دورية أكاديمية
Artificial intelligence improves resident detection of pediatric and young adult upper extremity fractures.
| العنوان: | Artificial intelligence improves resident detection of pediatric and young adult upper extremity fractures. |
|---|---|
| المؤلفون: | Zech JR; Department of Radiology, New York University Langone Health, 301 E 17th St, New York, NY, 10003, USA. jrzech@gmail.com., Ezuma CO; Department of Orthopedic Surgery, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA., Patel S; Department of Radiology, New York University Langone Health, 301 E 17th St, New York, NY, 10003, USA., Edwards CR; Department of Radiology, Columbia University Irving Medical Center, New York, NY, USA., Posner R; Department of Radiology, Columbia University Irving Medical Center, New York, NY, USA., Hannon E; Department of Pediatrics, Columbia University Irving Medical Center, New York, NY, USA., Williams F; Department of Pediatrics, Columbia University Irving Medical Center, New York, NY, USA., Lala SV; Department of Radiology, Columbia University Irving Medical Center, New York, NY, USA., Ahmad ZY; Department of Radiology, Columbia University Irving Medical Center, New York, NY, USA., Moy MP; Department of Radiology, Columbia University Irving Medical Center, New York, NY, USA., Wong TT; Department of Radiology, Columbia University Irving Medical Center, New York, NY, USA. |
| المصدر: | Skeletal radiology [Skeletal Radiol] 2024 May 02. Date of Electronic Publication: 2024 May 02. |
| Publication Model: | Ahead of Print |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Springer Verlag Country of Publication: Germany NLM ID: 7701953 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1432-2161 (Electronic) Linking ISSN: 03642348 NLM ISO Abbreviation: Skeletal Radiol Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: Berlin : Springer Verlag Original Publication: Berlin, New York, Springer International. |
| مستخلص: | Purpose: We wished to evaluate if an open-source artificial intelligence (AI) algorithm ( https://www.childfx.com ) could improve performance of (1) subspecialized musculoskeletal radiologists, (2) radiology residents, and (3) pediatric residents in detecting pediatric and young adult upper extremity fractures. Materials and Methods: A set of evaluation radiographs drawn from throughout the upper extremity (elbow, hand/finger, humerus/shoulder/clavicle, wrist/forearm, and clavicle) from 240 unique patients at a single hospital was constructed (mean age 11.3 years, range 0-22 years, 37.9% female). Two fellowship-trained musculoskeletal radiologists, three radiology residents, and two pediatric residents were recruited as readers. Each reader interpreted each case initially without and then subsequently 3-4 weeks later with AI assistance and recorded if/where fracture was present. Results: Access to AI significantly improved area under the receiver operator curve (AUC) of radiology residents (0.768 [0.730-0.806] without AI to 0.876 [0.845-0.908] with AI, P < 0.001) and pediatric residents (0.706 [0.659-0.753] without AI to 0.844 [0.805-0.883] with AI, P < 0.001) in identifying fracture, respectively. There was no evidence of improvement for subspecialized musculoskeletal radiology attendings in identifying fracture (AUC 0.867 [0.832-0.902] to 0.890 [0.856-0.924], P = 0.093). There was no evidence of difference between overall resident AUC with AI and subspecialist AUC without AI (resident with AI 0.863, attending without AI AUC 0.867, P = 0.856). Overall physician radiograph interpretation time was significantly lower with AI (38.9 s with AI vs. 52.1 s without AI, P = 0.030). Conclusion: An openly accessible AI model significantly improved radiology and pediatric resident accuracy in detecting pediatric upper extremity fractures. (© 2024. The Author(s), under exclusive licence to International Skeletal Society (ISS).) |
| References: | Hallas P, Ellingsen T. Errors in fracture diagnoses in the emergency department–characteristics of patients and diurnal variation. BMC Emerg Med. 2006;6:4. (PMID: 10.1186/1471-227X-6-4164833651386703) Whang JS, Baker SR, Patel R, Luk L, Castro A 3rd. The causes of medical malpractice suits against radiologists in the United States. Radiology. 2013;266:548–54. (PMID: 10.1148/radiol.1211111923204547) George MP, Bixby S. Frequently missed fractures in pediatric trauma: a pictorial review of plain film radiography. Radiol Clin North Am. 2019;57:843–55. (PMID: 10.1016/j.rcl.2019.02.00931076036) Baig MN. A review of epidemiological distribution of different types of fractures in paediatric age. Cureus. 2017;9:e1624. (PMID: 290981345659318) Kitamura G, Chung CY, Moore BE 2nd. Ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample, de novo training, and multiview incorporation. J Digit Imaging. 2019;32:672–7. (PMID: 10.1007/s10278-018-0167-7310017136646476) Ren M, Yi PH. Deep learning detection of subtle fractures using staged algorithms to mimic radiologist search pattern. Skeletal Radiol. 2021 https://doi.org/10.1007/s00256-021-03739-2. Gale W, Oakden-Rayner L, Carneiro G, Bradley AP, Palmer LJ. Detecting hip fractures with radiologist-level performance using deep neural networks [Internet]. arXiv [cs.CV]. 