Aims. Total hip arthroplasty (THA) and total knee arthroplasty (TKA) are common orthopaedic procedures requiring postoperative radiographs to confirm implant positioning and identify complications. Artificial intelligence (AI)-based image analysis has the potential to automate this postoperative surveillance. The aim of this study was to prepare a scoping review to investigate how AI is being used in the analysis of radiographs following THA and TKA, and how accurate these tools are. Methods. The Embase, MEDLINE, and PubMed libraries were systematically searched to identify relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews and Arksey and O’Malley framework were followed. Study quality was assessed using a modified Methodological Index for Non-Randomized Studies tool. AI performance was reported using either the area under the curve (AUC) or accuracy. Results. Of the 455 studies identified, only 12 were suitable for inclusion. Nine reported implant identification and three described predicting risk of implant failure. Of the 12, three studies compared AI performance with orthopaedic surgeons. AI-based implant identification achieved AUC 0.992 to 1, and most algorithms reported an accuracy > 90%, using 550 to 320,000 training radiographs. AI prediction of dislocation risk post-THA, determined after five-year follow-up, was satisfactory (AUC 76.67; 8,500 training radiographs). Diagnosis of hip implant loosening was good (accuracy 88.3%; 420 training radiographs) and measurement of postoperative acetabular angles was comparable to humans (mean absolute difference 1.35° to 1.39°). However, 11 of the 12 studies had several methodological limitations introducing a high risk of bias. None of the studies were externally validated. Conclusion. These studies show that AI is promising. While it already has the ability to analyze images with significant precision, there is currently insufficient high-level evidence to support its widespread clinical use. Further research to design robust studies that follow standard reporting guidelines should be encouraged to develop AI models that could be easily translated into real-world conditions. Cite this article: Bone Joint J 2022;104-B(8):929–937

Aims

To examine whether natural language processing (NLP) using a clinically based large language model (LLM) could be used to predict patient selection for total hip or total knee arthroplasty (THA/TKA) from routinely available free-text radiology reports.

Digital radiography is becoming widespread. Accurate pre-operative templating of digital images of the hip traditionally involves positioning a calibration object at its centre. This can be difficult and cause embarrassment. We have devised a method whereby a planar disc placed on the radiographic cassette accounts for the expected magnification. Initial examination of 50 pelvic CT scans showed a mean hip centre distance of 117 mm (79 to 142) above the gluteal skin. Further calculations predicted that a disc of 37.17 mm diameter, placed on the cassette, would appear identical to a 30 mm sphere placed at the level of the centre of the hip as requested by our templating software. We assessed accuracy and reproducibility by ‘reverse calibration’ of 20 radiographs taken three months after hip replacement using simultaneous sphere and disc methods, and a further 20 with a precision disc of accurate size. Even when variations in patient size were ignored, the disc proved more accurate and reliable than the sphere. The technique is reliable, robust, cost effective and acceptable to patients and radiographers. It can easily be used in any radiography department after a few simple calculations and manufacture of appropriately-sized discs

Aims

To determine the trajectories of patient reported pain and functional disability over five years following total hip arthroplasty (THA) or total knee arthroplasty (TKA).

Aims

The diagnosis of periprosthetic joint infection (PJI) can be difficult. All current diagnostic tests have problems with accuracy and interpretation of results. Many new tests have been proposed, but there is no consensus on the place of many of these in the diagnostic pathway. Previous attempts to develop a definition of PJI have not been universally accepted and there remains no reference standard definition.

Aims

The primary aim of this study was to compare the wear properties of vitamin E-diffused, highly crosslinked polyethylene (VEPE) and one formulation of moderately crosslinked and mechanically annealed ultra-high molecular weight polyethylene (ModXLPE) in patients five years after primary total hip arthroplasty (THA). The secondary aim was to assess the clinical results of patients treated with VEPE by evaluating patient-reported outcome measures (PROMs), radiological evidence of fixation, and the incidence of mechanical failure.

Aims

The aim of this study was to assess the effect of multimorbidity on improvements in health-related quality of life (HRQoL) following total hip arthroplasty (THA) and total knee arthroplasty (TKA).

Aims

Vancomycin is commonly added to acrylic bone cement during revision arthroplasty surgery. Proprietary cement preparations containing vancomycin are available, but are significantly more expensive. We investigated whether the elution of antibiotic from ‘home-made’ cement containing vancomycin was comparable with more expensive commercially available vancomycin impregnated cement.

We have developed a novel method of calculating the radiological magnification of the hip using two separate radio-opaque markers. We recruited 74 patients undergoing radiological assessment following total hip replacement. Both the new double marker and a conventional single marker were used by the radiographer at the time of x-ray. The predicted magnification according to each marker was calculated, as was the true radiological magnification of the components. The correlation between true and predicted magnification was good using the double marker (r = 0.90, n = 74, p < 0.001), but only moderate for the single marker (r = 0.50, n = 63, p < 0.001). The median error was significantly less for the double marker than for the single (1.1% vs 4.8%, p < 0.001). The double marker method demonstrated excellent validity (intraclass correlation coefficient = 0.89), in contrast to the single marker (0.32).

The double marker method appears to be superior to the single marker method when used in the clinical environment.

Obtaining a balanced flexion gap with correct femoral component rotation is one of the prerequisites for a successful outcome after total knee replacement (TKR). Different techniques for achieving this have been described. In this study we prospectively compared gap-balancing versus measured resection in terms of reliability and accuracy for femoral component rotation in 96 primary TKRs performed in 96 patients using the Journey system. In 48 patients (18 men and 30 women) with a mean age of 65 years (45 to 85) a tensor device was used to determine rotation. In the second group of 48 patients (14 men and 34 women) with a mean age of 64 years (41 to 86), an ‘adapted’ measured resection technique was used, taking into account the native rotational geometry of the femur as measured on a pre-operative CT scan.

Both groups systematically reproduced a similar external rotation of the femoral component relative to the surgical transepicondylar axis: 2.4° (sd 2.5) in the gap-balancing group and 1.7° (sd 2.1) in the measured resection group (p = 0.134). Both gap-balancing and adapted measured resection techniques proved equally reliable and accurate in determining femoral component rotation after TKR. There was a tendency towards more external rotation in the gap-balancing group, but this difference was not statistically significant (p = 0.134). The number of outliers for our ‘adapted’ measured resection technique was much lower than reported in the literature.

A new generation of knee prostheses has been introduced with the intention of improving post-operative knee flexion. In order to evaluate whether this goal has been achieved we performed a systematic review and meta-analysis. Systematic literature searches were conducted on MEDLINE and EMBASE from their inception to December 2007, and proceedings of scientific meetings were also searched. Only randomised, clinical trials were included in the meta-analysis. The mean difference in the maximum post-operative flexion between the ‘high-flex’ and conventional types of prosthesis was defined as the primary outcome measure. A total of five relevant articles was identified.

Analysis of these trials suggested that no clinically relevant or statistically significant improvement was obtained in flexion with the ‘high-flex’ prostheses. The weighted mean difference was 2.1° (95% confidence interval −0.2 to +4.3; p = 0.07).