Role of Artificial Intelligence in Minimizing Missed and Undiagnosed Fractures Among Trainee Residents
Mir Sadat-Ali,1 Hussain Khalil Al Omar,2 Muath M Alneghaimshi,2 Abdallah M AlHossan,3 Abdullah M Baragabh2 1Department of Orthopaedic Surgery, Haifa Medical Complex, Alkhobar, Saudi Arabia; 2King Fahad Military Medical Complex, Ministry of Defense Health Services, Dhahran, Saudi Arabia; 3King Fahad...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2025-07-01
|
| Series: | Journal of Multidisciplinary Healthcare |
| Subjects: | |
| Online Access: | https://www.dovepress.com/role-of-artificial-intelligence-in-minimizing-missed-and-undiagnosed-f-peer-reviewed-fulltext-article-JMDH |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Mir Sadat-Ali,1 Hussain Khalil Al Omar,2 Muath M Alneghaimshi,2 Abdallah M AlHossan,3 Abdullah M Baragabh2 1Department of Orthopaedic Surgery, Haifa Medical Complex, Alkhobar, Saudi Arabia; 2King Fahad Military Medical Complex, Ministry of Defense Health Services, Dhahran, Saudi Arabia; 3King Fahad Military Medical Complex, Ministry of Defense Health Services, Dhahran and Alfaisal University, Riyadh, Saudi ArabiaCorrespondence: Mir Sadat-Ali, Haifa Medical Complex, 7200 King Khalid Road, AlKhozama, Alklhobar, 32424, Saudi Arabia, Tel +966505848281, Email drsadat@hotmail.comBackground and Objectives: Traumatic Fractures and dislocations are missed up to 10% at the first line of defense in the emergency room and by the junior orthopedic residents in training. This review was done to evaluate the accuracy of AI-assisted fracture detection and to compare with the residents in training.Methods: We searched all related electronic databases for English language literature between January 2015 and July 2023, Pub Med, Scopus, Web of Science, Cochrane Central Ovid Medline, Ovid Embase, EBSCO Cumulative Index to Allied Health Literature, with keywords of Artificial Intelligence, fractures, dislocations, X-rays, radiographs and missed diagnosis. The data extracted included a number of patients/images studied, site of fractures analyzed, algorithms used, the accuracy of the report based on the algorithm, sensitivity, and specificity, area under the curve (AUC), comparison between the algorithm, junior orthopedic resident, emergency physicians, and board certified radiologists.Results: Twenty-seven publications fulfilled our objectives and were analyzed in detail. Ninety-two thousand two hundred and thirty-six images were analyzed for fractures, which showed that the overall accuracy of the correct diagnosis was 90.35± 6.88%, sensitivity 90.08± 8.2%, specificity 90.16± 7 and AUC was 0.931± 0.06. The accuracy of the AI model was 94.24± 4.19, and that of orthopedic resident was 85.18± 7.01 (P value of < 0.0001), with sensitivity 92.15± 7.12 versus 86.38± 7.6 (P< 0.0001) and specificity of 93.77± 4.03 versus 87.05± 12.9 (P< 0.0001). A single study compared 1703 hip fracture images between the AI model versus orthopedic resident and board-certified radiologist and found the accuracy to be 98% versus 87% and 92% (P value of < 0.0001).Conclusion: This review accentuates AI’s potential for accurate diagnosis of fractures. We believe the AI algorithm should be incorporated in the emergency rooms where trainee residents and junior orthopedic residents could routinely use AI so that the incidence of missed fractures can be curtailed.Keywords: artificial intelligence, diagnostic imaging, fractures missed diagnosis, X-rays |
|---|---|
| ISSN: | 1178-2390 |