Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 18, 2026Journal of NeuroEngineering and RehabilitationOpen Access

EEG complexity analysis using enhanced entropy features for depression detection and severity classification

View Full Paper
Ask AI
Bookmark
Share

Authors

DSDorsa Mosleh ShiraziMMMaryam MohebbiYAYashar Abolfathi

Discussion

Loading...

Member takes

Overview

Demonstrates objective depression detection and severity classification using EEG signals, indicating a non-invasive diagnostic tool.

Key Points

  • The research aims to develop an objective method for detecting and classifying the severity of depression using EEG signals.
  • Extracted novel entropy-based features including dispersion and permutation entropy from EEG signals.
  • Applied minimum-redundancy maximum-relevancy feature selection to reduce feature dimensions.
  • Utilized support vector machine, logistic regression, and k-nearest neighbor as classifiers.
  • Assessed classifier performance with 5-fold cross-validation.
  • SVM classifier achieved 97% accuracy in differentiating between normal and depressed individuals.
  • SVM classified depression severity with 71% accuracy.
  • Entropy-based EEG analysis reflects functional changes in key brain regions.

Cite This Study

Shirazi et al. (2026) studied this question.

synapsesocial.com/papers/69e31f1a40886becb653e8a9https://doi.org/10.1186/s12984-026-01975-y
View Full Paper
Ask AI
Bookmark
Share