Aims. Machine learning (ML), a branch of artificial intelligence that uses algorithms to learn from data and make predictions, offers a pathway towards more personalized and tailored surgical treatments. This approach is particularly relevant to prevalent joint diseases such as osteoarthritis (OA). In contrast to end-stage disease, where joint arthroplasty provides excellent results, early stages of OA currently lack effective therapies to halt or reverse progression. Accurate prediction of OA progression is crucial if timely interventions are to be developed, to enhance patient care and optimize the design of clinical trials. Methods. A systematic review was conducted in accordance with PRISMA guidelines. We searched MEDLINE and Embase on 5 May 2024 for studies utilizing ML to predict OA progression. Titles and abstracts were independently screened, followed by full-text reviews for studies that met the eligibility criteria. Key information was extracted and synthesized for analysis, including types of data (such as clinical, radiological, or biochemical), definitions of OA progression, ML algorithms, validation methods, and outcome measures. Results. Out of 1,160 studies initially identified, 39 were included. Most studies (85%) were published between 2020 and 2024, with 82% using publicly available datasets, primarily the Osteoarthritis Initiative. ML methods were predominantly supervised, with significant variability in the definitions of OA progression: most studies focused on structural changes (59%), while fewer addressed pain progression or both. Deep learning was used in 44% of studies, while automated ML was used in 5%. There was a lack of standardization in evaluation metrics and limited external validation. Interpretability was explored in 54% of studies, primarily using SHapley Additive exPlanations. Conclusion. Our systematic review demonstrates the feasibility of ML models in predicting OA progression, but also uncovers critical limitations that currently restrict their clinical applicability. Future priorities should include diversifying data sources, standardizing outcome measures, enforcing rigorous validation, and integrating more sophisticated algorithms. This paradigm shift from predictive modelling to actionable clinical tools has the potential to transform patient care and disease management in orthopaedic practice. Cite this article: Bone Joint J 2024;106-B(11):1216–1222

Aims. The aim of this study was to report the pooled prevalence of post-traumatic osteoarthritis (PTOA) and examine whether the risk of developing PTOA after anterior cruciate ligament (ACL) injury has decreased in recent decades. Methods. The PubMed and Web of Science databases were searched from 1 January 1980 to 11 May 2022. Patient series, observational studies, and clinical trials having reported the prevalence of radiologically confirmed PTOA after ACL injury, with at least a ten-year follow-up, were included. All studies were analyzed simultaneously, and separate analyses of the operative and nonoperative knees were performed. The prevalence of PTOA was calculated separately for each study, and pooled prevalence was reported with 95% confidence intervals (CIs) using either a fixed or random effects model. To examine the effect of the year of injury on the prevalence, a logit transformed meta-regression analysis was used with a maximum-likelihood estimator. Results from meta-regression analyses were reported with the unstandardized coefficient (β). Results. The pooled prevalence of PTOA was 37.9% (95% CI 32.1 to 44) for operatively treated ACL injuries with a median follow-up of 14.6 years (interquartile range (IQR) 10.6 to 16.7). For nonoperatively treated ACL injuries, the prevalence was 40.5% (95% CI 28.9 to 53.3), with a median of follow-up of 15 years (IQR 11.7 to 20.0). The association between the year of operation and the prevalence of PTOA was weak and imprecise and not related to the choice of treatment (operative β -0.038 (95% CI -0.076 to 0.000) and nonoperative β -0.011 (95% CI -0.101 to 0.079)). Conclusion. The initial injury, irrespective of management, has, by the balance of probability, resulted in PTOA within 20 years. In addition, the prevalence of PTOA has only slightly decreased during past decades. Therefore, further research is warranted to develop strategies to prevent the development of PTOA after ACL injuries. Cite this article: Bone Joint J 2023;105-B(11):1140–1148

