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:
Hip instability following total hip arthroplasty in treatment of intracapsular neck of femur fractures is reported at 8–11%. Utilising the principle of a small articulation to minimize the problems of wear coupled with a large articulation, dual-mobility total hip arthroplasty prostheses stabilise the hip further than conventional fixed-bearing designs. The aim of this study is to compare the rate of dislocation and complication between standard fixed-bearing and dual-mobility prostheses for the treatment of intracapsular neck of femur fractures. A four-year retrospective review in a large district general hospital was completed. All cases of intracapsular neck of femur fractures treated with total hip arthroplasty were identified through the theatre logbooks. Patient's operative and clinical notes were retrospectively reviewed to collect data.Abstract
Objectives
Methods
Balloon kyphoplasty (BKP) is a minimally invasive surgical technique used to correct kyphosis and vertebral compression fractures. BKP uses cement to fill a void created by the inflation of a balloon in a vertebra, it can be used as an alternative to vertebroplasty to reduce cement extravasation. Issues such as poor inter digitisation of the cement and the trabecular bone can arise with the BKP method. This can be due to a compacted layer created during the procedure which can cause complications post-surgery. The primary aim of this study was to investigate alternative cement application methods which could improve the mechanical strength of the bone-cement interface. Three alternative methods were investigated, and cylindrical bone-cement specimens were created for all methods (BKP and three alternatives). An important part of this study was to replicate the compacted layer created by the inflation of the balloon tamp in BKP. Synthetic trabecular bone specimens (Sawbones®, Pacific Research Laboratories, Vashon Island, Washington, USA) were pre-loaded in compression and the resultant compacted layers were found to replicate the compacted layers found in surgery. Mechanical testing was carried out with an MTS Model 858 Bionix® Servohydraulic load frame using static tensile and torsion loads. Static tests revealed that two of the three alternative methods were an improvement on BKP, with a high statistical significance in relation to the mechanical performance of the bone-cement interface (P < 0.001). This data illustrates the potential to improve the standard BKP technique, in terms of bone-cement interface performance.
To compare the degree of deformity correction achieved using cobalt chromium versus titanium alloy rods in patients with Adolescent Idiopathic Scoliosis. A retrospective comparison of two cohorts of patients with Adolescent Idiopathic Scoliosis treated with posterior segmental pedicle screw fixation using either Titanium or Cobalt Chromium rods. The radiographs of 50 patients treated before 2009 (Ti group) and 50 patients after 2009 (CoCr group) were reviewed for changes in: Main Coronal Curvature Sagittal Balance (C7 Plumb Line) Kyphosis (T5-12)Aim:
Method:
Deep infection following paediatric spinal deformity surgery is a serious complication, which can also result in increased length of stay and significant cost implications. Our objective was to reduce deep infection rates following spinal deformity surgery. All paediatric patients undergoing spinal deformity procedures between 2008 and 2010 (group 1) were prospectively followed up and deep infection rates recorded. In 2010, a review of infection rates necessitated a change in pre-operative, peri-operative, and post-operative practice. A scoliosis wound care pathway was implemented, which involved insertion of drains to protect wounds, strict dressing management performed by a Spinal Nurse Practitioner, and a telephone helpline for concerns about wound care and general peri-operative scoliosis care. The use of betadine wash and local antibiotic application intra-operatively were other measures instigated later in this period. All paediatric patients undergoing surgery between 2011 and 2012 (group 2) were then followed up and differences in infection rates between the two groups were analysed.Aim:
Method:
To determine if patients with coronal plane deformity in the lumbar spine have a higher grade of lumbar spine subtype compared to controls. This was a retrospective case/control study based on a review of radiological investigations in 250 patients aged over 40 years who had standing plain film lumbar radiographs with hips present. Measurements of lumbar coronal plane angle, lumbar lordosis, sacral slope, pelvic tilt and pelvic incidence were obtained. “Cases” with degenerative scoliosis (n=125) were defined as patients with a lumbar coronal plane angle of >10°. Lumbar spine subtype was categorised (1–4) using the Roussouly classification. Lumbar spine subtype was dichotomised into low (type 1,2) or high (type 3,4). Prevalence of lumbar spine subtype in cases versus controls was compared using the Chi squared test. Pelvic incidence was compared using an unpaired T-test. Predictors of lumbar coronal plane angle were identified using stepwise multiple regression. Significance was accepted at P<0.05.Aim:
