Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning
Alzheimer’s disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Develop...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9791366/ |
| _version_ | 1797805190503464960 |
|---|---|
| author | Mahmoud Seifallahi Afsoon Hasani Mehraban James E. Galvin Behnaz Ghoraani |
| author_facet | Mahmoud Seifallahi Afsoon Hasani Mehraban James E. Galvin Behnaz Ghoraani |
| author_sort | Mahmoud Seifallahi |
| collection | DOAJ |
| description | Alzheimer’s disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Developing a low-cost and easy-to-use AD detection tool, which can be used in any clinical or non-clinical setting, can enable widespread AD assessments and diagnosis. This paper investigated the feasibility of developing such a tool to detect AD vs. healthy control (HC) from a simple balance and walking assessment called the Timed Up and Go (TUG) test. We collected joint position data of 47 HC and 38 AD subjects as they performed TUG in front of a Kinect V.2 camera. Our signal processing and statistical analyses provided a comprehensive analysis of balance and gait with 12 significant features for discriminating AD from HC after adjusting for age and the Geriatric Depression Scale. Using these features and a support vector machine classifier, our model classified the two groups with an average accuracy of 97.75% and an F-score of 97.67% for five-fold cross-validation and 98.68% and 98.67% for leave-one-subject out cross-validation. These results demonstrate the potential of our approach as a new quantitative complementary tool for detecting AD among older adults. Our work is novel as it presents the first application of Kinect V.2 camera and machine learning to provide a comprehensive and quantitative analysis of the TUG test to detect AD patients from HC. This study supports the feasibility of developing a low-cost and convenient AD assessment tool that can be used during routine checkups or even at home; however, future investigations could confirm its clinical diagnostic value in a larger cohort. |
| first_indexed | 2024-03-13T05:48:19Z |
| format | Article |
| id | doaj.art-e98afa14aa05406fb12662b992ccfa1f |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:48:19Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-e98afa14aa05406fb12662b992ccfa1f2023-06-13T20:06:36ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102022-01-01301589160010.1109/TNSRE.2022.31812529791366Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine LearningMahmoud Seifallahi0https://orcid.org/0000-0002-6056-2115Afsoon Hasani Mehraban1James E. Galvin2Behnaz Ghoraani3https://orcid.org/0000-0003-0075-7663Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USADepartment of Occupational Therapy, Faculty of Rehabilitation Sciences, Iran University of Medical Sciences and Health Sciences, Tehran, IranDepartment of Neurology, Comprehensive Center for Brain Health, University of Miami, Miami, FL, USADepartment of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USAAlzheimer’s disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Developing a low-cost and easy-to-use AD detection tool, which can be used in any clinical or non-clinical setting, can enable widespread AD assessments and diagnosis. This paper investigated the feasibility of developing such a tool to detect AD vs. healthy control (HC) from a simple balance and walking assessment called the Timed Up and Go (TUG) test. We collected joint position data of 47 HC and 38 AD subjects as they performed TUG in front of a Kinect V.2 camera. Our signal processing and statistical analyses provided a comprehensive analysis of balance and gait with 12 significant features for discriminating AD from HC after adjusting for age and the Geriatric Depression Scale. Using these features and a support vector machine classifier, our model classified the two groups with an average accuracy of 97.75% and an F-score of 97.67% for five-fold cross-validation and 98.68% and 98.67% for leave-one-subject out cross-validation. These results demonstrate the potential of our approach as a new quantitative complementary tool for detecting AD among older adults. Our work is novel as it presents the first application of Kinect V.2 camera and machine learning to provide a comprehensive and quantitative analysis of the TUG test to detect AD patients from HC. This study supports the feasibility of developing a low-cost and convenient AD assessment tool that can be used during routine checkups or even at home; however, future investigations could confirm its clinical diagnostic value in a larger cohort.https://ieeexplore.ieee.org/document/9791366/Alzheimer’s disease (AD)timed up and go (TUG)Kinect V.2 cameraskeletal datamachine learningsupport vector machine (SVM) |
| spellingShingle | Mahmoud Seifallahi Afsoon Hasani Mehraban James E. Galvin Behnaz Ghoraani Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning IEEE Transactions on Neural Systems and Rehabilitation Engineering Alzheimer’s disease (AD) timed up and go (TUG) Kinect V.2 camera skeletal data machine learning support vector machine (SVM) |
| title | Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning |
| title_full | Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning |
| title_fullStr | Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning |
| title_full_unstemmed | Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning |
| title_short | Alzheimer’s Disease Detection Using Comprehensive Analysis of Timed Up and Go Test via Kinect V.2 Camera and Machine Learning |
| title_sort | alzheimer x2019 s disease detection using comprehensive analysis of timed up and go test via kinect v 2 camera and machine learning |
| topic | Alzheimer’s disease (AD) timed up and go (TUG) Kinect V.2 camera skeletal data machine learning support vector machine (SVM) |
| url | https://ieeexplore.ieee.org/document/9791366/ |
| work_keys_str_mv | AT mahmoudseifallahi alzheimerx2019sdiseasedetectionusingcomprehensiveanalysisoftimedupandgotestviakinectv2cameraandmachinelearning AT afsoonhasanimehraban alzheimerx2019sdiseasedetectionusingcomprehensiveanalysisoftimedupandgotestviakinectv2cameraandmachinelearning AT jamesegalvin alzheimerx2019sdiseasedetectionusingcomprehensiveanalysisoftimedupandgotestviakinectv2cameraandmachinelearning AT behnazghoraani alzheimerx2019sdiseasedetectionusingcomprehensiveanalysisoftimedupandgotestviakinectv2cameraandmachinelearning |