2017. Available from: http://arxiv.org/abs/1711.06504. Guermazi A, Tannoury C, Kompel AJ, Murakami AM, Ducarouge A, Gillibert A, et al. Improving radiographic fracture recognition performance and efficiency using artificial intelligence. Radiology. 2022;302:627–36. (PMID: 10.1148/radiol.21093734931859) Jones RM, Sharma A, Hotchkiss R, Sperling JW, Hamburger J, Ledig C, et al. Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. NPJ Digit Med. 2020;3:144. (PMID: 10.1038/s41746-020-00352-w331454407599208) Zech JR, Jaramillo D, Altosaar J, Popkin CA, Wong TT. Artificial intelligence to identify fractures on pediatric and young adult upper extremity radiographs. Pediatr Radiol. 2023;53(12):2386–97. (PMID: 10.1007/s00247-023-05754-y37740031) Rosenkrantz AB, Wang W, Hughes DR, Duszak R Jr. Generalist versus subspecialist characteristics of the U.S. radiologist workforce. Radiology. 2018;286:929–37. (PMID: 10.1148/radiol.201717168429173070) Lysack JT, Hoy M, Hudon ME, Nakoneshny SC, Chandarana SP, Matthews TW, et al. Impact of neuroradiologist second opinion on staging and management of head and neck cancer. J Otolaryngol Head Neck Surg. 2013;42:39. (PMID: 10.1186/1916-0216-42-39237390373680178) Hansen NL, Koo BC, Gallagher FA, Warren AY, Doble A, Gnanapragasam V, et al. Comparison of initial and tertiary centre second opinion reads of multiparametric magnetic resonance imaging of the prostate prior to repeat biopsy. Eur Radiol. 2017;27:2259–66. (PMID: 10.1007/s00330-016-4635-527778089) Yesilagac H, Arer IM, Gulalp B, Yabanoglu H, Karagun O, Karadeli E. Generalist versus abdominal subspecialist radiologist interpretations of abdominopelvic computed tomography performed on patients with abdominal pain and its impact on the therapeutic approach. Adv J Emerg Med. 2020;4:e21. (PMID: 323227897163262) Mollura DJ, Culp MP, Pollack E, Battino G, Scheel JR, Mango VL, et al. Artificial intelligence in low- and middle-income countries: innovating global health radiology. Radiology. 2020;297:513–20. (PMID: 10.1148/radiol.202020143433021895) Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., and Girshick, R. Detectron2 [Internet]. 2019. Available from: https://github.com/facebookresearch/detectron2. Ren S, He K, Girshick R, Sun J. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 2017;39:1137–49. (PMID: 10.1109/TPAMI.2016.257703127295650) Pizer SM, Johnston RE, Ericksen JP, Yankaskas BC, Muller KE. Contrast-limited adaptive histogram equalization: speed and effectiveness. [1990] Proceedings of the First Conference on Visualization in Biomedical Computing. 1990 p. 337–45. Irvin J, Rajpurkar P, Ko M, Yu Y, Ciurea-Ilcus S, Chute C, et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison [Internet]. arXiv [cs.CV]. 2019. Available from: http://arxiv.org/abs/1901.07031. Duron L, Ducarouge A, Gillibert A, Lainé J, Allouche C, Cherel N, et al. Assessment of an AI aid in detection of adult appendicular skeletal fractures by emergency physicians and radiologists: a multicenter cross-sectional diagnostic study. Radiology. 2021;300:120–9. (PMID: 10.1148/radiol.202120388633944629) Smith BJ, Hillis SL. 2020 Multi-reader multi-case analysis of variance software for diagnostic performance comparison of imaging modalities. Proc SPIE Int Soc Opt Eng 11316. Available from: https://doi.org/10.1117/12.2549075. Gaube S, Suresh H, Raue M, Lermer E, Koch TK, Hudecek MFC, et al. Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays. Sci Rep. 2023;13:1383. (PMID: 10.1038/s41598-023-28633-w366974509876883) Medality. 2023 radiology practice development report [Internet]. 2023. Available from: https://medality.com/2023-radiology-practice-development-report/. Shelmerdine SC, White RD, Liu H, Arthurs OJ, Sebire NJ. Artificial intelligence for radiological paediatric fracture assessment: a systematic review. Insights Imaging. 2022;13:94. (PMID: 10.1186/s13244-022-01234-3356574399166920) Dupuis M, Delbos L, Veil R, Adamsbaum C. External validation of a commercially available deep learning algorithm for fracture detection in children. Diagn Interv Imaging. 2022;103:151–9. (PMID: 10.1016/j.diii.2021.10.00734810137) Oakden-Rayner L, Dunnmon J, Carneiro G, Ré C. Hidden stratification causes clinically meaningful failures in machine learning for medical imaging [Internet]. arXiv [cs.LG]. 2019. Available from: http://arxiv.org/abs/1909.12475. Dratsch T, Chen X, RezazadeMehrizi M, Kloeckner R, Mähringer-Kunz A, Püsken M, et al. Automation bias in mammography: the impact of artificial intelligence BI-RADS suggestions on reader performance. Radiology. 2023;307:e222176. (PMID: 10.1148/radiol.22217637129490) |
| معلومات مُعتمدة: | RR2216 RSNA Research and Education Foundation |
| فهرسة مساهمة: | Keywords: Artificial intelligence; Deep learning; Fracture; Machine learning; Pediatrics; Upper extremity |
| تواريخ الأحداث: | Date Created: 20240502 Latest Revision: 20240502 |
| رمز التحديث: | 20240502 |
| DOI: | 10.1007/s00256-024-04698-0 |
| PMID: | 38695875 |
| قاعدة البيانات: | MEDLINE |
Find this article in full text from Springer Verlag. 
Full Text Finder | تدمد: | 1432-2161 |
|---|---|
| DOI: | 10.1007/s00256-024-04698-0 |