In recent years, machine learning (ML) and artificial neural networks (ANNs), a particular subset of ML, have been adopted by various areas of healthcare. A number of diagnostic and prognostic algorithms have been designed and implemented across a range of orthopaedic sub-specialties to date, with many positive results. However, the methodology of many of these studies is flawed, and few compare the use of ML with the current approach in clinical practice. Spinal surgery has advanced rapidly over the past three decades, particularly in the areas of implant technology, advanced surgical techniques, biologics, and enhanced recovery protocols. It is therefore regarded an innovative field. Inevitably, spinal surgeons will wish to incorporate ML into their practice should models prove effective in diagnostic or prognostic terms. The purpose of this article is to review published studies that describe the application of neural networks to spinal surgery and which actively compare ANN models to contemporary clinical standards allowing evaluation of their efficacy, accuracy, and relatability. It also explores some of the limitations of the technology, which act to constrain the widespread adoption of neural networks for diagnostic and prognostic use in spinal care. Finally, it describes the necessary considerations should institutions wish to incorporate ANNs into their practices. In doing so, the aim of this review is to provide a practical approach for spinal surgeons to understand the relevant aspects of neural networks. Cite this article:
Access to joint replacement is being restricted for patients with comorbidities in a number of high-income countries. However, there is little evidence on the impact of comorbidities on outcomes. The purpose of this study was to determine the safety and effectiveness of hip and knee arthroplasty in patients with and without comorbidities. In total, 312,079 hip arthroplasty and 328,753 knee arthroplasty patients were included. A total of 11 common comorbidities were identified in administrative hospital records. Safety risks were measured by assessing length of hospital stay (LOS) and 30-day emergency readmissions and mortality. Effectiveness outcomes were changes in Oxford Hip or Knee Scores (OHS/OKS) (scale from 0 (worst) to 48 (best)) and in health-related quality of life (EQ-5D) (scale from 0 (death) to 1 (full health)) from immediately before, to six months after, surgery. Regression analysis was used to estimate adjusted mean differences (LOS, change in OHS/OKS/EQ-5D) and risk differences (readmissions and mortality).Aims
Methods
Acute distal biceps tendon repair reduces fatigue-related pain and minimizes loss of supination of the forearm and strength of flexion of the elbow. We report the short- and long-term outcome following repair using fixation with a cortical button techqniue. Between October 2010 and July 2018, 102 patients with a mean age of 43 years (19 to 67), including 101 males, underwent distal biceps tendon repair less than six weeks after the injury, using cortical button fixation. The primary short-term outcome measure was the rate of complications. The primary long-term outcome measure was the abbreviated Disabilities of the Arm, Shoulder and Hand (QuickDASH) score. Secondary outcomes included the Oxford Elbow Score (OES), EuroQol five-dimension three-level score (EQ-5D-3L), satisfaction, and return to function.Aims
Methods
The direct anterior approach (DAA) for total hip arthroplasty (THA) has potential advantages over other approaches and is most commonly performed with the patient in the supine position. We describe a technique for DAA THA with the patient in the lateral decubitus position and report the early clinical and radiological outcomes, the characteristics of the learning curve, and perioperative complications. All primary DAA THAs performed in the lateral position by a single surgeon over a four-year period from the surgeon’s first case using the technique were identified from a prospectively collected database. Modified Harris Hip Scores (mHHS) were collected to assess clinical outcome, and routine radiological analysis was performed. Retrospective review of the medical records identified perioperative complications, the characteristics of the learning curve, and revisions.Aims
Methods