Method:
Recent guidelines have been published by the Association of Neurophysiological Scientists / British Society for Clinical Neurophysiology (ANS/BSCN) regarding the use of intra-operative neurophysiological monitoring (IOM) during spinal deformity procedures. We present our unit's experience with IOM and the compliance with national guidelines. All patients undergoing intra-operative spinal cord monitoring during adult and paediatric spinal deformity surgery between Jan 2009 and Dec 2012 were prospectively followed. The use of somatosensory-evoked potentials (SSEPs) and motor-evoked potentials (MEPs) was recorded and monitoring outcomes were compared to post-operative clinical neurological outcomes. Compliance with the national ANS/BSCN guidelines was assessed.Aim:
Method:
In a time of limited resources, the debate continues
over which types of hip prosthesis are clinically superior and more
cost-effective. Orthopaedic surgeons increasingly need robust economic
evidence to understand the full value of the operation, and to aid
decision making on the ‘package’ of procedures that are available
and to justify their practice beyond traditional clinical preference. In this paper we explore the current economic debate about the
merits of cemented and cementless total hip replacement, an issue
that continues to divide the orthopaedic community. Cite this article:
This study sought to determine whether the functional outcome of two common spinal operations could be improved by a programme of post-operative rehabilitation and/or an educational booklet each compared with usual care. This was a multi-centre, factorial, randomised controlled trial on the post operative management of spinal surgery patients, with randomisation stratified by surgeon and operative procedure. The study compared the effectiveness of a rehabilitation programme and an education booklet for the postoperative management of patients undergoing discectomy or lateral nerve root decompression surgery, each compared with “usual care” using a 2 × 2 factorial design, randomising patient to four groups; rehabilitation-only, booklet-only, rehabilitation-plus-booklet, and usual care only. The primary outcome measure was the Oswestry Disability Index (ODI) at 12 months, with secondary outcomes including visual analogue scale measures of back and leg pain. An economic analysis was also performed.Introduction
Methods
Lag screw cut-out following fixation of unstable intertrochanteric fractures in osteoporotic bone remains an unsolved challenge. A novel new device is the X-Bolt which is an expanding type bolt that may offer superior fixation in osteoporotic bone compared to the standard DHS screw type device. The aim of this study was to test if there was a difference in cut-out using the X-Bolt implant compared with the standard DHS systemIntroduction
Aims
Evaluate the outcome and complications of anterior pubic symphysis plating in the stabilisation of traumatic anterior pelvic ring injuries. All patients who underwent pubic symphysis plating in a tertiary referral unit were studied. Fracture classification, type of fixation, complications, and incidence of metalwork failure were recorded.Aim
Methods
Mortality rates following hip fracture are high. There are several scoring systems which aim to predict morbidity and mortality in hospital in-patients. The Nottingham Hip Fracture Score (NHFS) was devised to predict 30 day mortality following hip fracture. All patients with hip fractures admitted over a 6 month period were reviewed. The NHFS was calculated for each patient and any associations between patient factors, NHFS, and outcome were investigated.Introduction
Methods
Malnutrition has been suggested to increase the risk of falls in frail elderly. It has been hypothesised that elderly, orthopaedic trauma patients may be malnourished. We conducted an observational study to identify if this was the case. 30 trauma patients (? 65 years) admitted for surgical intervention for a fracture were recruited. Consent/ethical approval was obtained. Serum markers (LFTs, CRP, U&Es, FBC, magnesium), anthropometric measurements (triceps skin-fold thickness [TSF], mid-arm circumference [MAC], body mass index [BMI]) and short form mini-nutritional assessment (MNA-SF®) were carried out at presentation and at 3 months post-operation. Serum markers were also repeated at day 1 and day 3 post-operation.Background
Methods
Acetabular fractures are a challenging problem. It has been published that outcome is dependent upon the type of fracture, the reduction of the fracture and concomitant injuries. The end-points of poor outcome include avascular necrosis of the femoral head, osteoarthritis. However, we lack definitive statistics and so counselling patients on prognosis could be improved. In order to achieve this, more outcome studies from tertiary referral centres are required. We present the first long term follow up from a large tertiary referral centre in Ireland. We identified all patients who were ten years following open reduction and internal fixation of an acetbular fracture in our centre. We invited all of these patients to attend the hospital for clinical and radiographic follow-up. As part of this, three scoring systems were completed for each patient; the Short-form 36 health survey (SF36), the Merle d'Aubigné score and the Short Musculoskeletal Functional Assessment (SMFA).Introduction
