Using Deep Learning algorithms to detect the success or failure of the Electroconvulsive Therapy (ECT) sessions

Authors

  • usef faghihi University of Quebec at Trois-Rivières
  • Cyrus kalantarpour

DOI:

https://doi.org/10.32473/flairs.v34i1.128367

Keywords:

EEG, ECT, Deep Learning algorithms, Depression, Major Depression

Abstract

Major Depression Disorder (MDD) is a big problem in our society. MDD can cause suicide and take families apart. When treatment with medications fail, mental healthcare professionals, use Electroconvulsive Therapy (ECT) to treat patients with MDD. During an ECT session, electroencephalogram (EEG) signals let the mental healthcare professionals record patients' brain activities which are helpful to decide whether the treatment was successful. However, there is no standard way to know how and with what intensity a healthcare professional needs to apply electroshock to treat patients with MDD. So far, to our knowledge, researchers have used multi-parametric magnetic resonance imaging (MRI) techniques combined with statistical methods and/or linear machine learning algorithms to predict patients’ responses to ECT. However, the aforementioned methods are very expensive and time-consuming. In this study, we will be using Deep learning algorithms to detect the effectiveness of ECT sessions based on the EEG.

Downloads

Published

2021-04-18

How to Cite

faghihi, usef, & kalantarpour, C. (2021). Using Deep Learning algorithms to detect the success or failure of the Electroconvulsive Therapy (ECT) sessions. The International FLAIRS Conference Proceedings, 34. https://doi.org/10.32473/flairs.v34i1.128367

Issue

Section

Special Track: Semantic, Logics, Information Extraction and AI