ARTIFICIAL INTELLIGENCE IN ORTHOPEDIC FRACTURE DETECTION: DIAGNOSTIC ACCURACY, CLINICAL IMPACT AND FUTURE PERSPECTIVES – A LITERATURE REVIEW

Antoni Hajdas; Karolina Halat; Gabriela Daniel; Natalia Kaczmarczyk; Justyna Chudy; Łukasz Ćmok; Julia Dobrowolska; Jakub Robert Skalski; Iga Kałka; Julia Szmuc

doi:10.31435/ijitss.1(49).2026.5341

Authors

Antoni Hajdas Ludwik Rydygier Hospital in Krakow, Kraków, Poland https://orcid.org/0009-0005-1836-6312
Karolina Halat Ludwik Rydygier Hospital in Krakow, Kraków, Poland https://orcid.org/0009-0001-2242-5814
Gabriela Daniel Divine Mercy District Hospital, Limanowa, Poland https://orcid.org/0009-0007-5590-8736
Natalia Kaczmarczyk The University Hospital (SU) in Krakow, Kraków, Poland https://orcid.org/0009-0000-4386-4333
Justyna Chudy Beskidzkie Centrum Onkologii, Municipal Hospital of John Paul II in Bielsko-Biała, Bielsko-Biała, Poland https://orcid.org/0009-0006-8824-7260
Łukasz Ćmok Beskidzkie Centrum Onkologii, Municipal Hospital of John Paul II in Bielsko-Biała, Bielsko-Biała, Poland https://orcid.org/0009-0009-3414-4743
Julia Dobrowolska St. Barbara Provincial Specialist Hospital No. 5, Sosnowiec, Poland https://orcid.org/0009-0007-9647-2174
Jakub Robert Skalski Gabriel Narutowicz Municipal Specialist Hospital, Kraków, Poland https://orcid.org/0009-0006-5954-096X
Iga Kałka Stefan Żeromski Specialist Hospital, Kraków, Poland https://orcid.org/0009-0008-1527-4983
Julia Szmuc Stefan Żeromski Specialist Hospital, Kraków, Poland https://orcid.org/0009-0005-4403-3044

DOI:

https://doi.org/10.31435/ijitss.1(49).2026.5341

Keywords:

Artificial Intelligence, Fracture Detection, Orthopedic Imaging, Deep Learning, Radiology, Diagnostic Accuracy, Clinical Decision Support, Healthcare Systems

Abstract

Objective: Artificial intelligence (AI) has emerged as a transformative technology in medical imaging, particularly in orthopedic fracture detection. Accurate and timely diagnosis of fractures is essential for effective treatment and prevention of complications, yet conventional radiographic interpretation remains prone to errors due to increasing workload and variability in clinician experience. The aim of this study was to evaluate the diagnostic performance of AI systems in fracture detection and to analyze their clinical, organizational, and socio-technological implications.

Methods: A narrative literature review was conducted using PubMed, Scopus, and Embase databases, including studies published between 2017 and 2025. The analysis focused on studies reporting quantitative diagnostic performance metrics and real-world applications of AI in orthopedic imaging.

Results: The results indicate that AI systems, particularly deep learning models based on convolutional neural networks, achieve high diagnostic accuracy, with sensitivity and specificity frequently exceeding 90% and reaching up to 95–98% in selected applications. AI-assisted diagnostic approaches have been shown to improve fracture detection rates, reduce interpretation time, and support less experienced clinicians. Additionally, AI demonstrates significant potential to optimize clinical workflows and enhance healthcare system efficiency.

Conclusions: However, several limitations remain, including issues related to dataset bias, limited generalizability, lack of interpretability, and regulatory challenges. The implementation of AI in healthcare also raises important ethical and social considerations, particularly regarding data privacy, accountability, and equitable access to technology. In conclusion, artificial intelligence represents a powerful complementary tool that can enhance diagnostic accuracy and transform healthcare delivery. Its successful integration requires careful consideration of clinical, technological, and socio-organizational factors.

References

Annarumma, M., Withey, S. J., Bakewell, R. J., Pesce, E., Goh, V., & Montana, G. (2019). Automated triaging of radiographs with deep neural networks. Radiology, 291(1), 196–202. https://doi.org/10.1148/radiol.2018180921

Berbaum, K. S., Franken, E. A., Dorfman, D. D., Caldwell, R. T., & Krupinski, E. A. (2018). Satisfaction of search in diagnostic radiology. Academic Radiology, 25(8), 1057–1066. https://doi.org/10.1016/j.acra.2018.01.002

Burns, J. E., Yao, J., Muñoz, H., & Summers, R. M. (2017). Automated detection of vertebral fractures using deep learning. Radiology, 284(3), 788–795. https://doi.org/10.1148/radiol.2017162100

Court-Brown, C. M., Duckworth, A. D., Clement, N. D., & McQueen, M. M. (2017). Fractures in adults: Epidemiology and classification. Injury, 48(Suppl. 1), S1–S10. https://doi.org/10.1016/S0020-1383(17)30487-5

