Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods
Dementia and Alzheimer’s disease are caused by neurodegeneration and poor communication between neurons in the brain. So far, no effective medications have been discovered for dementia and Alzheimer’s disease. Thus, early diagnosis is necessary to avoid the development of these diseases. In this stu...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/22/2860 |
| _version_ | 1797510490608369664 |
|---|---|
| author | Badiea Abdulkarem Mohammed Ebrahim Mohammed Senan Taha H. Rassem Nasrin M. Makbol Adwan Alownie Alanazi Zeyad Ghaleb Al-Mekhlafi Tariq S. Almurayziq Fuad A. Ghaleb |
| author_facet | Badiea Abdulkarem Mohammed Ebrahim Mohammed Senan Taha H. Rassem Nasrin M. Makbol Adwan Alownie Alanazi Zeyad Ghaleb Al-Mekhlafi Tariq S. Almurayziq Fuad A. Ghaleb |
| author_sort | Badiea Abdulkarem Mohammed |
| collection | DOAJ |
| description | Dementia and Alzheimer’s disease are caused by neurodegeneration and poor communication between neurons in the brain. So far, no effective medications have been discovered for dementia and Alzheimer’s disease. Thus, early diagnosis is necessary to avoid the development of these diseases. In this study, efficient machine learning algorithms were assessed to evaluate the Open Access Series of Imaging Studies (OASIS) dataset for dementia diagnosis. Two CNN models (AlexNet and ResNet-50) and hybrid techniques between deep learning and machine learning (AlexNet+SVM and ResNet-50+SVM) were also evaluated for the diagnosis of Alzheimer’s disease. For the OASIS dataset, we balanced the dataset, replaced the missing values, and applied the t-Distributed Stochastic Neighbour Embedding algorithm (t-SNE) to represent the high-dimensional data in the low-dimensional space. All of the machine learning algorithms, namely, Support Vector Machine (SVM), Decision Tree, Random Forest and K Nearest Neighbours (KNN), achieved high performance for diagnosing dementia. The random forest algorithm achieved an overall accuracy of 94% and precision, recall and F1 scores of 93%, 98% and 96%, respectively. The second dataset, the MRI image dataset, was evaluated by AlexNet and ResNet-50 models and AlexNet+SVM and ResNet-50+SVM hybrid techniques. All models achieved high performance, but the performance of the hybrid methods between deep learning and machine learning was better than that of the deep learning models. The AlexNet+SVM hybrid model achieved accuracy, sensitivity, specificity and AUC scores of 94.8%, 93%, 97.75% and 99.70%, respectively. |
| first_indexed | 2024-03-10T05:32:15Z |
| format | Article |
| id | doaj.art-2502dcac4a47464788e01fe8dc0d1749 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T05:32:15Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-2502dcac4a47464788e01fe8dc0d17492023-11-22T23:08:10ZengMDPI AGElectronics2079-92922021-11-011022286010.3390/electronics10222860Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid MethodsBadiea Abdulkarem Mohammed0Ebrahim Mohammed Senan1Taha H. Rassem2Nasrin M. Makbol3Adwan Alownie Alanazi4Zeyad Ghaleb Al-Mekhlafi5Tariq S. Almurayziq6Fuad A. Ghaleb7Department of Computer Engineering, College of Computer Science and Engineering, University of Ha’il, Ha’il 81481, Saudi ArabiaDepartment of Computer Science, Hajjah University, Hajjah 967, YemenFaculty of Science and Technology, Bournemouth University, Poole BH12 5BB, UKCollege of Computer Science and Engineering, Hodeidah University, Hodiedah 967, YemenDepartment of Information and Computer Science, College of Computer Science and Engineering, University of Ha’il, Ha’il 81481, Saudi ArabiaDepartment of Information and Computer Science, College of Computer Science and Engineering, University of Ha’il, Ha’il 81481, Saudi ArabiaDepartment of Information and Computer Science, College of Computer Science and Engineering, University of Ha’il, Ha’il 81481, Saudi ArabiaSchool of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaDementia and Alzheimer’s disease are caused by neurodegeneration and poor communication between neurons in the brain. So far, no effective medications have been discovered for dementia and Alzheimer’s disease. Thus, early diagnosis is necessary to avoid the development of these diseases. In this study, efficient machine learning algorithms were assessed to evaluate the Open Access Series of Imaging Studies (OASIS) dataset for dementia diagnosis. Two CNN models (AlexNet and ResNet-50) and hybrid techniques between deep learning and machine learning (AlexNet+SVM and ResNet-50+SVM) were also evaluated for the diagnosis of Alzheimer’s disease. For the OASIS dataset, we balanced the dataset, replaced the missing values, and applied the t-Distributed Stochastic Neighbour Embedding algorithm (t-SNE) to represent the high-dimensional data in the low-dimensional space. All of the machine learning algorithms, namely, Support Vector Machine (SVM), Decision Tree, Random Forest and K Nearest Neighbours (KNN), achieved high performance for diagnosing dementia. The random forest algorithm achieved an overall accuracy of 94% and precision, recall and F1 scores of 93%, 98% and 96%, respectively. The second dataset, the MRI image dataset, was evaluated by AlexNet and ResNet-50 models and AlexNet+SVM and ResNet-50+SVM hybrid techniques. All models achieved high performance, but the performance of the hybrid methods between deep learning and machine learning was better than that of the deep learning models. The AlexNet+SVM hybrid model achieved accuracy, sensitivity, specificity and AUC scores of 94.8%, 93%, 97.75% and 99.70%, respectively.https://www.mdpi.com/2079-9292/10/22/2860Alzheimerdementiat-SNE algorithmmachine learningdeep learninghybrid techniques |
| spellingShingle | Badiea Abdulkarem Mohammed Ebrahim Mohammed Senan Taha H. Rassem Nasrin M. Makbol Adwan Alownie Alanazi Zeyad Ghaleb Al-Mekhlafi Tariq S. Almurayziq Fuad A. Ghaleb Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods Electronics Alzheimer dementia t-SNE algorithm machine learning deep learning hybrid techniques |
| title | Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods |
| title_full | Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods |
| title_fullStr | Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods |
| title_full_unstemmed | Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods |
| title_short | Multi-Method Analysis of Medical Records and MRI Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods |
| title_sort | multi method analysis of medical records and mri images for early diagnosis of dementia and alzheimer s disease based on deep learning and hybrid methods |
| topic | Alzheimer dementia t-SNE algorithm machine learning deep learning hybrid techniques |
| url | https://www.mdpi.com/2079-9292/10/22/2860 |
| work_keys_str_mv | AT badieaabdulkaremmohammed multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT ebrahimmohammedsenan multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT tahahrassem multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT nasrinmmakbol multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT adwanalowniealanazi multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT zeyadghalebalmekhlafi multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT tariqsalmurayziq multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods AT fuadaghaleb multimethodanalysisofmedicalrecordsandmriimagesforearlydiagnosisofdementiaandalzheimersdiseasebasedondeeplearningandhybridmethods |