Over 8000 total hip arthroplasties (THA) in the UK were revised in 2019, half for aseptic loosening. It is believed that Artificial Intelligence (AI) could identify or predict failing THA and result in early recognition of poorly performing implants and reduce patient suffering.

The aim of this study is to investigate whether Artificial Intelligence based machine learning (ML) / Deep Learning (DL) techniques can train an algorithm to identify and/or predict failing uncemented THA.

Consent was sought from patients followed up in a single design, uncemented THA implant surveillance study (2010–2021). Oxford hip scores and radiographs were collected at yearly intervals. Radiographs were analysed by 3 observers for presence of markers of implant loosening/failure: periprosthetic lucency, cortical hypertrophy, and pedestal formation.

DL using the RGB ResNet 18 model, with images entered chronologically, was trained according to revision status and radiographic features. Data augmentation and cross validation were used to increase the available training data, reduce bias, and improve verification of results.

184 patients consented to inclusion. 6 (3.2%) patients were revised for aseptic loosening. 2097 radiographs were analysed: 21 (11.4%) patients had three radiographic features of failure.

166 patients were used for ML algorithm testing of 3 scenarios to detect those who were revised. 1) The use of revision as an end point was associated with increased variability in accuracy. The area under the curve (AUC) was 23–97%. 2) Using 2/3 radiographic features associated with failure was associated with improved results, AUC: 75–100%. 3) Using 3/3 radiographic features, had less variability, reduced AUC of 73%, but 5/6 patients who had been revised were identified (total 66 identified).

The best algorithm identified the greatest number of revised hips (5/6), predicting failure 2–8 years before revision, before all radiographic features were visible and before a significant fall in the Oxford Hip score. True-Positive: 0.77, False Positive: 0.29.

ML algorithms can identify failing THA before visible features on radiographs or before PROM scores deteriorate. This is an important finding that could identify failing THA early.

This study utilized data from the NJR dataset on all Corail/Pinnacle total hip replacements (THR) to determine (a) the level of unit variation of the Corail/Pinnacle 36mm Metal On Metal THR within England and Wales; (b) patient, implant and surgeon factors that may be associated with higher revision rates; (c) Account for the influence of the MHRA announcement in 2010.

The national Revision Rate (RR) for the Corail / Pinnacle MOM THR was 10.77% (OR:1.46; CI:1.17–1.81). This was significantly greater than other articulation combinations (MOP 1.72%, COP 1.36%, COC 2.19%).

The 2010 MHRA announcement did not increase rate of revision (X²=1649.63, df=13, p<.001).

Patient factors associated with significantly increased revision rates included, female gender (OR 1.38 (CI 1.17–1.63, p<.001) and younger age OR 0.99 (CI 0.98–0.99), p<.001). Implant factor analysis demonstrated an inverse relationship between cup size and revision. As head length increased RR increased – highest risk of revision +12.5 (OR 1.69 (CI 1.12–2.55), p=0.13). Coxa vara, high offset stems had a higher risk of revision compared to standard offset stems (OR:1.41 (CI 1.15–1.74; p<.001). As stem size increased risk of revision decreased (OR 0.89 (CI 0.85–0.93); p<.001). Surgeon grade did not influence RR.

There was significant variation in RR between hospitals with 7 units (7/61 excluding low volume centres, <50 implants) identified as having significant higher rates of revision. However, for each of these units there was a greater proportion of higher risk patients (female, cup size 50–54, stem type).

This study has provided insight into unit variation, risk factors and the long term outcome of the Corail/Pinnacle 36mm MOMTHR. Future aims are to use these results to develop a risk stratified algorithm for the long term follow of these patients to minimize patient inconvenience and excess use of limited NHS resources.

Introduction

Mix and Match (M&M) describes the use of components from more than one manufacturer in a total hip replacement (THR) The NJR has records of over 90,000 instances where this practice, which is contrary to the advice of most manufacturers and regulators, has been followed.