Although there is increasing legalization of the use of cannabis in the USA, few well-powered studies have evaluated the association between cannabis use disorder and outcomes following primary total hip arthroplasty (THA). Thus, the aim of this study was to determine whether patients who use cannabis and undergo primary THA have higher rates of in-hospital length of stay (LOS), medical complications, implant-related complications, and costs. Using an administrative database, patients with cannabis use disorder undergoing primary THA were matched to a control group in a 1:5 ratio by age, sex, and various medical comorbidities. This yielded 23,030 patients (3,842 in the study group matched with 19,188 in the control group). The variables which were studied included LOS, 90-day medical complications, two-year implant-related complications, and 90-day costs of care. Mann-Whitney U tests were used to compare LOS and costs. Multivariate logistic regression analyses were used to calculate the odds ratios (ORs) of developing complications.Aims
Methods
Use of the direct anterior approach (DAA) for total hip arthroplasty (THA) has increased in recent years due to proposed benefits, including a lower risk of dislocation and improved early functional recovery. This study investigates the dislocation rate in a non-selective, consecutive cohort undergoing THA via the DAA without any exclusion or bias in patient selection based on habitus, deformity, age, sex, or fixation method. We retrospectively reviewed all patients undergoing THA via the DAA between 2011 and 2017 at our institution. Primary outcome was dislocation at minimum two-year follow-up. Patients were stratified by demographic details and risk factors for dislocation, and an in-depth analysis of dislocations was performed.Aims
Methods
This is a multicentre, non-inventor, prospective observational study of 503 INFINITY fixed bearing total ankle arthroplasties (TAAs). We report our early experience, complications, and radiological and functional outcomes. Patients were recruited from 11 specialist centres between June 2016 and November 2019. Demographic, radiological, and functional outcome data (Ankle Osteoarthritis Scale, Manchester Oxford Questionnaire, and EuroQol five-dimension five-level score) were collected preoperatively, at six months, one year, and two years. The Canadian Orthopaedic Foot and Ankle Society (COFAS) grading system was used to stratify deformity. Early and late complications and reoperations were recorded as adverse events. Radiographs were assessed for lucencies, cysts, and/or subsidence.Aims
Methods
Manipulation under anaesthesia (MUA) remains an effective intervention to address restricted range of motion (ROM) after total knee arthroplasty (TKA) and occurs in 2% to 3% of primary TKAs at our institution. Since there are few data on the outcomes of MUA with different anaesthetic methods, we sought to compare the outcomes of patients undergoing MUA with intravenous (IV) sedation and neuraxial anaesthesia. We identified 548 MUAs after primary TKA (136 IV sedation, 412 neuraxial anaesthesia plus IV sedation) from March 2016 to July 2019. The mean age of this cohort was 62 years (35 to 88) with a mean body mass index of 31 kg/m2 (18 to 49). The mean time from primary TKA to MUA was 10.2 weeks (6.2 to 24.3). Pre-MUA ROM was similar between groups; overall mean pre-MUA extension was 4.2° (p = 0.452) and mean pre-MUA flexion was 77° (p = 0.372). We compared orthopaedic complications, visual analogue scale (VAS) pain scores, length of stay (LOS), and immediate and three-month follow-up knee ROM between these groups.Aims
Methods
Although total knee arthroplasty (TKA) is a highly successful procedure, about 20% of patients remain dissatisfied postoperatively. This proportion is derived from dichotomous models of the assessment of surgical success or failure, which may not reflect the spectrum of outcomes. The aim of this study was to explore differing responses to surgery, and assess whether there are distinct groups of patients with differing patterns of outcome. This was a secondary analysis of a UK multicentre TKA longitudinal cohort study. We used a group-based trajectory modelling analysis of Oxford Knee Score (OKS) in the first year following surgery with longitudinal data involving five different timepoints and multiple predictor variables. Associations between the derived trajectory groups and categorical baseline variables were assessed, and predictors of trajectory group membership were identified using Poisson regression and multinomial logistic regression, as appropriate. The final model was adjusted for sociodemographic factors (age, sex) and baseline OKS.Aims
Methods
