Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers
Objective Ankle injuries in delivery workers (DWs) are often caused by trips, and high recurrence rates of ankle sprains are related to chronic ankle instability (CAI). Heel rise requires joint angles and moments similar to those of the terminal stance phase of walking that the foot supinates. Thus,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2024-02-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076241235116 |
| _version_ | 1797292620945293312 |
|---|---|
| author | Ui-jae Hwang Oh-yun Kwon Jun-hee Kim Gyeong-tae Gwak |
| author_facet | Ui-jae Hwang Oh-yun Kwon Jun-hee Kim Gyeong-tae Gwak |
| author_sort | Ui-jae Hwang |
| collection | DOAJ |
| description | Objective Ankle injuries in delivery workers (DWs) are often caused by trips, and high recurrence rates of ankle sprains are related to chronic ankle instability (CAI). Heel rise requires joint angles and moments similar to those of the terminal stance phase of walking that the foot supinates. Thus, our study aimed to develop, determine, and compare the predictive performance of statistical machine learning models to classify DWs with and without CAI using ankle kinematics during heel rise. Methods In total, 203 DWs were screened for eligibility. Seven predictors were included in our study (age, work duration, body mass index, calcaneal stance position angle [CSPA] in the initial and terminal positions during heel rise, calcaneal movement during heel rise [CM HR ], and plantar flexion angle during heel rise). Six machine learning algorithms, including logistic regression, decision tree, AdaBoost, Extreme Gradient boosting machines, random forest, and support vector machine, were trained. Results The random forest model (area under the curve [AUC], 0.967 [excellent]; F1, 0.889; accuracy, 0.925) confirmed the best predictive performance in the test datasets among the six machine learning models. For Shapley Additive Explanations, old age, low CMHR, high CSPA in the initial position, high PFA, long work duration, low CSPA in the terminal position, and high body mass index were the most important predictors of CAI in the random forest model. Conclusion Ankle kinematics during heel rise can be considered in the classification of DWs with and without CAI. |
| first_indexed | 2024-03-07T19:59:06Z |
| format | Article |
| id | doaj.art-783c4771b260453bafe72b20bcb1d598 |
| institution | Directory Open Access Journal |
| issn | 2055-2076 |
| language | English |
| last_indexed | 2024-03-07T19:59:06Z |
| publishDate | 2024-02-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj.art-783c4771b260453bafe72b20bcb1d5982024-02-28T11:03:28ZengSAGE PublishingDigital Health2055-20762024-02-011010.1177/20552076241235116Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workersUi-jae Hwang0Oh-yun Kwon1Jun-hee Kim2Gyeong-tae Gwak3 Department of Physical Therapy, College of Health Science, Laboratory of KEMA AI Research (KAIR), , Wonju, South Korea Department of Physical Therapy, College of Health Science, Laboratory of Kinetic Ergocise Based on Movement Analysis, , Wonju, South Korea Department of Physical Therapy, College of Health Science, Laboratory of KEMA AI Research (KAIR), , Wonju, South Korea Department of Physical Therapy, College of Health Science, Laboratory of KEMA AI Research (KAIR), , Wonju, South KoreaObjective Ankle injuries in delivery workers (DWs) are often caused by trips, and high recurrence rates of ankle sprains are related to chronic ankle instability (CAI). Heel rise requires joint angles and moments similar to those of the terminal stance phase of walking that the foot supinates. Thus, our study aimed to develop, determine, and compare the predictive performance of statistical machine learning models to classify DWs with and without CAI using ankle kinematics during heel rise. Methods In total, 203 DWs were screened for eligibility. Seven predictors were included in our study (age, work duration, body mass index, calcaneal stance position angle [CSPA] in the initial and terminal positions during heel rise, calcaneal movement during heel rise [CM HR ], and plantar flexion angle during heel rise). Six machine learning algorithms, including logistic regression, decision tree, AdaBoost, Extreme Gradient boosting machines, random forest, and support vector machine, were trained. Results The random forest model (area under the curve [AUC], 0.967 [excellent]; F1, 0.889; accuracy, 0.925) confirmed the best predictive performance in the test datasets among the six machine learning models. For Shapley Additive Explanations, old age, low CMHR, high CSPA in the initial position, high PFA, long work duration, low CSPA in the terminal position, and high body mass index were the most important predictors of CAI in the random forest model. Conclusion Ankle kinematics during heel rise can be considered in the classification of DWs with and without CAI.https://doi.org/10.1177/20552076241235116 |
| spellingShingle | Ui-jae Hwang Oh-yun Kwon Jun-hee Kim Gyeong-tae Gwak Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers Digital Health |
| title | Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers |
| title_full | Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers |
| title_fullStr | Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers |
| title_full_unstemmed | Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers |
| title_short | Classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers |
| title_sort | classification of chronic ankle instability using machine learning technique based on ankle kinematics during heel rise in delivery workers |
| url | https://doi.org/10.1177/20552076241235116 |
| work_keys_str_mv | AT uijaehwang classificationofchronicankleinstabilityusingmachinelearningtechniquebasedonanklekinematicsduringheelriseindeliveryworkers AT ohyunkwon classificationofchronicankleinstabilityusingmachinelearningtechniquebasedonanklekinematicsduringheelriseindeliveryworkers AT junheekim classificationofchronicankleinstabilityusingmachinelearningtechniquebasedonanklekinematicsduringheelriseindeliveryworkers AT gyeongtaegwak classificationofchronicankleinstabilityusingmachinelearningtechniquebasedonanklekinematicsduringheelriseindeliveryworkers |