Aims. This systematic review asked which patterns of complications are associated with the three reverse total shoulder arthroplasty (RTSA) prosthetic designs, as classified by Routman et al, in patients undergoing RTSA for the management of cuff tear arthropathy, massive cuff tear, osteoarthritis, and rheumatoid arthritis. The three implant design philosophies investigated were medial glenoid/medial humerus (MGMH), medial glenoid/lateral humerus (MGLH), and lateral glenoid/medial humerus (LGMH). Methods. A systematic review of the literature was performed via a search of MEDLINE and Embase. Two reviewers extracted data on complication occurrence and patient-reported outcome measures (PROMs). Meta-analysis was conducted on the reported proportion of complications, weighted by sample size, and PROMs were pooled using the reported standardized mean difference (SMD). Quality of methodology was assessed using Wylde’s non-summative four-point system. The study was registered with PROSPERO (CRD42020193041). Results. A total of 42 studies met the inclusion and exclusion criteria. Rates of scapular notching were found to be significantly higher in MGMH implants (52% (95% confidence interval (CI) 40 to 63)) compared with MGLH ((18% (95% CI 6 to 34)) and LGMH (12% (95% CI 3 to 26)). Higher rates of glenoid loosening were seen in MGMH implants (6% (95% CI 3 to 10)) than in MGLH implants (0% (95% CI 0 to 2)). However, strength of evidence for this finding was low. No significant differences were identified in any other complication, and there were no significant differences observed in PROMs between implant philosophies. Conclusion. This systematic review has found significant improvement in PROMS and low complication rates across the implant philosophies studied. Scapular notching was the only complication found definitely to have significantly higher prevalence with the MGMH implant design. Cite this article: Bone Joint J 2021;103-B(5):813–821

Aims. Short-stemmed femoral implants have been used for total hip arthroplasty (THA) in young and active patients to conserve bone, provide physiological loading, and reduce the incidence of thigh pain. Only short- to mid-term results have been presented and there have been concerns regarding component malalignment, incorrect sizing, and subsidence. This systematic review reports clinical and radiological outcomes, complications, revision rates, and implant survival in THA using short-stemmed femoral components. Materials and Methods. A literature review was performed using the EMBASE, Medline, and Cochrane databases. Strict inclusion and exclusion criteria were used to identify studies reporting clinical and radiological follow-up for short-stemmed hip arthroplasties. Results. A total of 28 studies were eligible for inclusion. This included 5322 hips in 4657 patients with a mean age of 59 years (13 to 94). The mean follow-up was 6.1 years (0.5 to 20). The mean Harris Hip Score improved from 46 (0 to 100) to 92 (39 to 100). The mean Oxford Hip Score improved from 25 (2 to 42.5) to 35 (12.4 to 48). The mean Western Ontario & McMaster Universities Osteoarthritis Index improved from 54 (2 to 95) to 22 (0 to 98). Components were aligned in a neutral coronal alignment in up to 90.9% of cases. A total of 15 studies reported component survivorship, which was 98.6% (92% to 100%) at a mean follow-up of 12.1 years. Conclusion. Short-stemmed femoral implants show similar improvement in clinical and radiological outcomes compared with conventional length implants. Only mid-term survivorship, however, is known. An abundance of short components have been developed and used commercially without staged clinical trials. Long-term survival is still unknown for many of these components. There remains tension between innovation and the moral duty to ensure that the introduction of new implants is controlled until safety and patient benefit are demonstrated. Implant innovation and subsequent use should be driven by proven clinical outcomes, rather than market and financial forces, and ethical practice must be ensured. Cite this article: Bone Joint J 2019;101-B:502–511

Aims

Intra-articular (IA) injection may be used when treating hip osteoarthritis (OA). Common injections include steroids, hyaluronic acid (HA), local anaesthetic, and platelet-rich plasma (PRP). Network meta-analysis allows for comparisons between two or more treatment groups and uses direct and indirect comparisons between interventions. This network meta-analysis aims to compare the efficacy of various IA injections used in the management of hip OA with a follow-up of up to six months.

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.

Cite this article: Bone Joint J 2022;104-B(12):1292–1303.

Aims

Conventional patient-reported surveys, used for patients undergoing total hip arthroplasty (THA), are limited by subjectivity and recall bias. Objective functional evaluation, such as gait analysis, to delineate a patient’s functional capacity and customize surgical interventions, may address these shortcomings. This systematic review endeavours to investigate the application of objective functional assessments in appraising individuals undergoing THA.

Aims

This systematic review aimed to summarize the full range of complications reported following ankle arthroscopy and the frequency at which they occur.

Aims

Proximal humeral fractures are the third most common fracture among the elderly. Complications associated with fixation include screw perforation, varus collapse, and avascular necrosis of the humeral head. To address these challenges, various augmentation techniques to increase medial column support have been developed. There are currently no recent studies that definitively establish the superiority of augmented fixation over non-augmented implants in the surgical treatment of proximal humeral fractures. The aim of this systematic review and meta-analysis was to compare the outcomes of patients who underwent locking-plate fixation with cement augmentation or bone-graft augmentation versus those who underwent locking-plate fixation without augmentation for proximal humeral fractures.

