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

Whether a combined anteroposterior fusion or a posterior-only fusion is more effective in the management of patients with Scheuermann’s kyphosis remains controversial. The aim of this study was to compare the radiological and clinical outcomes of these surgical approaches, and to evaluate the postoperative complications with the hypothesis that proximal junctional kyphosis would be more common in one-stage posterior-only fusion.

Aims

The timing of surgical fixation in spinal fractures is a contentious topic. Existing literature suggests that early stabilization leads to reduced morbidity, improved neurological outcomes, and shorter hospital stay. However, the quality of evidence is low and equivocal with regard to the safety of early fixation in the severely injured patient. This paper compares complication profiles between spinal fractures treated with early fixation and those treated with late fixation.

Continuous technical improvement in spinal surgical procedures, with the aim of enhancing patient outcomes, can be assisted by the deployment of advanced technologies including navigation, intraoperative CT imaging, and surgical robots. The latest generation of robotic surgical systems allows the simultaneous application of a range of digital features that provide the surgeon with an improved view of the surgical field, often through a narrow portal.

There is emerging evidence that procedure-related complications and intraoperative blood loss can be reduced if the new technologies are used by appropriately trained surgeons. Acceptance of the role of surgical robots has increased in recent years among a number of surgical specialities including general surgery, neurosurgery, and orthopaedic surgeons performing major joint arthroplasty. However, ethical challenges have emerged with the rollout of these innovations, such as ensuring surgeon competence in the use of surgical robotics and avoiding financial conflicts of interest. Therefore, it is essential that trainees aspiring to become spinal surgeons as well as established spinal specialists should develop the necessary skills to use robotic technology safely and effectively and understand the ethical framework within which the technology is introduced.

Traditional and more recently developed platforms exist to aid skill acquisition and surgical training which are described.

The aim of this narrative review is to describe the role of surgical robotics in spinal surgery, describe measures of proficiency, and present the range of training platforms that institutions can use to ensure they employ confident spine surgeons adequately prepared for the era of robotic spinal surgery.

Cite this article: Bone Joint J 2020;102-B(5):568–572.

Aims

Patients with multiple myeloma (MM) develop deposits in the spine which may lead to vertebral compression fractures (VCFs). Our aim was to establish which spinopelvic parameters are associated with the greatest disability in patients with spinal myeloma and VCFs.

The purpose of this study was to review the early results of a consecutive series of patients undergoing periac-etabular osteotomy (PAO) at Cappagh National Orthopaedic Hospital. The procedure was first carried out in 1998, and a total of 85 PAOs have been performed in 79 patients. The mean follow-up was 42 months (range 6-84 months). There were 72 females and 7 males with a mean age at the time of the operation of 22.9 years (range, 14-41 years). The preoperative diagnosis was developmental hip dysplasia in 80 hips, Legg-Calve-Perthes disease in one hip, congenital coxa vara in three hips, and slipped capital femoral epiphysis in one hip. The average Merle d’Aubigne score increased from 12.4 points preoperatively to 16 points at latest followup. The lateral center edge angle of Wiberg was between – 20 and +28 before surgery and was improved from 12 to 48 (average 30 degrees) following PAO. While, the anterior center edge angle of Lequesne and de Seze was between – 22 and +35 preoperatively and was improved by an average of 28 degrees (range, 17 – 40) postoperatively. The acetabular index angle decreased from an average of 24.8 preoperatively to 8.4 postoperatively. Clinical follow-up revealed that 77% of patients had no or mild pain, 33% of patients had a limp and 64% of patients were unlimited in physical activity, representing a markedly improved clinical outcome. Four patients underwent subsequent total hip arthroplasty. The short term results in this group of patients treated with PAO show reliable radiographic correction of deformity and improved clinical scores. The study reflects the learning curve associated with performing this procedure and the results that can be expected with a smaller clinical case-load than described in previous studies. We suggest that PAO may safely be carried out at a non-super-specialized institution provided the surgeons have sufficient experience and patients are selected appropriately.

This study assessed the frequency of acute injury to the spinal cord in Irish Rugby over a period of ten years, between 1995 and 2004. There were 12 such injuries; 11 were cervical and one was thoracic. Ten occurred in adults and two in schoolboys. All were males playing Rugby Union and the mean age at injury was 21.6 years (16 to 36). The most common mechanism of injury was hyperflexion of the cervical spine and the players injured most frequently were playing at full back, hooker or on the wing. Most injuries were sustained during the tackle phase of play. Six players felt their injury was preventable. Eight are permanently disabled as a result of their injury.

Study Design: A retrospective review of the functional outcome of neurologically intact patients with burst fractures of the first lumbar vertebra.

Objective: To assess the functional outcome of patients treated either surgically or conservatively following burst fractures of L1.

Methods: A retrospective review of 38 neurologically intact patients with burst fractures of L1 was performed. Follow-up clinical evaluation was obtained from 26 patients, eleven of whom were treated surgically and fifteen of whom were managed conservatively. Patients were assessed with regard to pain, employment status, ability to partake in recreational activities and their overall satisfaction with treatment. Radiographic evaluation of anterior body compression and vertebral kyphosis was performed at the time of injury. Computed tomography scanning of spinal canal compromise was also recorded at the time of injury. Subsequent recordings of vertebral kyphosis were assessed at the time of remobilisation and at 3-month follow-up evaluation.

Results: Mean follow-up time for the 26 patients was 43.02 months. At final clinical follow-up of the fifteen patients managed conservatively, 6 patients (40%) had little or no pain; 12 patients (80%) had returned to work with 6 (40%) stating that they had little or no restrictions in their ability to work; 8 patients (53%) had returned to the same level of recreational activity as prior to their injury with 7 (47%) stating they had little or no restrictions in their ability to participate in recreational activities. One patient (9%) reported being very dissatisfied with the operative treatment of their spine fracture.

No correlation was found between kyphotic deformity, extent of canal compromise and clinical outcome.

Conclusions: Non-operative management of burst fractures of the first lumbar vertebra is a very safe and effective method of treatment. It reduces hospitalisation time and avoids the costs and risk of surgery. Patients return to the functional activities of daily living quickly and have a better clinical outcome when compared with operative management.