An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms
IntroductionSchizophrenia is a severe psychological disorder that significantly impacts an individual’s life and is characterized by abnormalities in perception, behavior, and cognition. Conventional Schizophrenia diagnosis techniques are time- consuming and prone to error. The study proposes a nove...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1630291/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849421426962989056 |
|---|---|
| author | Ahmad Almadhor Stephen Ojo Thomas I. Nathaniel Shtwai Alsubai Abdullah Alharthi Abdullah Al Hejaili Gabriel Avelino Sampedro |
| author_facet | Ahmad Almadhor Stephen Ojo Thomas I. Nathaniel Shtwai Alsubai Abdullah Alharthi Abdullah Al Hejaili Gabriel Avelino Sampedro |
| author_sort | Ahmad Almadhor |
| collection | DOAJ |
| description | IntroductionSchizophrenia is a severe psychological disorder that significantly impacts an individual’s life and is characterized by abnormalities in perception, behavior, and cognition. Conventional Schizophrenia diagnosis techniques are time- consuming and prone to error. The study proposes a novel automated technique for diagnosing Schizophrenia based on electroencephalogram (EEG) sensor data, aiming to enhance interpretability and prediction performance.MethodsThis research utilizes Deep Learning (DL) models, including the Deep Neural Network (DNN), Bi-Directional Long Short-Term Memory-Gated Recurrent Unit (BiLSTM- GRU), and BiLSTM with Attention, for the detection of Schizophrenia based on EEG data. During preprocessing, SMOTE is applied to address the class imbalance. Important EEG characteristics that influence model decisions are highlighted by the interpretable BiLSTM-Attention model using attention weights in conjunction with SHAP and LIME explainability tools. In addition to fine-tuning input dimensionality, F-test feature selection increases learning efficiency.ResultsThrough the integration of feature importance analysis and conventional performance measures, this study presents valuable insights into the discriminative neurophysiological patterns associated with Schizophrenia, advancing both diagnostic and neuroscientific expertise. The experiment’s findings show that the BiLSTM with attention mechanism model provides and accuracy of 0.68%.DiscussionThe results show that the recommended approach is useful for Schizophrenia diagnosis. |
| format | Article |
| id | doaj-art-7f384c50e9b842a89e96262aa18a1437 |
| institution | Kabale University |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-7f384c50e9b842a89e96262aa18a14372025-08-20T03:31:27ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-07-011510.3389/fonc.2025.16302911630291An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanismsAhmad Almadhor0Stephen Ojo1Thomas I. Nathaniel2Shtwai Alsubai3Abdullah Alharthi4Abdullah Al Hejaili5Gabriel Avelino Sampedro6Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Sakaka, Saudi ArabiaDepartment of Electrical and Computer Engineering, College of Engineering, Anderson University, Anderson, SC, United StatesSchool of Medicine Greenville, University of South Carolina, Greenville, SC, United StatesCollege of Computer Engineering and Sciences, Prince Sattam bin Abdulaziz University, AlKharj, Saudi ArabiaDepartment of Electrical Engineering, King Khalid University, Abha, Saudi ArabiaComputer Science Department, Faculty of Computers & Information Technology, University of Tabuk, Tabuk, Saudi ArabiaSchool of Management and Information Technology, De La Salle-College of Saint Benilde, Manila, PhilippinesIntroductionSchizophrenia is a severe psychological disorder that significantly impacts an individual’s life and is characterized by abnormalities in perception, behavior, and cognition. Conventional Schizophrenia diagnosis techniques are time- consuming and prone to error. The study proposes a novel automated technique for diagnosing Schizophrenia based on electroencephalogram (EEG) sensor data, aiming to enhance interpretability and prediction performance.MethodsThis research utilizes Deep Learning (DL) models, including the Deep Neural Network (DNN), Bi-Directional Long Short-Term Memory-Gated Recurrent Unit (BiLSTM- GRU), and BiLSTM with Attention, for the detection of Schizophrenia based on EEG data. During preprocessing, SMOTE is applied to address the class imbalance. Important EEG characteristics that influence model decisions are highlighted by the interpretable BiLSTM-Attention model using attention weights in conjunction with SHAP and LIME explainability tools. In addition to fine-tuning input dimensionality, F-test feature selection increases learning efficiency.ResultsThrough the integration of feature importance analysis and conventional performance measures, this study presents valuable insights into the discriminative neurophysiological patterns associated with Schizophrenia, advancing both diagnostic and neuroscientific expertise. The experiment’s findings show that the BiLSTM with attention mechanism model provides and accuracy of 0.68%.DiscussionThe results show that the recommended approach is useful for Schizophrenia diagnosis.https://www.frontiersin.org/articles/10.3389/fonc.2025.1630291/fullschizophreniaelectroencephalography (EEG)SHAPLIMEfeature selectionSMOTE |
| spellingShingle | Ahmad Almadhor Stephen Ojo Thomas I. Nathaniel Shtwai Alsubai Abdullah Alharthi Abdullah Al Hejaili Gabriel Avelino Sampedro An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms Frontiers in Oncology schizophrenia electroencephalography (EEG) SHAP LIME feature selection SMOTE |
| title | An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms |
| title_full | An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms |
| title_fullStr | An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms |
| title_full_unstemmed | An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms |
| title_short | An interpretable XAI deep EEG model for schizophrenia diagnosis using feature selection and attention mechanisms |
| title_sort | interpretable xai deep eeg model for schizophrenia diagnosis using feature selection and attention mechanisms |
| topic | schizophrenia electroencephalography (EEG) SHAP LIME feature selection SMOTE |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1630291/full |
| work_keys_str_mv | AT ahmadalmadhor aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT stephenojo aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT thomasinathaniel aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT shtwaialsubai aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT abdullahalharthi aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT abdullahalhejaili aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT gabrielavelinosampedro aninterpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT ahmadalmadhor interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT stephenojo interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT thomasinathaniel interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT shtwaialsubai interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT abdullahalharthi interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT abdullahalhejaili interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms AT gabrielavelinosampedro interpretablexaideepeegmodelforschizophreniadiagnosisusingfeatureselectionandattentionmechanisms |