Automatic Estimation of Osteoporotic Fracture Cases by Using Ensemble Learning Approaches
Niyazi Kilic1, Erkan Hosgormez2
1Engineering Faculty, Electrical and Electronics Department, Istanbul University, 34320, Avcilar, Istanbul, Turkey. niyazik@istanbul.edu.tr.
Journal of Medical Systems
|December 15, 2015
Summary
This study shows ensemble learning accurately detects osteoporosis using bone densitometry. Machine learning models achieved 98.85% accuracy, predicting fractures from easily measured physical parameters.
Area of Science:
- Biomedical Engineering
- Machine Learning
- Osteoporosis Research
Background:
- Osteoporotic fractures pose a significant health risk.
- Accurate detection of osteoporosis is crucial for fracture prevention.
- Current diagnostic methods may have limitations.
Purpose of the Study:
- To investigate the effectiveness of ensemble learning methods for osteoporotic fracture detection.
- To evaluate the impact of physical bone densitometry parameters on classification accuracy.
- To develop a non-invasive system for early warning of bone fractures.
Main Methods:
- Six feature set models were created using various physical bone densitometry parameters.
- Ensemble learning techniques including bagging, gradient boosting, and random subspace (RSM) were employed.
- Instance-based learning (IBk) and random forest (RF) classifiers were applied to the feature sets.
- Patients were classified into osteoporosis, osteopenia, and control groups.
Main Results:
- The highest classification accuracy of 98.85% was achieved using a combination of five Bone Mineral Density (BMD) and five T-score values (model 6).
- The Random Subspace Method (RSM) combined with the Random Forest (RF) classifier demonstrated superior performance.
- Ensemble classifiers effectively distinguished between osteoporosis, osteopenia, and healthy individuals.
Conclusions:
- Ensemble learning, particularly RSM-RF with specific bone densitometry parameters, shows high potential for accurate osteoporotic fracture detection.
- The proposed system offers a non-invasive approach to identify at-risk patients, enabling early warnings before fractures occur.
- Utilizing easily measurable physical parameters can significantly aid in the early diagnosis and management of osteoporosis.
Related Concept Videos
01:18Classification of Bones
13.3K
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 and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
13.3K
01:27Fractures: Bone Repair
6.6K
Treatment for a fracture is based on the type of break, the bone affected, and the patient's age.
Minor fractures with no bone displacement are treated by immobilizing the fractured bone using a cast or splint. However, in the case of fractures with displaced bones, the broken bones are repositioned before immobilization to ensure successful healing without deformation and loss of function. The realignment of fractured bone ends is performed through a process called reduction. If the...
Minor fractures with no bone displacement are treated by immobilizing the fractured bone using a cast or splint. However, in the case of fractures with displaced bones, the broken bones are repositioned before immobilization to ensure successful healing without deformation and loss of function. The realignment of fractured bone ends is performed through a process called reduction. If the...
6.6K