An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals
Background: Electroencephalography (EEG) signal analysis is a rapid, low-cost, and practical method for diagnosing the early stages of dementia, including mild cognitive impairment (MCI) and Alzheimer’s disease (AD). The extraction of appropriate biomarkers to assess a subject’s cognitive impairment...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/3/477 |
| _version_ | 1827760197935824896 |
|---|---|
| author | Seyed-Ali Sadegh-Zadeh Elham Fakhri Mahboobe Bahrami Elnaz Bagheri Razieh Khamsehashari Maryam Noroozian Amir M. Hajiyavand |
| author_facet | Seyed-Ali Sadegh-Zadeh Elham Fakhri Mahboobe Bahrami Elnaz Bagheri Razieh Khamsehashari Maryam Noroozian Amir M. Hajiyavand |
| author_sort | Seyed-Ali Sadegh-Zadeh |
| collection | DOAJ |
| description | Background: Electroencephalography (EEG) signal analysis is a rapid, low-cost, and practical method for diagnosing the early stages of dementia, including mild cognitive impairment (MCI) and Alzheimer’s disease (AD). The extraction of appropriate biomarkers to assess a subject’s cognitive impairment has attracted a lot of attention in recent years. The aberrant progression of AD leads to cortical detachment. Due to the interaction of several brain areas, these disconnections may show up as abnormalities in functional connectivity and complicated behaviors. Methods: This work suggests a novel method for differentiating between AD, MCI, and HC in two-class and three-class classifications based on EEG signals. To solve the class imbalance, we employ EEG data augmentation techniques, such as repeating minority classes using variational autoencoders (VAEs), as well as traditional noise-addition methods and hybrid approaches. The power spectrum density (PSD) and temporal data employed in this study’s feature extraction from EEG signals were combined, and a support vector machine (SVM) classifier was used to distinguish between three categories of problems. Results: Insufficient data and unbalanced datasets are two common problems in AD datasets. This study has shown that it is possible to generate comparable data using noise addition and VAE, train the model using these data, and, to some extent, overcome the aforementioned issues with an increase in classification accuracy of 2 to 7%. Conclusion: In this work, using EEG data, we were able to successfully detect three classes: AD, MCI, and HC. In comparison to the pre-augmentation stage, the accuracy gained in the classification of the three classes increased by 3% when the VAE model added additional data. As a result, it is clear how useful EEG data augmentation methods are for classes with smaller sample numbers. |
| first_indexed | 2024-03-11T09:48:11Z |
| format | Article |
| id | doaj.art-797917c0d33849d29ae2c90ff1d65ba9 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T09:48:11Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-797917c0d33849d29ae2c90ff1d65ba92023-11-16T16:25:16ZengMDPI AGDiagnostics2075-44182023-01-0113347710.3390/diagnostics13030477An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain SignalsSeyed-Ali Sadegh-Zadeh0Elham Fakhri1Mahboobe Bahrami2Elnaz Bagheri3Razieh Khamsehashari4Maryam Noroozian5Amir M. Hajiyavand6Department of Computing, School of Digital, Technologies and Arts, Staffordshire University, Stoke-on-Trent ST4 2DE, UKDepartment of Computing, School of Digital, Technologies and Arts, Staffordshire University, Stoke-on-Trent ST4 2DE, UKBehavioral Sciences Research Center, School of Medicine, Isfahan University of Medical Sciences, Isfahan 8174533871, IranDepartment of Computing, School of Digital, Technologies and Arts, Staffordshire University, Stoke-on-Trent ST4 2DE, UKQuality and Usability, Technical University of Berlin, 10623 Berlin, GermanyCognitive Neurology and Neuropsychiatry Division, Department of Psychiatry, Tehran University of Medical Sciences, Tehran 1416634793, IranDepartment of Mechanical Engineering, School of Engineering, University of Birmingham, Birmingham B15 2SQ, UKBackground: Electroencephalography (EEG) signal analysis is a rapid, low-cost, and practical method for diagnosing the early stages of dementia, including mild cognitive impairment (MCI) and Alzheimer’s disease (AD). The extraction of appropriate biomarkers to assess a subject’s cognitive impairment has attracted a lot of attention in recent years. The aberrant progression of AD leads to cortical detachment. Due to the interaction of several brain areas, these disconnections may show up as abnormalities in functional connectivity and complicated behaviors. Methods: This work suggests a novel method for differentiating between AD, MCI, and HC in two-class and three-class classifications based on EEG signals. To solve the class imbalance, we employ EEG data augmentation techniques, such as repeating minority classes using variational autoencoders (VAEs), as well as traditional noise-addition methods and hybrid approaches. The power spectrum density (PSD) and temporal data employed in this study’s feature extraction from EEG signals were combined, and a support vector machine (SVM) classifier was used to distinguish between three categories of problems. Results: Insufficient data and unbalanced datasets are two common problems in AD datasets. This study has shown that it is possible to generate comparable data using noise addition and VAE, train the model using these data, and, to some extent, overcome the aforementioned issues with an increase in classification accuracy of 2 to 7%. Conclusion: In this work, using EEG data, we were able to successfully detect three classes: AD, MCI, and HC. In comparison to the pre-augmentation stage, the accuracy gained in the classification of the three classes increased by 3% when the VAE model added additional data. As a result, it is clear how useful EEG data augmentation methods are for classes with smaller sample numbers.https://www.mdpi.com/2075-4418/13/3/477Alzheimer’s diseasediagnosiselectroencephalogram (EEG)machine learningdata augmentation strategy |
| spellingShingle | Seyed-Ali Sadegh-Zadeh Elham Fakhri Mahboobe Bahrami Elnaz Bagheri Razieh Khamsehashari Maryam Noroozian Amir M. Hajiyavand An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals Diagnostics Alzheimer’s disease diagnosis electroencephalogram (EEG) machine learning data augmentation strategy |
| title | An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals |
| title_full | An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals |
| title_fullStr | An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals |
| title_full_unstemmed | An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals |
| title_short | An Approach toward Artificial Intelligence Alzheimer’s Disease Diagnosis Using Brain Signals |
| title_sort | approach toward artificial intelligence alzheimer s disease diagnosis using brain signals |
| topic | Alzheimer’s disease diagnosis electroencephalogram (EEG) machine learning data augmentation strategy |
| url | https://www.mdpi.com/2075-4418/13/3/477 |
| work_keys_str_mv | AT seyedalisadeghzadeh anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT elhamfakhri anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT mahboobebahrami anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT elnazbagheri anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT raziehkhamsehashari anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT maryamnoroozian anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT amirmhajiyavand anapproachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT seyedalisadeghzadeh approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT elhamfakhri approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT mahboobebahrami approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT elnazbagheri approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT raziehkhamsehashari approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT maryamnoroozian approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals AT amirmhajiyavand approachtowardartificialintelligencealzheimersdiseasediagnosisusingbrainsignals |