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:
Cauda equina syndrome (CES) can be associated with chronic severe lower back pain and long-term autonomic dysfunction. This study assesses the recently defined core outcome set for CES in a cohort of patients using validated questionnaires. Between January 2005 and December 2019, 82 patients underwent surgical decompression for acute CES secondary to massive lumbar disc prolapse at our hospital. After review of their records, patients were included if they presented with the clinical and radiological features of CES, then classified as CES incomplete (CESI) or with painless urinary retention (CESR) in accordance with guidelines published by the British Association of Spinal Surgeons. Patients provided written consent and completed a series of questionnaires.Aims
Methods
The aims of this network meta-analysis (NMA) were to examine nonunion rates and functional outcomes following various operative and nonoperative treatments for displaced mid-shaft clavicle fractures. Initial search strategy incorporated MEDLINE, PubMed, Embase, and the Cochrane Library for relevant randomized controlled trials (RCTs). Four treatment arms were created: nonoperative (NO); intramedullary nailing (IMN); reconstruction plating (RP); and compression/pre-contoured plating (CP). A Bayesian NMA was conducted to compare all treatment options for outcomes of nonunion, malunion, and function using the Disabilities of the Arm Shoulder and Hand (DASH) and Constant-Murley Shoulder Outcome scores.Aims
Methods
MRI has been suggested as an objective method of assessing anterior crucate ligament (ACL) graft “ligamentization” after reconstruction. It has been proposed that the MRI appearances could be used as an indicator of graft maturity and used as part of a return-to-sport assessment. The aim of this study was to evaluate the correlation between MRI graft signal and postoperative functional scores, anterior knee laxity, and patient age at operation. A consecutive cohort of 149 patients who had undergone semitendinosus autograft ACL reconstruction, using femoral and tibial adjustable loop fixations, were evaluated retrospectively postoperatively at two years. All underwent MRI analysis of the ACL graft, performed using signal-to-noise quotient (SNQ) and the Howell score. Functional outcome scores (Lysholm, Tegner, International Knee Documentation Committee (IKDC) subjective, and IKDC objective) were obtained and all patients underwent instrumented side-to-side anterior laxity differential laxity testing.Aims
Methods
Due to widespread cancellations in elective orthopaedic procedures, the number of patients on waiting list for surgery is rising. We aim to determine and quantify if disparities exist between inpatient and day-case orthopaedic waiting list numbers; we also aim to determine if there is a ‘hidden burden’ that already exists due to reductions in elective secondary care referrals. Retrospective data were collected between 1 April 2020 and 31 December 2020 and compared with the same nine-month period the previous year. Data collected included surgeries performed (day-case vs inpatient), number of patients currently on the orthopaedic waiting list (day-case vs inpatient), and number of new patient referrals from primary care and therapy services.Aims
Methods
To describe the clinical, radiological, and functional outcomes in patients with isolated congenital thoracolumbar kyphosis who were treated with three-column osteotomy by posterior-only approach. Hospital records of 27 patients with isolated congenital thoracolumbar kyphosis undergoing surgery at a single centre were retrospectively analyzed. All patients underwent deformity correction which involved a three-column osteotomy by single-stage posterior-only approach. Radiological parameters (local kyphosis angle (KA), thoracic kyphosis (TK), lumbar lordosis (LL), pelvic tilt (PT), sacral slope (SS), C7 sagittal vertical axis (C7 SVA), T1 slope, and pelvic incidence minus lumbar lordosis (PI-LL)), functional scores, and clinical details of complications were recorded.Aims
Methods
Patients with spinal pathology who undergo total hip arthroplasty (THA) have an increased risk of dislocation and revision. The aim of this study was to determine if the use of the Hip-Spine Classification system in these patients would result in a decreased rate of postoperative dislocation in patients with spinal pathology. This prospective, multicentre study evaluated 3,777 consecutive patients undergoing THA by three surgeons, between January 2014 and December 2019. They were categorized using The Hip-Spine Classification system: group 1 with normal spinal alignment; group 2 with a flatback deformity, group 2A with normal spinal mobility, and group 2B with a stiff spine. Flatback deformity was defined by a pelvic incidence minus lumbar lordosis of > 10°, and spinal stiffness was defined by < 10° change in sacral slope from standing to seated. Each category determined a patient-specific component positioning. Survivorship free of dislocation was recorded and spinopelvic measurements were compared for reliability using intraclass correlation coefficient.Aims
