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: Bone Joint J 2021;103-B(9):1442–1448.

Aims

This study reports updates the previously published two-year clinical, functional, and radiological results of a group of patients who underwent transfibular total ankle arthroplasty (TAA), with follow-up extended to a minimum of five years.

Aims

The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?

Aims

The aim of this study was to establish a reliable method for producing 3D reconstruction of sonographic callus.

Aims

A multicentre, randomized, clinician-led, pragmatic, parallel-group orthopaedic trial of two surgical procedures was set up to obtain high-quality evidence of effectiveness. However, the trial faced recruitment challenges and struggled to maintain recruitment rates over 30%, although this is not unusual for surgical trials. We conducted a qualitative study with the aim of gathering information about recruitment practices to identify barriers to patient consent and participation to an orthopaedic trial.

Matrix metalloproteinases (MMPs), responsible for extracellular matrix remodelling and angiogenesis, might play a major role in the response of the growth plate to detrimental loads that lead to overuse injuries in young athletes. In order to test this hypothesis, human growth plate chondrocytes were subjected to mechanical forces equal to either physiological loads, near detrimental or detrimental loads for two hours. In addition, these cells were exposed to physiological loads for up to 24 hours. Changes in the expression of MMPs -2, -3 and -13 were investigated. We found that expression of MMPs in cultured human growth plate chondrocytes increases in a linear manner with increased duration and intensity of loading. We also showed for the first time that physiological loads have the same effect on growth plate chondrocytes over a long period of time as detrimental loads applied for a short period. These findings confirm the involvement of MMPs in overuse injuries in children. We suggest that training programmes for immature athletes should be reconsidered in order to avoid detrimental stresses and over-expression of MMPs in the growth plate, and especially to avoid physiological loads becoming detrimental. Cite this article: Bone Joint J 2013;95-B:568–73

Aims

This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA).

Aims

The aim of this study is to define a core outcome set (COS) to allow consistency in outcome reporting amongst studies investigating the management of orthopaedic treatment in children with spinal dysraphism (SD).

Aims

Psychoeducative prehabilitation to optimize surgical outcomes is relatively novel in spinal fusion surgery and, like most rehabilitation treatments, they are rarely well specified. Spinal fusion patients experience anxieties perioperatively about pain and immobility, which might prolong hospital length of stay (LOS). The aim of this prospective cohort study was to determine if a Preoperative Spinal Education (POSE) programme, specified using the Rehabilitation Treatment Specification System (RTSS) and designed to normalize expectations and reduce anxieties, was safe and reduced LOS.

A prospective study of 33 civilian parachutists with 41 injuries is presented. Because the training for civilians is less rigorous than that for military parachutists, the hospital admission rate for severe injuries was high (81.8%). Most injuries occurred during landing and the ankle was most frequently involved. The types and possible mechanisms of injury are discussed, as well as recommendations for modifying the civilian training programme

Of 66 recruits who sustained stress fractures during basic training and returned to training after a period of rest, seven (10.6%) suffered recurrent fractures within one year. None of the recurrences was at the original anatomical site. All of the recruits with recurrent stress fractures had had at least one of their initial stress fractures in the femur. This suggests that a femoral stress fracture carries a high risk of recurrence at other sites

One of the most important factors in the rehabilitation of the amputee is the preparation of the patient and stump for limb fitting and training. The different procedures for the upper and lower extremities are described. Emphasis is laid on the importance of early reassurance and rehabilitation whenever possible. Patients unavoidably immobilised for long periods require general physical reconditioning before limb fitting and training can be undertaken. Special care is needed to avoid the upper limb amputee's becoming dependent on the surviving hand and using the artificial limb only for its cosmetic effect

Aims

The aim of this study was to investigate the potentially increased risk of dislocation in patients with neurological disease who sustain a femoral neck fracture, as it is unclear whether they should undergo total hip arthroplasty (THA) or hemiarthroplasty (HA). A secondary aim was to investgate whether dual-mobility components confer a reduced risk of dislocation in these patients.

During a four-month period we observed 12 stress fractures of the inferior pubic ramus in 11 military recruits undergoing basic training. Eleven of these were in women. This high number was considered to be caused by the introduction of mixed training of male and female recruits; this forces women to increase their stride length when marching. The presenting symptom was chronic groin pain which failed to settle with rest, and the clinical diagnoses were confirmed by radiographs in all but one patient who was diagnosed by . 99m. Tc bone scanning. Since the required stride length has been reduced there have been no new cases of stress fracture of the pelvis