Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model
Objective To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed. Methods A total of 84 KOA patients and 97 normal par...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Academy of Rehabilitation Medicine
2020-12-01
|
| Series: | Annals of Rehabilitation Medicine |
| Subjects: | |
| Online Access: | http://www.e-arm.org/upload/pdf/arm-20071.pdf |
| _version_ | 1827835434366926848 |
|---|---|
| author | Jung Ho Yang Jae Hyeon Park Seong-Ho Jang Jaesung Cho |
| author_facet | Jung Ho Yang Jae Hyeon Park Seong-Ho Jang Jaesung Cho |
| author_sort | Jung Ho Yang |
| collection | DOAJ |
| description | Objective To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed. Methods A total of 84 KOA patients and 97 normal participants were recruited. KOA patients were clustered into three groups according to the Kellgren-Lawrence (K-L) grading system. All subjects completed gait trials under the same experimental conditions. Machine learning-based classification using the support vector machine (SVM) classifier was performed to classify KOA patients and the severity of KOA. Logistic regression analysis was also performed to compare the results in classifying KOA patients with machine learning method. Results In the classification between KOA patients and normal subjects, the accuracy of classification was higher in machine learning method than in logistic regression analysis. In the classification of KOA severity, accuracy was enhanced through the feature selection process in the machine learning method. The most significant gait feature for classification was flexion and extension of the knee in the swing phase in the machine learning method. Conclusion The machine learning method is thought to be a new approach to complement conventional logistic regression analysis in the classification of KOA patients. It can be clinically used for diagnosis and gait correction of KOA patients. |
| first_indexed | 2024-03-12T06:09:27Z |
| format | Article |
| id | doaj.art-4192d7bb1a3443489bb2b439cca48a2a |
| institution | Directory Open Access Journal |
| issn | 2234-0645 2234-0653 |
| language | English |
| last_indexed | 2024-03-12T06:09:27Z |
| publishDate | 2020-12-01 |
| publisher | Korean Academy of Rehabilitation Medicine |
| record_format | Article |
| series | Annals of Rehabilitation Medicine |
| spelling | doaj.art-4192d7bb1a3443489bb2b439cca48a2a2023-09-03T03:15:24ZengKorean Academy of Rehabilitation MedicineAnnals of Rehabilitation Medicine2234-06452234-06532020-12-0144641542710.5535/arm.200714186Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression ModelJung Ho Yang0Jae Hyeon Park1Seong-Ho Jang2Jaesung Cho3 Department of Rehabilitation Medicine, Hanyang University College of Medicine, Seoul, Korea Department of Rehabilitation Medicine, Hanyang University Guri Hospital, Hanyang University College of Medicine, Guri, Korea Department of Rehabilitation Medicine, Hanyang University College of Medicine, Seoul, Korea Korea Orthopedics & Rehabilitation Engineering Center, Incheon, KoreaObjective To present new classification methods of knee osteoarthritis (KOA) using machine learning and compare its performance with conventional statistical methods as classification techniques using machine learning have recently been developed. Methods A total of 84 KOA patients and 97 normal participants were recruited. KOA patients were clustered into three groups according to the Kellgren-Lawrence (K-L) grading system. All subjects completed gait trials under the same experimental conditions. Machine learning-based classification using the support vector machine (SVM) classifier was performed to classify KOA patients and the severity of KOA. Logistic regression analysis was also performed to compare the results in classifying KOA patients with machine learning method. Results In the classification between KOA patients and normal subjects, the accuracy of classification was higher in machine learning method than in logistic regression analysis. In the classification of KOA severity, accuracy was enhanced through the feature selection process in the machine learning method. The most significant gait feature for classification was flexion and extension of the knee in the swing phase in the machine learning method. Conclusion The machine learning method is thought to be a new approach to complement conventional logistic regression analysis in the classification of KOA patients. It can be clinically used for diagnosis and gait correction of KOA patients.http://www.e-arm.org/upload/pdf/arm-20071.pdfknee osteoarthritisgait analysisknee jointseveritymachine learning |
| spellingShingle | Jung Ho Yang Jae Hyeon Park Seong-Ho Jang Jaesung Cho Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model Annals of Rehabilitation Medicine knee osteoarthritis gait analysis knee joint severity machine learning |
| title | Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model |
| title_full | Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model |
| title_fullStr | Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model |
| title_full_unstemmed | Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model |
| title_short | Novel Method of Classification in Knee Osteoarthritis: Machine Learning Application Versus Logistic Regression Model |
| title_sort | novel method of classification in knee osteoarthritis machine learning application versus logistic regression model |
| topic | knee osteoarthritis gait analysis knee joint severity machine learning |
| url | http://www.e-arm.org/upload/pdf/arm-20071.pdf |
| work_keys_str_mv | AT junghoyang novelmethodofclassificationinkneeosteoarthritismachinelearningapplicationversuslogisticregressionmodel AT jaehyeonpark novelmethodofclassificationinkneeosteoarthritismachinelearningapplicationversuslogisticregressionmodel AT seonghojang novelmethodofclassificationinkneeosteoarthritismachinelearningapplicationversuslogisticregressionmodel AT jaesungcho novelmethodofclassificationinkneeosteoarthritismachinelearningapplicationversuslogisticregressionmodel |