Methods
Cement-in-cement revision of the femoral component represents a widely practised technique for a variety of indications in revision total hip arthroplasty. In this study, we compare the clinical and radiological outcomes of two polished tapered femoral components. From our prospectively collated database, we identified all patients undergoing cement-in-cement revision from January 2005 to January 2013 who had a minimum of two years' follow-up. All cases were performed by the senior author using either an Exeter short revision stem or the C-Stem AMT high offset No. 1 prosthesis. Patients were followed-up annually with clinical and radiological assessment.Aims
Methods
The purpose of this study was to compare clinical results, long-term survival, and complication rates of stemless shoulder prosthesis with stemmed anatomical shoulder prostheses for treatment of osteoarthritis and to analyze radiological bone changes around the implants during follow-up. A total of 161 patients treated with either a stemmed or a stemless shoulder arthroplasty for primary osteoarthritis of the shoulder were evaluated with a mean follow-up of 118 months (102 to 158). The Constant score (CS), the Disabilities of the Arm, Shoulder and Hand (DASH) score, and active range of motion (ROM) were recorded. Radiological analysis for bone adaptations was performed by plain radiographs. A Kaplan-Meier survivorship analysis was calculated and complications were noted.Aims
Methods
Traditionally, acetabular component insertion during total hip arthroplasty (THA) is visually assisted in the posterior approach and fluoroscopically assisted in the anterior approach. The present study examined the accuracy of a new surgeon during anterior (NSA) and posterior (NSP) THA using robotic arm-assisted technology compared to two experienced surgeons using traditional methods. Prospectively collected data was reviewed for 120 patients at two institutions. Data were collected on the first 30 anterior approach and the first 30 posterior approach surgeries performed by a newly graduated arthroplasty surgeon (all using robotic arm-assisted technology) and was compared to standard THA by an experienced anterior (SSA) and posterior surgeon (SSP). Acetabular component inclination, version, and leg length were calculated postoperatively and differences calculated based on postoperative film measurement.Aims
Methods
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). Searches of PubMed, Medline, and Google Scholar were performed in April 2020 in line with the Preferred Reporting Items for Systematic Review and Meta-Analysis statement. Search terms included “robotic”, “hip”, and “arthroplasty”. The criteria for inclusion were published clinical research articles reporting the learning curve for rTHA (robotic arm-assisted only) and those comparing the implantation accuracy, functional outcomes, survivorship, or complications with mTHA.Aims
Methods
We report the long-term outcomes of the UK Heel Fracture Trial (HeFT), a pragmatic, multicentre, two-arm, assessor-blinded, randomized controlled trial. HeFT recruited 151 patients aged over 16 years with closed displaced, intra-articular fractures of the calcaneus. Patients with significant deformity causing fibular impingement, peripheral vascular disease, or other significant limb injuries were excluded. Participants were randomly allocated to open reduction and internal fixation (ORIF) or nonoperative treatment. We report Kerr-Atkins scores, self-reported difficulty walking and fitting shoes, and additional surgical procedures at 36, 48, and 60 months.Aims
Methods
Periprosthetic joint infection (PJI) is a devastating complication following total knee arthroplasty (TKA). Two-stage revision has traditionally been considered the gold standard of treatment for established infection, but increasing evidence is emerging in support of one-stage exchange for selected patients. The objective of this study was to determine the outcomes of single-stage revision TKA for PJI, with mid-term follow-up. A total of 84 patients, with a mean age of 68 years (36 to 92), underwent single-stage revision TKA for confirmed PJI at a single institution between 2006 and 2016. In all, 37 patients (44%) were treated for an infected primary TKA, while the majority presented with infected revisions: 31 had undergone one previous revision (36.9%) and 16 had multiple prior revisions (19.1%). Contraindications to single-stage exchange included systemic sepsis, extensive bone or soft-tissue loss, extensor mechanism failure, or if primary wound closure was unlikely to be achievable. Patients were not excluded for culture-negative PJI or the presence of a sinus.Aims
Methods
