Developing an Electronic System for Analyzing and Diagnosing X-Ray Images to Classify Bone Fractures Using Machine Learning Algorithms

Abstract

Artificial Intelligence (AI) has become a powerful tool in medical imaging, improving diagnostic accuracy and reducing human errors. X-ray images are widely used to diagnose bone fractures caused by accidents, aging, and osteoporosis; however, manual interpretation is often time-consuming and prone to inaccuracies, especially in subtle fracture cases. This study proposes an intelligent machine learning–based system for automated bone fracture detection from X-ray images. A descriptive-analytical methodology was adopted, and the system was designed using the Waterfall Model. The system uses Python, Jupyter, and Google Colab. Two classification algorithms, Support Vector Machine (SVM) and K-Nearest Neighbors (KNN), were trained using a dataset containing fractured and non-fractured bone images after applying image preprocessing and feature extraction techniques. Experimental results showed that the SVM model outperformed the KNN model, achieving an accuracy of 83.36% compared to 82.86%. Additionally, the SVM model reached an accuracy of 96% when evaluated on a balanced test dataset, compared to 52% for the KNN model. These results demonstrate the effectiveness of the proposed system in improving classification and highlight the efficiency of artificial intelligence in supporting bone fracture diagnosis, thus improving the quality of healthcare and reducing the burden on radiologists.