Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals
Schizophrenia is a brain disorder that disrupts behavioral and cognitive manifestations such as thinking, perception and speech. Early diagnosis of schizophrenia plays an important role in treating and limiting the effects of the disease. An automated diagnosis system for schizophrenia detection thr...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-06-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_199134_4f1e67ca05cb9dea38f5858a18e7b6c6.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823856471279927296 |
|---|---|
| author | Swetha Padmavathi Polisetty Radhamani Ellapparaj Karthikeyan M P |
| author_facet | Swetha Padmavathi Polisetty Radhamani Ellapparaj Karthikeyan M P |
| author_sort | Swetha Padmavathi Polisetty |
| collection | DOAJ |
| description | Schizophrenia is a brain disorder that disrupts behavioral and cognitive manifestations such as thinking, perception and speech. Early diagnosis of schizophrenia plays an important role in treating and limiting the effects of the disease. An automated diagnosis system for schizophrenia detection through a deep learning model is suggested in this research. For this purpose, EEG signals were captured from 36 patients with schizophrenia and 36 healthy controls at resting state. After data preprocessing to reduce noise and artifacts from EEGs, an 11-layer deep learning model consisting of convolution and LSTM layers with LeakyReLU activation function and different kernel sizes was implemented to automatically extract and classify features. The proposed deep learning network produced impressive classification accuracies of 99.33% and 98.49% for 10-fold cross-validation and random splitting methods, respectively. The proposed framework successfully classified the schizophrenia patients with healthy controls with an overall accuracy of 99.33%, sensitivity of 99.26%, specificity of 99.42% and PPV of 99.50%. This robust end-to-end system is expected to be useful as a diagnostic tool for clinicians and provide valuable support in the assessment of schizophrenia due to its automated nature for EEG processing. |
| format | Article |
| id | doaj-art-fd2b3d84dfaa4019b4a9931a5c29da1d |
| institution | Kabale University |
| issn | 2821-0263 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Advances in Engineering and Intelligence Systems |
| spelling | doaj-art-fd2b3d84dfaa4019b4a9931a5c29da1d2025-02-12T08:47:56ZengBilijipub publisherAdvances in Engineering and Intelligence Systems2821-02632024-06-0100302516210.22034/aeis.2024.458185.1194199134Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG SignalsSwetha Padmavathi Polisetty0Radhamani Ellapparaj1Karthikeyan M P2School of Computer Science and Engineering, VIT-AP University, Andhra Pradesh, 522241, IndiaDepartment of Computer Science, Sri S. Ramasamy Naidu Memorial College, Sattur, Tamil Nadu, 626203, IndiaDepartment of Computer Science and IT, JAIN (Deemed-to-Be University), Bengaluru, 560069, IndiaSchizophrenia is a brain disorder that disrupts behavioral and cognitive manifestations such as thinking, perception and speech. Early diagnosis of schizophrenia plays an important role in treating and limiting the effects of the disease. An automated diagnosis system for schizophrenia detection through a deep learning model is suggested in this research. For this purpose, EEG signals were captured from 36 patients with schizophrenia and 36 healthy controls at resting state. After data preprocessing to reduce noise and artifacts from EEGs, an 11-layer deep learning model consisting of convolution and LSTM layers with LeakyReLU activation function and different kernel sizes was implemented to automatically extract and classify features. The proposed deep learning network produced impressive classification accuracies of 99.33% and 98.49% for 10-fold cross-validation and random splitting methods, respectively. The proposed framework successfully classified the schizophrenia patients with healthy controls with an overall accuracy of 99.33%, sensitivity of 99.26%, specificity of 99.42% and PPV of 99.50%. This robust end-to-end system is expected to be useful as a diagnostic tool for clinicians and provide valuable support in the assessment of schizophrenia due to its automated nature for EEG processing.https://aeis.bilijipub.com/article_199134_4f1e67ca05cb9dea38f5858a18e7b6c6.pdfschizophreniaelectroencephalogramdeep learningclassification |
| spellingShingle | Swetha Padmavathi Polisetty Radhamani Ellapparaj Karthikeyan M P Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals Advances in Engineering and Intelligence Systems schizophrenia electroencephalogram deep learning classification |
| title | Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals |
| title_full | Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals |
| title_fullStr | Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals |
| title_full_unstemmed | Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals |
| title_short | Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals |
| title_sort | evaluation of a deep learning model for automatic detection of schizophrenia using eeg signals |
| topic | schizophrenia electroencephalogram deep learning classification |
| url | https://aeis.bilijipub.com/article_199134_4f1e67ca05cb9dea38f5858a18e7b6c6.pdf |
| work_keys_str_mv | AT swethapadmavathipolisetty evaluationofadeeplearningmodelforautomaticdetectionofschizophreniausingeegsignals AT radhamaniellapparaj evaluationofadeeplearningmodelforautomaticdetectionofschizophreniausingeegsignals AT karthikeyanmp evaluationofadeeplearningmodelforautomaticdetectionofschizophreniausingeegsignals |