The purpose of this study was to report bone adaptive changes after anatomical total shoulder arthroplasty (TSA) using a standard-length hydroxyapatite (HA)-coated humeral component, and to report on a computer-based analysis of radiographs to determine changes in peri-implant bone density objectively. A total of 44 TSAs, performed between 2011 and 2014 using a cementless standard-length humeral component proximally coated with HA, were included. There were 23 males and 21 females with a mean age of 65 years (17 to 65). All shoulders had good quality radiographs at six weeks and five years postoperatively. Three observers graded bone adaptive changes. All radiographs were uploaded into a commercially available photographic software program. The grey value density of humeral radiological areas was corrected to the grey value density of the humeral component and compared over time.Aims
Methods
To evaluate the perioperative complications associated with total en bloc spondylectomy (TES) in patients with spinal tumours, based on the extent and level of tumour resection. In total, 307 patients who underwent TES in a single centre were reviewed retrospectively. There were 164 male and 143 female patients with a mean age at the time of surgery of 52.9 years (SD 13.3). A total of 225 patients were operated on for spinal metastases, 34 for a malignant primary tumour, 41 for an aggressive benign tumour, and seven with a primary of unknown origin. The main lesion was located in the thoracic spine in 213, and in the lumbar spine in 94 patients. There were 97 patients who underwent TES for more than two consecutive vertebrae.Aims
Methods
We aimed to evaluate the long-term impact of fracture-related infection (FRI) on patients’ physical health and psychological wellbeing. For this purpose, quality of life after successful surgical treatment of FRIs of long bones was assessed. A total of 37 patients treated between November 2009 and March 2019, with achieved eradication of infection and stable bone consolidation after long bone FRI, were included. Quality of life was evaluated with the EuroQol five-dimension questionnaire (EQ-5D) and German Short-Form 36 (SF-36) outcome instruments as well as with an International Classification of Diseases of the World Health Organization (ICD)-10 based symptom rating (ISR) and compared to normative data.Aims
Methods
Evaluating musculoskeletal conditions of the lower limb and understanding the pathophysiology of complex bone kinematics is challenging. Static images do not take into account the dynamic component of relative bone motion and muscle activation. Fluoroscopy and dynamic MRI have important limitations. Dynamic CT (4D-CT) is an emerging alternative that combines high spatial and temporal resolution, with an increased availability in clinical practice. 4D-CT allows simultaneous visualization of bone morphology and joint kinematics. This unique combination makes it an ideal tool to evaluate functional disorders of the musculoskeletal system. In the lower limb, 4D-CT has been used to diagnose femoroacetabular impingement, patellofemoral, ankle and subtalar joint instability, or reduced range of motion. 4D-CT has also been used to demonstrate the effect of surgery, mainly on patellar instability. 4D-CT will need further research and validation before it can be widely used in clinical practice. We believe, however, it is here to stay, and will become a reference in the diagnosis of lower limb conditions and the evaluation of treatment options. Cite this article:
The aim of this study was to define the complications and long-term outcome following adolescent mid-shaft clavicular fracture. We retrospectively reviewed a consecutive series of 677 adolescent fractures in 671 patients presenting to our region (age 13 to 17 years) over a ten-year period (2009 to 2019). Long-term patient-reported outcomes (abbreviated version of the Disabilities of the Arm, Shoulder and Hand (QuickDASH) score and EuroQol five-dimension three-level (EQ-5D-3L) quality of life score) were undertaken at a mean of 6.4 years (1.2 to 11.3) following injury in severely displaced mid-shaft fractures (Edinburgh 2B) and angulated mid-shaft fractures (Edinburgh 2A2) at a minimum of one year post-injury. The median patient age was 14.8 years (interquartile range (IQR) 14.0 to 15.7) and 89% were male (n = 594/671).Aims
Methods
The aim of this study was to determine whether national standards of best practice are associated with improved health-related quality of life (HRQoL) outcomes in hip fracture patients. This was a multicentre cohort study conducted in 20 acute UK NHS hospitals treating hip fracture patients. Patients aged ≥ 60 years treated operatively for a hip fracture were eligible for inclusion. Regression models were fitted to each of the “Best Practice Tariff” indicators and overall attainment. The impact of attainment on HRQoL was assessed by quantifying improvement in EuroQol five-dimension five-level questionnaire (EQ-5D-5L) from estimated regression model coefficients.Aims
Methods