Methods
Acetabular fractures are a challenging problem. It has been published that outcome is dependent upon the type of fracture, the reduction of the fracture and concomitant injuries. The end-points of poor outcome include avascular necrosis of the femoral head, osteoarthritis. However, we lack definitive statistics and so counselling patients on prognosis could be improved. In order to achieve this, more outcome studies from tertiary referral centres are required. We present the first long term follow up from a large tertiary referral Centre in Ireland. We identified all patients who were ten years following open reduction and internal fixation of an acetbular fracture in our centre. We invited all of these patients to attend the hospital for clinical and radiographic follow-up. As part of this, three scoring systems were completed for each patient; the Short-form 36 health survey (SF36), the Merle d'Aubigné score and the Short Musculoskeletal Functional Assessment (SMFA).Introduction
Methods
Mortality rates following hip fracture are high. There are several scoring systems which aim to predict morbidity and mortality in hospital in-patients. The Nottingham Hip Fracture Score (NHFS) was devised to predict 30 day mortality following hip fracture. Methods: All patients with hip fractures admitted over a 6 month period were reviewed. The NHFS was calculated for each patient and any associations between patient factors, NHFS, and outcome were investigated. 160 patients were admitted during the study period. 148 patients were followed up for an average of 8.5 months. 9.5% patients died within 30 days. The mean NHFS was 4.6. NHFS showed a significant correlation with overall mortality and positive association with both 30 day mortality and length of stay. Delay to operation was not associated with increased mortality, but increasing age was positively correlated to 30 day mortality.Introduction
Results
There is controversy regarding the optimum method of stabilising traumatic anterior pelvic ring injuries. This study aimed to evaluate the role of pubic symphysis plating. All patients who underwent pubic symphysis plating in a regional pelvic and acetabular unit were studied. Fracture classification, type of fixation, complications, and incidence of metalwork failure were recorded. Out of 178 consecutive patients, 159 (89%) were studied for a mean of 37.6 months. There were 121 males and 38 females (mean age 43 years). Symphysis pubic fixation was performed in 100 AO-OTA type B and 59 type C injuries using a Matta symphyseal plate (n=92), reconstruction plate (n=65), or DCP (n=2). Supplementary posterior pelvic fixation was performed in 102 patients. 5 patients required revision for failure of fixation or symptomatic instability of the pubic symphysis. A further 7 patients had metalwork removed for other reasons. Metalwork breakage occurred in 63 patients (40%). 62 of these 63 patients were asymptomatic and metalwork was left in situ.Methods
Results
Controversy exists whether a single proximal lateral tibia (PLT) locked plate is adequate for bicondylar fractures and whether the use of integral raft screws makes the use of bone graft less important. 57 consecutive patients who underwent reconstruction with a locked PLT plate were retrospectively reviewed. Radiographs were examined for operative reduction and subsequent loss of reduction. 55 patients were followed-up for an average of 27 weeks. Fractures were divided into unicondylar (Group 1, n=33) and bicondylar (Group 2, n=22). Union occurred in all patients, with no revisions or removal of metalwork at final follow-up. In 50 patients (88%), the fracture was reduced to within 2mm of anatomical. Articular surface collapse of >2mm occurred in three patients. Nine patients underwent bone grafting with no difference in outcome. A supplementary medial plate was used in three patients with a separate posteromedial fragment. Except for a separate posteromedial fragment, the use of a single locked PLT plate for bicondylar fractures allows union to occur without failure. With the use of integral raft screws, the need for bone graft is questionable. The short-term radiological results and complication rate of PLT locked plating is excellent.
There is minimal published data regarding the long-term functional outcome in pyogenic spinal infection. Previous studies have used heterogeneous, unreliable and non-validated measure instruments, or neurological outcome alone, yielding data that is difficult to interpret. We aim to assess long-term adverse outcome using standardised measures, Oswestry disability index (ODI) and MOS short form-36 (SF-36). All cases of pyogenic spinal infection presenting to a single institution managed operatively and non-operatively from 1994-2004 were retrospectively identified. Follow-up was by clinical review and standardised questionnaires. Inclusion in each case was on the basis of consistent clinical, imaging and microbiology criteria.Background
Methods
