Knee osteoarthritis (OA) is one of the leading causes of disability among people aged 65 years and over in Australia. Individuals with knee osteoarthritis suffer from pain, stiffness and physical disability which consequently lead to a loss of functional independence. Knee replacement is a common surgical procedure used for the management of knee osteoarthritis. Knee replacement provides pain relief and improves physical function and quality of life for patients who suffer from osteoarthritis
Quantitative measures of gait can aid in the identification of potential fallers and predict functional status. Since, normal walking patterns are adversely affected by lower extremity joint disease; spatio-temporal parameters have clinical relevance in the assessment of motor pathologies particularly in orthopaedics. Spatio-temporal gait parameters, therefore, have been frequently used in a clinical setting.
Knee replacement surgery has been reported to improve the gait patterns of patients with osteoarthritis. However gait dysfunction, including gait symmetry may still persist after the surgery. Quantitative measures of gait such as spatio-temporal measures may be used as markers of the integrity of a person's locomotor ability and should be monitored after surgical intervention. Since gait dysfunction can lead to reduced physical activity levels, mobility and independence, an understanding how gait patterns of patients with knee osteoarthritis and those who undergo unilateral knee replacement differs from normal may help target pre and postoperative physical therapy for improving and preventing knee osteoarthritis.
In this paper, we investigated the automated recognition of subjects with osteoarthritis using the Support Vector Machine (SVM) based on spatio-temporal gait parameters. We then employed the SVM to assess the gait pattern of patients after knee replacement surgery. SVMs are powerful nonlinear classifiers based on statistical learning theory which have been successfully used in various pattern recognition problems. Our objective was to investigate if these variables can discriminate the pathology from the healthy subjects and to determine the subset of variables that best describe OA gait. Furthermore, we investigated whether the SVM can assess any gait improvement 2 months following surgical intervention. In the following, section 2 describes our data collection process and gives an overview of the SVM formulation. Our experimental results and discussion are contained in section 3 and 4 respectively.
Knee osteoarthritis (OA) is one of the leading causes of disability among people aged 65 years and over in Australia. Individuals with knee osteoarthritis suffer from pain, stiffness and physical disability which consequently lead to a loss of functional independence. Knee replacement is a common surgical procedure used for the management of knee osteoarthritis. Knee replacement provides pain relief and improves physical function and quality of life for patients who suffer from osteoarthritisQuantitative measures of gait can aid in the identification of potential fallers and predict functional status. Since, normal walking patterns are adversely affected by lower extremity joint disease; spatio-temporal parameters have clinical relevance in the assessment of motor pathologies particularly in orthopaedics. Spatio-temporal gait parameters, therefore, have been frequently used in a clinical setting.Knee replacement surgery has been reported to improve the gait patterns of patients with osteoarthritis. However gait dysfunction, including gait symmetry may still persist after the surgery. Quantitative measures of gait such as spatio-temporal measures may be used as markers of the integrity of a person's locomotor ability and should be monitored after surgical intervention. Since gait dysfunction can lead to reduced physical activity levels, mobility and independence, an understanding how gait patterns of patients with knee osteoarthritis and those who undergo unilateral knee replacement differs from normal may help target pre and postoperative physical therapy for improving and preventing knee osteoarthritis.In this paper, we investigated the automated recognition of subjects with osteoarthritis using the Support Vector Machine (SVM) based on spatio-temporal gait parameters. We then employed the SVM to assess the gait pattern of patients after knee replacement surgery. SVMs are powerful nonlinear classifiers based on statistical learning theory which have been successfully used in various pattern recognition problems. Our objective was to investigate if these variables can discriminate the pathology from the healthy subjects and to determine the subset of variables that best describe OA gait. Furthermore, we investigated whether the SVM can assess any gait improvement 2 months following surgical intervention. In the following, section 2 describes our data collection process and gives an overview of the SVM formulation. Our experimental results and discussion are contained in section 3 and 4 respectively.
การแปล กรุณารอสักครู่..
