Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification
Dementia is a cognitive disorder that mainly targets older adults. At present, dementia has no cure or prevention available. Scientists found that dementia symptoms might emerge as early as ten years before the onset of real disease. As a result, machine learning (ML) scientists developed various te...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/11/2/439 |
| _version_ | 1827758401704165376 |
|---|---|
| author | Ashir Javeed Ana Luiza Dallora Johan Sanmartin Berglund Alper Idrisoglu Liaqat Ali Hafiz Tayyab Rauf Peter Anderberg |
| author_facet | Ashir Javeed Ana Luiza Dallora Johan Sanmartin Berglund Alper Idrisoglu Liaqat Ali Hafiz Tayyab Rauf Peter Anderberg |
| author_sort | Ashir Javeed |
| collection | DOAJ |
| description | Dementia is a cognitive disorder that mainly targets older adults. At present, dementia has no cure or prevention available. Scientists found that dementia symptoms might emerge as early as ten years before the onset of real disease. As a result, machine learning (ML) scientists developed various techniques for the early prediction of dementia using dementia symptoms. However, these methods have fundamental limitations, such as low accuracy and bias in machine learning (ML) models. To resolve the issue of bias in the proposed ML model, we deployed the adaptive synthetic sampling (ADASYN) technique, and to improve accuracy, we have proposed novel feature extraction techniques, namely, feature extraction battery (FEB) and optimized support vector machine (SVM) using radical basis function (rbf) for the classification of the disease. The hyperparameters of SVM are calibrated by employing the grid search approach. It is evident from the experimental results that the newly pr oposed model (FEB-SVM) improves the dementia prediction accuracy of the conventional SVM by 6%. The proposed model (FEB-SVM) obtained 98.28% accuracy on training data and a testing accuracy of 93.92%. Along with accuracy, the proposed model obtained a precision of 91.80%, recall of 86.59, F1-score of 89.12%, and Matthew’s correlation coefficient (MCC) of 0.4987. Moreover, the newly proposed model (FEB-SVM) outperforms the 12 state-of-the-art ML models that the researchers have recently presented for dementia prediction. |
| first_indexed | 2024-03-11T09:06:50Z |
| format | Article |
| id | doaj.art-4aeddaa56af747b4bf6edfeace48cd35 |
| institution | Directory Open Access Journal |
| issn | 2227-9059 |
| language | English |
| last_indexed | 2024-03-11T09:06:50Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj.art-4aeddaa56af747b4bf6edfeace48cd352023-11-16T19:18:15ZengMDPI AGBiomedicines2227-90592023-02-0111243910.3390/biomedicines11020439Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for ClassificationAshir Javeed0Ana Luiza Dallora1Johan Sanmartin Berglund2Alper Idrisoglu3Liaqat Ali4Hafiz Tayyab Rauf5Peter Anderberg6Aging Research Center, Karolinska Institutet, 171 65 Stockholm, SwedenDepartment of Health, Blekinge Institute of Technology, 371 79 Karlskrona, SwedenDepartment of Health, Blekinge Institute of Technology, 371 79 Karlskrona, SwedenDepartment of Health, Blekinge Institute of Technology, 371 79 Karlskrona, SwedenDepartment of Electrical Engineering, University of Science and Technology Bannu, Bannu 28100, PakistanCentre for Smart Systems, AI and Cybersecurity, Staffordshire University, Stoke-on-Trent ST4 2DE, UKDepartment of Health, Blekinge Institute of Technology, 371 79 Karlskrona, SwedenDementia is a cognitive disorder that mainly targets older adults. At present, dementia has no cure or prevention available. Scientists found that dementia symptoms might emerge as early as ten years before the onset of real disease. As a result, machine learning (ML) scientists developed various techniques for the early prediction of dementia using dementia symptoms. However, these methods have fundamental limitations, such as low accuracy and bias in machine learning (ML) models. To resolve the issue of bias in the proposed ML model, we deployed the adaptive synthetic sampling (ADASYN) technique, and to improve accuracy, we have proposed novel feature extraction techniques, namely, feature extraction battery (FEB) and optimized support vector machine (SVM) using radical basis function (rbf) for the classification of the disease. The hyperparameters of SVM are calibrated by employing the grid search approach. It is evident from the experimental results that the newly pr oposed model (FEB-SVM) improves the dementia prediction accuracy of the conventional SVM by 6%. The proposed model (FEB-SVM) obtained 98.28% accuracy on training data and a testing accuracy of 93.92%. Along with accuracy, the proposed model obtained a precision of 91.80%, recall of 86.59, F1-score of 89.12%, and Matthew’s correlation coefficient (MCC) of 0.4987. Moreover, the newly proposed model (FEB-SVM) outperforms the 12 state-of-the-art ML models that the researchers have recently presented for dementia prediction.https://www.mdpi.com/2227-9059/11/2/439dementiafeature fusionmachine learningimbalance classes |
| spellingShingle | Ashir Javeed Ana Luiza Dallora Johan Sanmartin Berglund Alper Idrisoglu Liaqat Ali Hafiz Tayyab Rauf Peter Anderberg Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification Biomedicines dementia feature fusion machine learning imbalance classes |
| title | Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification |
| title_full | Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification |
| title_fullStr | Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification |
| title_full_unstemmed | Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification |
| title_short | Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification |
| title_sort | early prediction of dementia using feature extraction battery feb and optimized support vector machine svm for classification |
| topic | dementia feature fusion machine learning imbalance classes |
| url | https://www.mdpi.com/2227-9059/11/2/439 |
| work_keys_str_mv | AT ashirjaveed earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification AT analuizadallora earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification AT johansanmartinberglund earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification AT alperidrisoglu earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification AT liaqatali earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification AT hafiztayyabrauf earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification AT peteranderberg earlypredictionofdementiausingfeatureextractionbatteryfebandoptimizedsupportvectormachinesvmforclassification |