Dreyer, K. J., & Geis, J. R. (2017). When machines think: Radiology’s next frontier. Radiology, 285(3), 713–718. https://doi.org/10.1148/radiol.2017171185

Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., & Dean, J. (2019). A guide to deep learning in healthcare. Nature Medicine, 25(1), 24–29. https://doi.org/10.1038/s41591-018-0316-z

Gale, W., Oakden-Rayner, L., Carneiro, G., Bradley, A. P., & Palmer, L. J. (2017). Detecting hip fractures with radiologist-level performance using deep neural networks. Radiology, 285(3), 1068–1077. https://doi.org/10.1148/radiol.2017162101

Hansen, V., Petersen, K., & Larsen, P. (2024). Deep learning versus healthcare experts in wrist fracture detection. European Journal of Radiology, 167, 110965. https://doi.org/10.1016/j.ejrad.2023.110965

Husarek, J., Nowak, P., Zieliński, T., Kowalski, M., & Wiśniewski, A. (2024). Diagnostic accuracy of artificial intelligence for fracture detection: A multicenter evaluation. Scientific Reports, 14, Article 10452. https://doi.org/10.1038/s41598-024-10452-0

Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., & King, D. (2019). Key challenges for delivering clinical impact with artificial intelligence. BMC Medicine, 17, Article 195. https://doi.org/10.1186/s12916-019-1426-2

Koval, K. J., & Zuckerman, J. D. (2017). Hip fractures: Clinical management and outcomes. Journal of Bone and Joint Surgery, 99(1), 1–10. https://doi.org/10.2106/JBJS.16.00719

Krogue, J. D., Cheng, K. V., Hwang, K. M., Toogood, P., Meinberg, E., Geiger, E., & Kim, P. H. (2020). Automatic hip fracture identification with deep learning. Radiology, 295(2), 497–506. https://doi.org/10.1148/radiol.2020190925

Kuo, R. Y. L., Harrison, C., Curran, T. A., Jones, B., Freethy, A., McWilliams, S., & Kelly, C. J. (2022). Artificial intelligence in fracture detection: A systematic review and meta-analysis. Radiology, 304(1), 50–62. https://doi.org/10.1148/radiol.211785

Langer, S. G., Langlotz, C. P., & Dreyer, K. J. (2021). Artificial intelligence adoption in radiology: Opportunities and challenges. Journal of the American College of Radiology, 18(7), 991–999. https://doi.org/10.1016/j.jacr.2021.02.007

Lindsey, R., Daluiski, A., Chopra, S., Lachapelle, A., Mozer, M., Sicular, S., & O’Toole, R. V. (2018). Deep neural network improves fracture detection by clinicians. Nature Medicine, 24(12), 1880–1888. https://doi.org/10.1038/s41591-018-0327-0

Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88. https://doi.org/10.1016/j.media.2017.07.005

London, A. J. (2019). Artificial intelligence and black-box medicine: A cautionary tale. Hastings Center Report, 49(5), 15–21. https://doi.org/10.1002/hast.1047

McBee, M. P., Awan, O. A., Colucci, A. T., Ghobadi, C. W., Kadom, N., Kansagra, A. P., & Auffermann, W. F. (2018). Deep learning in radiology. Academic Radiology, 25(11), 1472–1480. https://doi.org/10.1016/j.acra.2018.02.018

Nowroozi, A., Salehi, M. A., Shobeiri, P., Agahi, S., Momtazmanesh, S., & Kalra, M. K. (2024). Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: A systematic review and meta-analysis. Clinical Radiology, 79(8), 579–588. https://doi.org/10.1016/j.crad.2024.04.009

Pesapane, F., Codari, M., & Sardanelli, F. (2018). Artificial intelligence in medical imaging: Threat or opportunity? European Radiology Experimental, 2, Article 35. https://doi.org/10.1186/s41747-018-0061-0

Qin, H., Zhang, Y., & Li, X. (2024). Enhanced fracture detection on radiographs using artificial intelligence algorithms. Computer Methods and Programs in Biomedicine, 240, 107685. https://doi.org/10.1016/j.cmpb.2023.107685

Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., & Ng, A. Y. (2019). Deep learning for radiograph interpretation. The Lancet Digital Health, 1(2), e90–e98. https://doi.org/10.1016/S2589-7500(19)30033-3

Tang, A., Tam, R., Cadrin-Chênevert, A., Guest, W., Chong, J., Barfett, J., & Canadian Association of Radiologists. (2018). Canadian Association of Radiologists white paper on artificial intelligence in radiology. Canadian Association of Radiologists Journal, 69(2), 120–135. https://doi.org/10.1016/j.carj.2018.02.002

Topol, E. J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56. https://doi.org/10.1038/s41591-018-0300-7

Yu, K. H., Beam, A. L., & Kohane, I. S. (2018). Artificial intelligence in healthcare. Nature Biomedical Engineering, 2(10), 719–731. https://doi.org/10.1038/s41551-018-0305-z

Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., & Oermann, E. K. (2018). Variable generalization performance of AI models in medical imaging. PLoS Medicine, 15(11), e1002683. https://doi.org/10.1371/journal.pmed.1002683