Identifying Volar Locking Plates on Plain Radiographs - Can Artificial Intelligence Models‘Beat’ Clinicians?

Q: Why is identifying volar locking plates on plain radiographs important?

It guides planning for revision, implant removal, and management of periprosthetic fractures, and it can be difficult when surgery occurred in another institution or country.

Q: How was the AI model evaluated against clinicians?

Fifty-two radiographs were independently labeled by ChatGPT 5 and five hand consultants; accuracy was computed per rater and pairwise comparisons used McNemar’s test with a logistic regression using clustered standard errors.

Q: What were the main findings about AI versus consultant performance?

ChatGPT 5 correctly identified only 3 of 52 radiographs, while consultant accuracy ranged from 13.5% to 46.2%; most consultants significantly outperformed the AI and humans had substantially higher odds of correct identification.

Sep 30, 2026

Uploaded by Mimi

Hand surgeons often need to identify volar locking plates on plain radiographs when planning revision, implant removal, or management of periprosthetic fractures. The task is challenging when surgery occurred elsewhere or when operative notes are unavailable, and the clinical value of AI for implant identification remains uncertain. This study evaluated an openly available AI model, ChatGPT 5, against experienced hand consultants using 52 distal radius plate radiographs from 10 manufacturers.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusion

Introduction

Materials And Methods

Review began 11/15/2025 Review ended 12/04/2025 Published 12/08/2025 © Copyright 2025 Albert et al. This is an open access article distributed under the terms of the Creative Commons Attribution License CC-BY 4.0. , which permits unrestricted use , distribution , and reproduction in any medium , provided the original author and source are credited. DOI: 10.7759/cureus.98715 Open Access Original Article Identifying Volar Locking Plates on Plain Radiographs: Can Artificial Intelligence Models‘Beat’ Clinicians? Allen Albert 1, Alex Nicholls 2, Duncan Avis 2, Medhat Zekry 1, Matay Arsan 1, Priyanshu Saha 1 , Adam Stoneham 1 1. Trauma and Orthopaedics, Homerton University Hospital, London, GBR 2. Trauma and Orthopaedics, Hampshire Hospitals NHS Foundation Trust, Hampshire, GBR Corresponding author: Allen Albert, [allen.jasper.durai@gmail.com](allen.jasper.durai@gmail.com) Abstract Background Hand surgeons are frequently required to identify volar locking plates on plain radiographs. This is important, for example, when planning what equipment is required for revision, implant removal or periprosthetic fractures, but it can be challenging, especially if surgery took place in another hospital or even country. Artificial intelligence (AI) clearly has potential in medical image recognition, but its role in orthopaedic implant identification currently remains uncertain. This study compared the performance of an openly available AI model, ChatGPT 5, with that of experienced hand consultants. Methods Fifty-two radiographs of distal radius plates from 10 major implant manufacturers were obtained from openaccess sources. An AI programme (ChatGPT 5) and five hand consultants independently identified the manufacturer for each radiograph. Accuracy was calculated for each rater. Pairwise comparisons between AI and each consultant were assessed using McNemar’s test, and a standard logistic regression with clustered standard errors was fitted to compare AI with consultants as a group. Results ChatGPT5 correctly identified just 3 of 52 radiographs (5 .8% accuracy) . Consultant accuracies ranged between 13.5 and 46 .2%(mean 30.8% ± 11. 1) . McNemar’s test showed that Consultants 1, 3, 4 and 5 significantly outperformed the AI (p < 0 .01), while Consultant 2 did not (p = 0 .289) . In a standard logistic regression with clustered standard errors, the human cohort had 7.26 times higher odds of correct identification compared with the AI (OR 7.26, 95% CI 2 .27-23.18, p < 0 .001) . Conclusion Identifying volar locking distal radius plates from plain radiographs remains difficult, even for experienced surgeons and even the ‘best’ consultant identified under 50% correctly. That notwithstanding, humans were on average seven times better than ChatGPT 5 which only identified just over 5% correctly. While current non-specialised AI tools are not suitable for implant identification currently, dedicated AI models trained on curated orthopaedic datasets may hold promise for future clinical use. Categories: Radiology, Healthcare Technology, Orthopedics Keywords: artificial intelligence, image recognition, implant identification, volar locking plate, x-ray analysis Introduction Distal radius fractures rank amongst the commonest adult orthopaedic injuries; the incidence has been steadily rising over the last 20 years, and this trend is expected to continue [1] . Treatment can be nonoperative or operative depending on many factors including the degree of displacement and the patients’age and comorbidities [2], while significant variation exists in clinical practice [3] . Although good results are achievable with percutaneous wire fixation [4,5], there has been a steady rise in the use of internal fixation in North America [6,7] and Europe [8,9] and volar locking plates have risen from around 20% of surgeries in 1997 to over 90% in 2018 [10]. Hardware removal following open reduction and internal fixation is controver

FAQs

Why is identifying volar locking plates on plain radiographs important?

It guides planning for revision, implant removal, and management of periprosthetic fractures, and it can be difficult when surgery occurred in another institution or country.

How was the AI model evaluated against clinicians?

Fifty-two radiographs were independently labeled by ChatGPT 5 and five hand consultants; accuracy was computed per rater and pairwise comparisons used McNemar’s test with a logistic regression using clustered standard errors.

What were the main findings about AI versus consultant performance?

ChatGPT 5 correctly identified only 3 of 52 radiographs, while consultant accuracy ranged from 13.5% to 46.2%; most consultants significantly outperformed the AI and humans had substantially higher odds of correct identification.

Sep 30, 2026

Uploaded by Mimi