A radiographic artificial intelligence tool to identify candidates suitable for partial knee arthroplasty
File(s)
Published version
Author(s)
Type
Journal Article
Abstract
Introduction: Knee osteoarthritis is a prevalent condition frequently necessitating knee replacement surgery, with demand projected to rise substantially. Partial knee arthroplasty (PKA) offers advantages over total knee arthroplasty (TKA), yet its utilisation remains low despite guidance recommending consideration alongside TKA in shared decision making. Radiographic decision aids exist but are underutilised due to clinician time constraints.
Materials and Methods: This research develops a novel radiographic artificial intelligence (AI) tool using a dataset of knee radiographs and a panel of expert orthopaedic surgeons' assessments. Six AI models were trained to identify PKA candidacy.
Results: 4,967 labelled four-view radiograph series were included. Models achieved statistically significant accuracies above random assignment, with EfficientNet-ES demonstrating the highest performance (AUC 95%, F1 score 83% and accuracy 80%).
Conclusions: The AI decision tool shows promise in identifying PKA candidates, potentially addressing underutilisation of this procedure. Its integration into clinical practice could enhance shared decision making and improve patient outcomes. Further validation and implementation studies are warranted to assess real-world utility and impact.
Materials and Methods: This research develops a novel radiographic artificial intelligence (AI) tool using a dataset of knee radiographs and a panel of expert orthopaedic surgeons' assessments. Six AI models were trained to identify PKA candidacy.
Results: 4,967 labelled four-view radiograph series were included. Models achieved statistically significant accuracies above random assignment, with EfficientNet-ES demonstrating the highest performance (AUC 95%, F1 score 83% and accuracy 80%).
Conclusions: The AI decision tool shows promise in identifying PKA candidates, potentially addressing underutilisation of this procedure. Its integration into clinical practice could enhance shared decision making and improve patient outcomes. Further validation and implementation studies are warranted to assess real-world utility and impact.
Date Issued
2024-11
Date Acceptance
2024-09-16
Citation
Archives of Orthopaedic and Trauma Surgery, 2024, 144 (11), pp.4963-4968
ISSN
0936-8051
Publisher
Springer
Start Page
4963
End Page
4968
Journal / Book Title
Archives of Orthopaedic and Trauma Surgery
Volume
144
Issue
11
Copyright Statement
© The Author(s) 2024 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
License URL
Identifier
https://link.springer.com/article/10.1007/s00402-024-05589-8
Publication Status
Published
Date Publish Online
2024-10-03