additional info
- Publisher Copyright: © 2019 EDAA.
- id
- 11c363c7-8a56-45a3-a200-b707429f8722
- date added to LUP
- 2022-02-05 01:21:01
- date last changed
- 2022-04-22 07:26:04
@inproceedings{11c363c7-8a56-45a3-a200-b707429f8722, abstract = {{<p>Epilepsy is one of the most common neurological disorders and affects over 65 million people worldwide. Despite the continuing advances in anti-epileptic treatments, one third of the epilepsy patients live with drug resistant seizures. Besides, the mortality rate among epileptic patients is 2 - 3 times higher than in the matching group of the general population. Wearable devices offer a promising solution for the detection of seizures in real time so as to alert family and caregivers to provide immediate assistance to the patient. However, in order for the detection system to be reliable, a considerable amount of labeled data is required to train it. Labeling epilepsy data is a costly and time-consuming process that requires manual inspection and annotation of electroencephalogram (EEG) recordings by medical experts. In this paper, we present a self-learning methodology for epileptic seizure detection without medical supervision. We propose a minimally-supervised algorithm for automatic labeling of seizures in order to generate personalized training data. We demonstrate that the median deviation of the labels from the ground truth is only 10.1 seconds or, equivalently, less than 1% of the signal length. Moreover, we show that training a real-time detection algorithm with data labeled by our algorithm produces a degradation of less than 2.5% in comparison to training it with data labeled by medical experts. We evaluated our methodology on a wearable platform and achieved a lifetime of 2.59 days on a single battery charge.</p>}}, author = {{Pascual, Damián and Aminifar, Amir and Atienza, David}}, booktitle = {{Proceedings of the 2019 Design, Automation and Test in Europe Conference and Exhibition, DATE 2019}}, isbn = {{9783981926323}}, language = {{eng}}, month = {{05}}, pages = {{764--769}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{A Self-Learning Methodology for Epileptic Seizure Detection with Minimally-Supervised Edge Labeling}}, url = {{http://dx.doi.org/10.23919/DATE.2019.8714995}}, doi = {{10.23919/DATE.2019.8714995}}, year = {{2019}}, }