Header

UZH-Logo

Maintenance Infos

Machine Learning Techniques for Personalized Detection of Epileptic Events in Clinical Video Recordings


Pediaditis, Matthew; Ciubotaru, Anca-Nicoleta; Brunschwiler, Thomas; Hilfiker, Peter; Grünwald, Thomas; Ha Berlin, Marcellina; Imbach, Lukas L; Muroi, Carl; Stra Ssle, Christian; Keller, Emanuela; Gabrani, Maria (2021). Machine Learning Techniques for Personalized Detection of Epileptic Events in Clinical Video Recordings. AMIA: Annual Symposium proceedings, 2020:1003-1011.

Abstract

Continuous patient monitoring is essential to achieve an effective and optimal patient treatment in the intensive care unit. In the specific case of epilepsy it is the only way to achieve a correct diagnosis and a subsequent optimal medication plan if possible. In addition to automatic vital sign monitoring, epilepsy patients need manual monitoring by trained personnel, a task that is very difficult to be performed continuously for each patient. Moreover, epileptic manifestations are highly personalized even within the same type of epilepsy. In this work we assess two machine learning methods, dictionary learning and an autoencoder based on long short-term memory (LSTM) cells, on the task of personalized epileptic event detection in videos, with a set of features that were specifically developed with an emphasis on high motion sensitivity. According to the strengths of each method we have selected different types of epilepsy, one with convulsive behaviour and one with very subtle motion. The results on five clinical patients show a highly promising ability of both methods to detect the epileptic events as anomalies deviating from the stable/normal patient status.

Abstract

Continuous patient monitoring is essential to achieve an effective and optimal patient treatment in the intensive care unit. In the specific case of epilepsy it is the only way to achieve a correct diagnosis and a subsequent optimal medication plan if possible. In addition to automatic vital sign monitoring, epilepsy patients need manual monitoring by trained personnel, a task that is very difficult to be performed continuously for each patient. Moreover, epileptic manifestations are highly personalized even within the same type of epilepsy. In this work we assess two machine learning methods, dictionary learning and an autoencoder based on long short-term memory (LSTM) cells, on the task of personalized epileptic event detection in videos, with a set of features that were specifically developed with an emphasis on high motion sensitivity. According to the strengths of each method we have selected different types of epilepsy, one with convulsive behaviour and one with very subtle motion. The results on five clinical patients show a highly promising ability of both methods to detect the epileptic events as anomalies deviating from the stable/normal patient status.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

28 downloads since deposited on 14 Jul 2021
10 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Institute of Intensive Care Medicine
04 Faculty of Medicine > University Hospital Zurich > Clinic for Neurosurgery
Dewey Decimal Classification:610 Medicine & health
Scopus Subject Areas:Health Sciences > General Medicine
Language:English
Date:25 January 2021
Deposited On:14 Jul 2021 15:33
Last Modified:24 Dec 2022 08:09
Publisher:American Medical Informatics Association
ISSN:1559-4076
OA Status:Green
Free access at:PubMed ID. An embargo period may apply.
PubMed ID:33936476
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)