Social determinants of health (SDOHs) may contribute to the total cost of care (TCOC) for patients undergoing total knee arthroplasty (TKA). The aim of this study was to investigate the association between demographic data, health status, and SDOHs on 30-day length of stay (LOS) and TCOC after this procedure. Patients who underwent TKA between 1 January 2018 and 31 December 2019 were identified. A total of 234 patients with complete SDOH data were included. Data were drawn from the Chesapeake Regional Information System, the Centers for Disease Control social vulnerability index (SVI), the US Department of Agriculture, and institutional electronic medical records. The SVI identifies areas vulnerable to catastrophic events with four themed scores: socioeconomic status; household composition and disability; minority status and language; and housing and transportation. Food deserts were defined as neighbourhoods located one or ten miles from a grocery store in urban and rural areas, respectively. Multiple regression analyses were performed to determine associations with LOS and costs after controlling for various demographic parameters.Aims
Methods
To report the outcome of spinal deformity correction through anterior spinal fusion in wheelchair-bound patients with myelomeningocele. We reviewed 12 consecutive patients (7M:5F; mean age 12.4 years (9.2 to 16.8)) including demographic details, spinopelvic parameters, surgical correction, and perioperative data. We assessed the impact of surgery on patient outcomes using the Spina Bifida Spine Questionnaire and a qualitative questionnaire.Aims
Methods
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). 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).Aims
Methods
Femoral revision component subsidence has been identified as predicting early failure in revision hip surgery. This comparative cohort study assessed the potential risk factors of subsidence in two commonly used femoral implant designs. A comparative cohort study was undertaken, analyzing a consecutive series of patients following revision total hip arthroplasties using either a tapered-modular (TM) fluted titanium or a porous-coated cylindrical modular (PCM) titanium femoral component, between April 2006 and May 2018. Clinical and radiological assessment was compared for both treatment cohorts. Risk factors for subsidence were assessed and compared.Aims
Methods
The aim of this meta-analysis was to compare the outcome of total elbow arthroplasty (TEA) undertaken for rheumatoid arthritis (RA) with TEA performed for post-traumatic conditions with regard to implant failure, functional outcome, and perioperative complications. We completed a comprehensive literature search on PubMed, Web of Science, Embase, and the Cochrane Library and conducted a systematic review and meta-analysis. Nine cohort studies investigated the outcome of TEA between RA and post-traumatic conditions. The preferred reporting items for systematic reviews and meta-analysis (Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)) guidelines and Newcastle-Ottawa scale were applied to assess the quality of the included studies. We assessed three major outcome domains: implant failures (including aseptic loosening, septic loosening, bushing wear, axle failure, component disassembly, or component fracture); functional outcomes (including arc of range of movement, Mayo Elbow Performance Score (MEPS), and the Disabilities of the Arm, Shoulder and Hand (DASH) questionnaire), and perioperative complications (including deep infection, intraoperative fracture, postoperative fracture, and ulnar neuropathy).Aims
Materials and Methods
Two-stage exchange arthroplasty is the most common definitive treatment for prosthetic joint infection (PJI) in the USA. Complications that occur during treatment are often not considered. The purpose of this study was to analyze complications in patients undergoing two-stage exchange for infected total knee arthroplasty (TKA) and determine when they occur. We analyzed all patients that underwent two-stage exchange arthroplasty for treatment of PJI of the knee from January 2010 to December 2018 at a single institution. We categorized complications as medical versus surgical. The intervals for complications were divided into: interstage; early post-reimplantation (three months); and late post-reimplantation (three months to minimum one year). Minimum follow-up was one year. In total, 134 patients underwent a first stage of a two-stage exchange. There were 69 males and 65 females with an mean age at first stage surgery of 67 years (37 to 89). Success was based on the new Musculoskeletal Infection Society (MSIS) definition of success reporting.Aims
Methods
