Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation
Stroke is a leading cause of disability among elderly individuals, and gait impairment is a typical characteristic related to the stroke severity experienced by patients. The aim of this study is to propose a novel stroke severity classification method using symmetric gait features with recursive fe...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9932572/ |
| _version_ | 1828128052375191552 |
|---|---|
| author | Joohwan Sung Sungmin Han Heesu Park Soree Hwang Song Joo Lee Jong Woong Park Inchan Youn |
| author_facet | Joohwan Sung Sungmin Han Heesu Park Soree Hwang Song Joo Lee Jong Woong Park Inchan Youn |
| author_sort | Joohwan Sung |
| collection | DOAJ |
| description | Stroke is a leading cause of disability among elderly individuals, and gait impairment is a typical characteristic related to the stroke severity experienced by patients. The aim of this study is to propose a novel stroke severity classification method using symmetric gait features with recursive feature elimination with cross-validation (RFECV). An experiment was conducted on data acquired from thirteen chronic stroke patients and eighteen elderly participants. They walked on a treadmill at four different speeds based on their preferred speed. Symmetric gait features representing the ratio between the left- and right-side values were used as inputs along with the general gait features that did not completely contain the patients’ gait characteristics. We used four different machine learning (ML) techniques to determine the optimal subset for differentiating between the elderly and stroke groups according to severity based on RFECV. In addition, to verify the performance of RFECV and the symmetric gait features, four different feature sets were used: 1) all forty-five general features, 2) all twenty-one symmetric features, 3) the optimal general feature subset obtained by using RFECV, and 4) the optimal symmetric feature subset obtained by using RFECV. The best classification result was obtained by RF-RFECV with an RF classifier derived from the symmetric features (accuracy: 96.01%). The result proved that the stroke severity classification performance increased when symmetric gait data and the RFECV technique were applied. The findings of this study can help clinicians diagnose the stroke severity experienced by patients based on information obtained using ML technology. |
| first_indexed | 2024-04-11T15:58:28Z |
| format | Article |
| id | doaj.art-ed8e289de364409582673e3a888a7815 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T15:58:28Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ed8e289de364409582673e3a888a78152022-12-22T04:15:05ZengIEEEIEEE Access2169-35362022-01-011011943711944710.1109/ACCESS.2022.32181189932572Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-ValidationJoohwan Sung0Sungmin Han1https://orcid.org/0000-0003-2762-668XHeesu Park2https://orcid.org/0000-0001-6858-539XSoree Hwang3Song Joo Lee4https://orcid.org/0000-0002-6710-9209Jong Woong Park5https://orcid.org/0000-0003-2751-2519Inchan Youn6https://orcid.org/0000-0002-0977-0808Biomedical Research Division, Korea Institute of Science and Technology, Seoul, South KoreaBiomedical Research Division, Korea Institute of Science and Technology, Seoul, South KoreaBiomedical Research Division, Korea Institute of Science and Technology, Seoul, South KoreaBiomedical Research Division, Korea Institute of Science and Technology, Seoul, South KoreaBiomedical Research Division, Korea Institute of Science and Technology, Seoul, South KoreaDepartment of Biomedical Science, School of Biomedical Engineering, College of Medicine, Korea University, Seoul, South KoreaBiomedical Research Division, Korea Institute of Science and Technology, Seoul, South KoreaStroke is a leading cause of disability among elderly individuals, and gait impairment is a typical characteristic related to the stroke severity experienced by patients. The aim of this study is to propose a novel stroke severity classification method using symmetric gait features with recursive feature elimination with cross-validation (RFECV). An experiment was conducted on data acquired from thirteen chronic stroke patients and eighteen elderly participants. They walked on a treadmill at four different speeds based on their preferred speed. Symmetric gait features representing the ratio between the left- and right-side values were used as inputs along with the general gait features that did not completely contain the patients’ gait characteristics. We used four different machine learning (ML) techniques to determine the optimal subset for differentiating between the elderly and stroke groups according to severity based on RFECV. In addition, to verify the performance of RFECV and the symmetric gait features, four different feature sets were used: 1) all forty-five general features, 2) all twenty-one symmetric features, 3) the optimal general feature subset obtained by using RFECV, and 4) the optimal symmetric feature subset obtained by using RFECV. The best classification result was obtained by RF-RFECV with an RF classifier derived from the symmetric features (accuracy: 96.01%). The result proved that the stroke severity classification performance increased when symmetric gait data and the RFECV technique were applied. The findings of this study can help clinicians diagnose the stroke severity experienced by patients based on information obtained using ML technology.https://ieeexplore.ieee.org/document/9932572/Machine learningassessment of stroke severitysymmetric gait datafeature selectionrehabilitation |
| spellingShingle | Joohwan Sung Sungmin Han Heesu Park Soree Hwang Song Joo Lee Jong Woong Park Inchan Youn Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation IEEE Access Machine learning assessment of stroke severity symmetric gait data feature selection rehabilitation |
| title | Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation |
| title_full | Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation |
| title_fullStr | Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation |
| title_full_unstemmed | Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation |
| title_short | Classification of Stroke Severity Using Clinically Relevant Symmetric Gait Features Based on Recursive Feature Elimination With Cross-Validation |
| title_sort | classification of stroke severity using clinically relevant symmetric gait features based on recursive feature elimination with cross validation |
| topic | Machine learning assessment of stroke severity symmetric gait data feature selection rehabilitation |
| url | https://ieeexplore.ieee.org/document/9932572/ |
| work_keys_str_mv | AT joohwansung classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation AT sungminhan classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation AT heesupark classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation AT soreehwang classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation AT songjoolee classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation AT jongwoongpark classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation AT inchanyoun classificationofstrokeseverityusingclinicallyrelevantsymmetricgaitfeaturesbasedonrecursivefeatureeliminationwithcrossvalidation |