Biometric Recognition and Rehabilitation Assessment of Lower Extremity Sports Injury Based on Gait Touch Information
Overview
- Phase
- Not Applicable
- Intervention
- Not specified
- Conditions
- Sport Injury
- Sponsor
- Peking University Third Hospital
- Enrollment
- 550
- Locations
- 1
- Primary Endpoint
- walking speed
- Last Updated
- 5 years ago
Overview
Brief Summary
The current common clinical methods cannot truly reflect the biomechanical status of the knee joint. Based on the foot-knee coupling mechanism, the simple and practical dynamic gait touch information provided by the 3D force platform are closely related to the knee biomechanics. The purpose of this study is to investigate the disease feature recognition, computer-aided diagnosis and rehabilitation assessment based on the gait touch information related to lower limb injuries.
Detailed Description
Background: The current common clinical methods cannot truly reflect the biomechanical status of the knee joint. The three-dimensional gait analysis is the gold standard, but it is difficult to apply clinically. There is an urgent need for a clinically practical method to quantitatively evaluate the biomechanics of the knee joint under dynamic weight bearing. Methods: 50 healthy volunteers, 450 sports injuries patients (including hip, knee, and ankle joint diseases) and 50 patients with degenerative osteoarthritis were recruited. 55 passive reflective markers were placed bilaterally on the body. Lower extremity kinematics and dynamic plantar pressure during walking, jogging were collected. Outcome evaluation indicators and statistical methods: The following indicators use repeated measurement two-factor analysis of variance: the left and right sides, different rehabilitation times are used as repeated measurement variables, to analyze the biomechanical changes of the lower limb joint biomechanics and gait touch information. A variety of machine learning methods (such as PCA, SVM, CNN, etc.) are used to analyze, and select the appropriate algorithm and parameters according to the learning effect. Finally, this study will establish a machine learning models for computer-aided diagnosis, treatment, and rehabilitation assessment.
Investigators
Eligibility Criteria
Inclusion Criteria
- •patients with a certain sports injury (soft tissue injury or degenerative osteoarthritis) of a joint of the lower limb (hip or knee or ankle or foot).
Exclusion Criteria
- •Cognitive impairment
- •other injuries affecting movement performance.
Outcomes
Primary Outcomes
walking speed
Time Frame: On the day of enrollment.
Three-dimensional gait analysis system and plantar pressure were used during walking.
ground reaction force
Time Frame: On the day of enrollment.
Three-dimensional gait analysis system and plantar pressure were used during walking.
knee flexion angle
Time Frame: On the day of enrollment.
Three-dimensional gait analysis system and plantar pressure were used during walking.
the moment of knee extension in the gait cycle
Time Frame: On the day of enrollment.
Three-dimensional gait analysis system and plantar pressure were used during walking.
Secondary Outcomes
- The International Knee Documentation Committee (IKDC) score(On the day of enrollment.)