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.
A modular hemiarthroplasty has a Metal-on-Metal (MoM) taper-trunnion junction, which may lead to increased wear and Adverse-Reaction-to-Metal-Debris (ARMD). To-date no wear related issues have been described in the elderly and less active that receives a hemiarthroplasty. This study aims to determine in vivo wear (i.e. serum metal ion levels) in hip hemiarthroplasty, and identify factors associated with increased wear. This is a prospective, IRB approved, single-centre, cohort study of patients that received an uncemented, modular hemiarthroplasty of proven design for the treatment of hip fracture between 2013–2015. All, alive, patients at 12-months post-implantation with AMTS≥6 were invited to participate. Of the 125 eligible patients, 50 accepted the invitation and were reviewed, including clinical/radiological assessment, metal-ion ([Chromium (Cr) and Cobalt (Co)]) measurement and Oxford Hip Score (OHS). Acetabular erosion was graded (0–3: normal-protrusio). Metal ion levels were considered high if ≥7ppb. The mean OHS was 37 (SD: 10). No acetabular erosion was detected in 21, whilst the remaining had either grade-1 (n=21) or grade-2 (n=8). The median Cr and Co levels were 2.9 (SD:9) and 2.2 (SD:4) respectively. There were 8 cases (16%) with high ion levels. To-date only 2 of them has an ARMD lesion, and none have been revised. Patients with metal ion levels had similar pre-fall mobility, taper- and head- size and OHS to those with low metal ion levels (p=0.2–0.7) However, all hips with high metal ion levels had evidence of acetabular erosion (≥1). Modular Hip hemiarthroplasties and their taper-trunnion junction are not immune to high wear and ARMD despite being implanted in a less active cohort. Acetabular erosion should alert clinicians, as it is associated with 20× increased-risk of taper wear, presumably due to the increased transmitted torque. Whether the use of modular hemiarthroplasties should remain is debatable.
