Crossmark

Evaluating the methodological suitability of partial dependence plots and Shapley additive explanations for population-level interpretation of machine learning models in total joint arthroplasty

Crossref DOI link: https://doi.org/10.1186/s42836-025-00360-9

Published Online: 2026-01-29

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Joachim, Kole

Sparks, Othneil

Perrotta, Amanda

Lin, Adrian

Gettleman, Brandon

Hamad, Christopher

Jeong, Sumin

Dingle, Ezekiel

Stavrakis, Alexandra

Christ, Alexander B.
License Information

Text and Data Mining valid from 2026-01-29

Version of Record valid from 2026-01-29
More Information

Article History

Received: 31 July 2025

Accepted: 23 December 2025

First Online: 29 January 2026

Declarations

:

: This study was deemed exempt from IRB review by our institution due to the use of publicly available, de-identified data from the NSQIP database.

: Not applicable.

: A.C. reports professional activities with Stryker, Daiichi Sankyo, Smith & Nephew, Onkos Surgical, and Zimmer Biomet Holdings. He serves on the AAOS Hip & Knee Evaluation Committee, MSTS Fellowship Committee, and is President of the ORS Implant Section. He also serves on the editorial or governing board of Arthroplasty, and declared that all authors were not involved in the journal’s review or decisions related to this manuscript. A.S. reports professional activities with Smith & Nephew and Zimmer. All other authors declare no competing interests.

Document is current

Any future updates will be listed below