Page 30 - AIH-2-2

Artificial Intelligence in Health Machine learning in arthroplasty

6. Conclusion References

The integration of ML into total joint arthroplasty (TJA) for 1. Helm JM, Swiergosz AM, Haeberle HS, et al. Machine
hip, knee, and shoulder procedures represents a significant learning and artificial intelligence: Definitions, applications,
advancement in predictive measurements with promising and future directions. Curr Rev Musculoskelet Med.
implications for patient care and clinical outcomes. Various 2020;13(1):69-76.
ML models and algorithms have demonstrated remarkable doi: 10.1007/s12178-020-09600-8
capabilities and accuracy in multiple aspects of TJA, 2. Patel AV, Stevens AJ, Mallory N, et al. Modern applications
including radiographic imaging, implant identification and of machine learning in shoulder arthroplasty: A review. JBJS
positioning, disease identification, outcome prediction, Rev. 2023;11(7): e22.00225.
and complication detection. Despite the considerable doi: 10.2106/JBJS.RVW.22.00225
progress made in leveraging ML in orthopedics, there
remains hesitation among patients and physicians due 3. Sidey-Gibbons JAM, Sidey-Gibbons CJ. Machine learning in
to its novelty and the limited understanding of how ML medicine: A practical introduction. BMC Med Res Methodol.
models function and arrive at their decisions. Many of the 2019;19(1):64.
studies discussed in this article fail to adequately explain or doi: 10.1186/s12874-019-0681-4
replicate their program’s outcome. In addition to the clinical 4. Halawi MJ. Outcome measures in total joint arthroplasty:
advantages of AI involvement in arthroplasty, several Current status, challenges, and future directions.
ethical considerations exist, including the protection of Orthopedics. 2015;38(8):e685-e689.
patient data and clarity in understanding the AI decision-
making process. Nonetheless, the continued evolution and doi: 10.3928/01477447-20150804-55
increased accuracy of ML algorithms point to a future in 5. Tokgöz E. Artificial intelligence, deep learning, and machine
which the technology serves as a valuable asset in assisting learning applications in total hip arthroplasty. In: Total
orthopedic surgeons’ clinical decision-making in all facets Hip Arthroplasty. Berlin, Germany: Springer International
of patient care. Publishing; 2023. p. 231-246.
doi: 10.1007/978-3-031-08927-5_11
Acknowledgments
6. Hakwer, GA, Badley, EM, Borkhoff, CM, et al. Which patients
None. are most likely to benefit from total joint arthroplasty?
Arthritis Rheum. 2013;65(5):1243-1252.
Funding
doi: 10.1002/art.37901
None. 7. Klemt C, Uzosike AC, Esposito JG, et al. The utility of

Conflict of interest machine learning algorithms for the prediction of patient-
reported outcome measures following primary hip and
The authors declare that they have no competing interests. knee total joint arthroplasty. Arch Orthop Trauma Surg.
2023;143(4):2235-2245.
Author contributions doi: 10.1007/s00402-022-04526-x

Conceptualization: Akshar V. Patel, Julie Y. Bishop, Gregory 8. Karlin EA, Lin CC, Meftah M, Slover JD, Schwarzkopf R.
L. Cvetanovich, Ryan C. Rauck The impact of machine learning on total joint arthroplasty
Writing – original draft: Ryan C. White, Galo C. Bustamante, patient outcomes: A systemic review. J Arthroplasty.
Ryan M. Dopirak 2023;38(10):2085-2095.
Writing – review & editing: Collin P. Todd, Seth Wilson, doi: 10.1016/j.arth.2022.10.039
John S. Barnett, Jayden K. Simo
9. Borjali A, Chen AF, Muratoglu OK, Morid MA, Varadarajan KM.
Ethics approval and consent to participate Detecting total hip replacement prosthesis design on plain
radiographs using deep convolutional neural network.
Not applicable. J Orthop Res. 2020;38(7):1465-1471.

Consent for publication doi: 10.1002/jor.24617
10. Karnuta JM, Murphy MP, Luu BC, et al. Artificial
Not applicable.
intelligence for automated implant identification in total
Availability of data hip arthroplasty: A multicenter external validation study
exceeding two million plain radiographs. J Arthroplasty.
Not applicable. 2023;38(10):1998-2003.e1.

Volume 2 Issue 2 (2025) 24 doi: 10.36922/aih.3278