Aims

This systematic review aims to compare the precision of component positioning, patient-reported outcome measures (PROMs), complications, survivorship, cost-effectiveness, and learning curves of MAKO robotic arm-assisted unicompartmental knee arthroplasty (RAUKA) with manual medial unicompartmental knee arthroplasty (mUKA).

Aims

Arthroplasty is being increasingly used for the management of distal humeral fractures (DHFs) in elderly patients. Arthroplasty options include total elbow arthroplasty (TEA) and hemiarthroplasty (HA); both have unique complications and there is not yet a consensus on which implant is superior. This systematic review asked: in patients aged over 65 years with unreconstructable DHFs, what differences are there in outcomes, as measured by patient-reported outcome measures (PROMs), range of motion (ROM), and complications, between distal humeral HA and TEA?

Aims

The preoperative diagnosis of periprosthetic joint infection (PJI) remains a challenge due to a lack of biomarkers that are both sensitive and specific. We investigated the performance characteristics of polymerase chain reaction (PCR), interleukin-6 (IL6), and calprotectin of synovial fluid in the diagnosis of PJI.

Aims

This study aimed to answer two questions: what are the best diagnostic methods for diagnosing bacterial arthritis of a native joint?; and what are the most commonly used definitions for bacterial arthritis of a native joint?

Aims

The goal of the current systematic review was to assess the impact of implant placement accuracy on outcomes following total knee arthroplasty (TKA).

Aims

The aims of this systematic review were to assess the learning curve of semi-active robotic arm-assisted total hip arthroplasty (rTHA), and to compare the accuracy, patient-reported functional outcomes, complications, and survivorship between rTHA and manual total hip arthroplasty (mTHA).

Aims

This study aimed to compare the effect of antibiotic-loaded bone cement (ALBC) versus plain bone cement (PBC) on revision rates for periprosthetic joint infection (PJI) and all-cause revisions following primary elective total hip arthroplasty (THA) and total knee arthroplasty (TKA).

Aims

The aims of this study were to validate the outcome of total elbow arthroplasty (TEA) in patients with rheumatoid arthritis (RA), and to identify factors that affect the outcome.

Aims

Dislocation is the most common indication for further surgery following total hip arthroplasty (THA) when undertaken in patients with a femoral neck fracture. This study aimed to assess the complication rates of THA with dual mobility components (THA-DMC) following a femoral neck fracture and to compare outcomes between THA-DMC, conventional THA, and hemiarthroplasty (HA).

Aims

There is inconsistent evidence on whether prior spinal fusion surgery adversely impacts outcomes following total hip arthroplasty (THA). We conducted a systematic review and meta-analysis to assess the association between pre-existing spinal fusion surgery and the rate of complications following primary THA.

The application of robotics in the operating theatre for knee arthroplasty remains controversial. As with all new technology, the introduction of new systems might be associated with a learning curve. However, guidelines on how to assess the introduction of robotics in the operating theatre are lacking. This systematic review aims to evaluate the current evidence on the learning curve of robot-assisted knee arthroplasty. An extensive literature search of PubMed, Medline, Embase, Web of Science, and Cochrane Library was conducted. Randomized controlled trials, comparative studies, and cohort studies were included. Outcomes assessed included: time required for surgery, stress levels of the surgical team, complications in regard to surgical experience level or time needed for surgery, size prediction of preoperative templating, and alignment according to the number of knee arthroplasties performed. A total of 11 studies met the inclusion criteria. Most were of medium to low quality. The operating time of robot-assisted total knee arthroplasty (TKA) and unicompartmental knee arthroplasty (UKA) is associated with a learning curve of between six to 20 cases and six to 36 cases respectively. Surgical team stress levels show a learning curve of seven cases in TKA and six cases for UKA. Experience with the robotic systems did not influence implant positioning, preoperative planning, and postoperative complications. Robot-assisted TKA and UKA is associated with a learning curve regarding operating time and surgical team stress levels. Future evaluation of robotics in the operating theatre should include detailed measurement of the various aspects of the total operating time, including total robotic time and time needed for preoperative planning. The prior experience of the surgical team should also be evaluated and reported.

Cite this article: Bone Joint J 2020;102-B(4):407–413.