USE OF AN ARTIFICIAL INTELLIGENCE ASSISTANT FOR DETECTING BONE FRACTURES ON RADIOGRAPHIC IMAGES: DIAGNOSTIC ACCURACY AND DECISION SUPPORT

Authors

  • Qiyamova Nasiba Bozor qizi student of Samarkand state medical university Author
  • Hudoynazarov Fayyozbek Muhammadiyevich student of Samarkand state medical university Author
  • Otamurodova Xurshidabonu Baxtiyor qizi student of Samarkand state medical university Author

Keywords:

Keywords: artificial intelligence; radiography; machine learning; deep learning; bone fracture; computer-aided diagnosis; diagnostic accuracy; radiologist; clinical decision support

Abstract

Artificial intelligence (AI) is increasingly being incorporated into medical imaging, particularly radiography, where large numbers of examinations must be interpreted accurately and efficiently. Fracture detection is an important application because subtle cortical breaks, nondisplaced fractures, and overlapping anatomical structures may be difficult to recognize on plain radiographs. This article reviews the role of AI assistants in radiographic fracture detection, the principles of image analysis, potential diagnostic benefits, limitations, and requirements for clinical implementation. Published evidence indicates that modern AI algorithms can achieve high sensitivity and specificity for fracture detection in selected datasets, although performance varies according to anatomical region, image quality, prevalence, algorithm architecture, and the characteristics of the patient population. AI should therefore be regarded as a clinical decision-support tool rather than an autonomous replacement for radiologists or other qualified clinicians. Proper validation, human oversight, data governance, and monitoring are essential for safe implementation.

References

1.Nowroozi A, Salehi MA, Shobeiri P, et al. Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis. Clinical Radiology. 2024;79(8):579–588.

2.Suen K, et al. Accuracy of wrist fracture detection on radiographs by artificial intelligence compared to human clinicians: a systematic review and meta-analysis. European Journal of Radiology. 2024;174:111593.

3.World Health Organization. Ethics and Governance of Artificial Intelligence for Health. Geneva: World Health Organization; 2021.

4.World Health Organization. Ethics and Governance of Artificial Intelligence for Health: WHO Guidance Executive Summary. Geneva: World Health Organization; 2021.

5.U.S. Food and Drug Administration. Artificial Intelligence-Enabled Medical Devices. Center for Devices and Radiological Health. 2026.

6.U.S. Food and Drug Administration. Artificial Intelligence Program: Research on AI/ML-Based Medical Devices. Center for Devices and Radiological Health.

7.U.S. Food and Drug Administration. Regulatory Evaluation of New Artificial Intelligence Uses for Improving and Automating Medical Practices. Center for Devices and Radiological Health.

8.U.S. Food and Drug Administration. Artificial Intelligence and Machine Learning in Software as a Medical Device. Regulatory science and medical-device guidance resources.

Downloads

Published

2026-09-23