Related Experiment Video
Updated: Jun 8, 2026
08:52
Software-Assisted Quantitative Measurement of Osteoarthritic Subchondral Bone Thickness
Published on: March 18, 2022
A fuzzy decision tree-based SVM classifier for assessing osteoarthritis severity using ground reaction force
S P Moustakidis1, J B Theocharis, G Giakas
1Aristotle University of Thessaloniki, Department of Electrical and Computer Engineering, Division of Electronics and Computer. Eng., 54124 Thessaloniki, Greece.
Medical Engineering & Physics
|September 30, 2010
Summary
A new fuzzy decision tree-based SVM classifier effectively distinguishes knee osteoarthritis (OA) gait patterns and severity using 3-D ground reaction forces. This method enhances classification accuracy and reduces model complexity for better OA diagnosis.
Area of Science:
- Biomechanics
- Machine Learning
- Medical Diagnostics
Background:
- Osteoarthritis (OA) diagnosis relies on clinical assessment and imaging, often detecting disease progression late.
- Analyzing gait patterns using 3-D ground reaction forces (GRF) offers a non-invasive method for early OA detection and severity assessment.
- Current classification methods may struggle with the complexity and variability of gait data, leading to potential overfitting and reduced accuracy.
Purpose of the Study:
- To propose a novel fuzzy decision tree-based Support Vector Machine (FDT-SVM) classifier.
- To differentiate between asymptotic (AS) and osteoarthritis (OA) knee gait patterns.
- To investigate the severity of OA using 3-D GRF measurements.
Main Methods:
- Developed an FDT-SVM classifier integrating feature selection (FS) and class grouping (CG) using fuzzy partition vectors (FPV).
- Employed a fuzzy complementary criterion (FuzCoC) for iterative feature selection and a novel Wavelet Packet (WP) decomposition for feature extraction from GRF data.
- Validated the method using statistical metrics from confusion matrices, including sensitivity, specificity, and total classification accuracy, and analyzed individual GRF component impacts.
Main Results:
- The FDT-SVM classifier demonstrated high accuracy in distinguishing AS and OA knee gait patterns.
- The integrated FS and CG techniques effectively reduced classifier complexity and mitigated overfitting.
- Comparative analysis showed the proposed approach outperforms existing techniques in classifying OA severity and gait patterns.
Conclusions:
- The novel FDT-SVM classifier provides an effective and accurate method for analyzing knee OA gait patterns and severity from 3-D GRF data.
- The integrated fuzzy techniques enhance classification performance and model robustness.
- This approach holds promise for improved non-invasive diagnosis and monitoring of knee osteoarthritis.
Related Concept Videos
01:09Functional Classification of Joints
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An immobile...
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An immobile...
01:18Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...