Diagnosis of Parkinson disease from EEG signals using a CNN-LSTM model and explainable AI

Mohammad Bdaqli, Afshin Shoeibi*, Parisa Moridian, Delaram Sadeghi, Mozhde Firoozi Pouyani, Ahmad Shalbaf, Juan M. Gorriz

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Parkinson’s disease (PD), a complex and debilitating neurological disorder, often leads to progressive cognitive decline, including mild cognitive impairment (MCI) and dementia. Over the years, various methods have been developed to diagnose PD, with neuroimaging modalities, particularly electroencephalogram (EEG) recording, gaining significant traction among specialist doctors. This article presents a novel PD detection method employing deep learning (DL) techniques to analyze EEG signals. The proposed method utilizes the UC San Diego (UCSD) resting-state EEG dataset and involves a meticulous preprocessing phase encompassing filtering, channel selection, and EEG signal windowing. Subsequently, a novel 1D CNN-LSTM architecture is introduced for extracting salient features from EEG signals. In the classification stage, three algorithms, namely Softmax, support vector machine (SVM), and decision tree (DT), are employed and their performances compared. To assess the robustness of the classification models, k-fold cross-validation with k=10 is implemented. The results demonstrate that the SVM algorithm exhibits superior performance, achieving an impressive 99.51% accuracy for binary classification and 99.75% accuracy for multi-class classification tasks. To gain insights into the model’s decision-making process and enhance interpretability, t-distributed Stochastic Neighbor Embedding (t-SNE) is utilized as an explainable artificial intelligence (XAI) method in the post-processing stage.
Original languageEnglish
Title of host publicationArtificial intelligence for neuroscience and emotional systems
Subtitle of host publication10th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2024, Olhâo, Portugal, June 4–7, 2024, proceedings, part I
EditorsJosé Manuel Ferrández Vicente, Mikel Val Calvo, Hojjat Adeli
Place of PublicationCham
PublisherSpringer, Springer Nature
Pages128-138
Number of pages11
ISBN (Electronic)9783031611407
ISBN (Print)9783031611391
DOIs
Publication statusPublished - 2024
Externally publishedYes
EventInternational Work-Conference on the Interplay Between Natural and Artificial Computation (10th : 2024) - Olhâo, Portugal
Duration: 4 Jun 20247 Jun 2024
Conference number: 10th

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume14674
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Work-Conference on the Interplay Between Natural and Artificial Computation (10th : 2024)
Abbreviated titleIWINAC 2024
Country/TerritoryPortugal
CityOlhâo
Period4/06/247/06/24

Keywords

  • Parkinson Disease
  • Diagnosis
  • EEG
  • CNN-CNN
  • Explainable Artificial Intelligence

Fingerprint

Dive into the research topics of 'Diagnosis of Parkinson disease from EEG signals using a CNN-LSTM model and explainable AI'. Together they form a unique fingerprint.

Cite this