The Mathys Affinis Short is the most frequently used stemless total shoulder prosthesis in the UK. The purpose of this prospective cohort study is to report the survivorship, clinical, and radiological outcomes of the first independent series of the Affinis Short prosthesis. From January 2011 to January 2019, a total of 141 Affinis Short prostheses were implanted in 127 patients by a single surgeon. Mean age at time of surgery was 68 (44 to 89). Minimum one year and maximum eight year follow-up (mean 3.7 years) was analyzed using the Oxford Shoulder Score (OSS) at latest follow-up. Kaplan-Meier survivorship analysis was performed with implant revision as the endpoint. Most recently performed radiographs were reviewed for component radiolucent lines (RLLs) and proximal humeral migration.Aims
Methods
Metaphyseal cones with cemented stems are frequently used in revision total knee arthroplasty (TKA). However, if the diaphysis has been previously violated, the resultant sclerotic canal can impair cemented stem fixation, which is vital for bone ingrowth into the cone, and long-term fixation. We report the outcomes of our solution to this problem, in which impaction grafting and a cemented stem in the diaphysis is combined with an uncemented metaphyseal cone, for revision TKA in patients with severely compromised bone. A metaphyseal cone was combined with diaphyseal impaction grafting and cemented stems for 35 revision TKAs. There were two patients with follow-up of less than two years who were excluded, leaving 33 procedures in 32 patients in the study. The mean age of the patients at the time of revision TKA was 67 years (32 to 87); 20 (60%) were male. Patients had undergone a mean of four (1 to 13) previous knee arthroplasty procedures. The indications for revision were aseptic loosening (80%) and two-stage reimplantation for prosthetic joint infection (PJI; 20%). The mean follow-up was four years (2 to 11).Aims
Methods
Despite advances in the treatment of paediatric hip disease, adolescent and young adult patients can develop early onset end-stage osteoarthritis. The aims of this study were to address the indications and medium-term outcomes for total hip arthroplasty (THA) with ceramic bearings for teenage patients. Surgery was performed by a single surgeon working in the paediatric orthopaedic unit of a tertiary referral hospital. Databases were interrogated from 2003 to 2017 for all teenage patients undergoing THA with a minimum 2.3 year follow-up. Data capture included patient demographics, the underlying hip pathology, number of previous surgeries, and THA prostheses used. Institutional ethical approval was granted to contact patients for prospective clinical outcomes and obtain up-to-date radiographs. In total, 60 primary hips were implanted in 51 patients (35 female, 16 male) with nine bilateral cases. The mean age was 16.7 years (12 to 19) and mean follow-up was 9.3 years (2.3 to 16.8).Aims
Methods
The impact of tobacco use on readmission and medical and surgical complications has been documented in hip and knee arthroplasty. However, there remains little information about the effect of smoking on the outcome after total shoulder arthroplasty (TSA). We hypothesized that active smokers are at an increased risk of poor medical and surgial outcomes after TSA. Data for patients who underwent arthroplasty of the shoulder in the USA between January 2011 and December 2015 were obtained from the National Readmission Database, and 90-day readmissions and complications were documented using validated coding methods. Multivariate regression analysis was performed to quantify the risk of smoking on the outcome after TSA, while controlling for patient demographics, comorbidities, and hospital-level confounding factors.Aims
Methods
During the COVID-19 pandemic, many patients continue to require urgent surgery for hip fractures. However, the impact of COVID-19 on perioperative outcomes in these high-risk patients remains unknown. The objectives of this study were to establish the effects of COVID-19 on perioperative morbidity and mortality, and determine any risk factors for increased mortality in patients with COVID-19 undergoing hip fracture surgery. This multicentre cohort study included 340 COVID-19-negative patients versus 82 COVID-19-positive patients undergoing surgical treatment for hip fractures across nine NHS hospitals in Greater London, UK. Patients in both treatment groups were comparable for age, sex, body mass index, fracture configuration, and type of surgery performed. Predefined perioperative outcomes were recorded within a 30-day postoperative period. Univariate and multivariate analysis were used to identify risk factors associated with increased risk of mortality.Aims
Methods
