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:
Although lumbosacral transitional vertebrae (LSTV) are well-documented, few large-scale studies have investigated thoracolumbar transitional vertebrae (TLTV) and spinal numerical variants. This study sought to establish the prevalence of numerical variants and to evaluate their relationship with clinical problems. A total of 1,179 patients who had undergone thoracic, abdominal, and pelvic CT scanning were divided into groups according to the number of thoracic and lumbar vertebrae, and the presence or absence of TLTV or LSTV. The prevalence of spinal anomalies was noted. The relationship of spinal anomalies to clinical symptoms (low back pain, Japanese Orthopaedic Association score, Roland-Morris Disability Questionnaire) and degenerative spondylolisthesis (DS) was also investigated.Aims
Methods
Cross-table lateral (CTL) radiographs are commonly used to measure acetabular component anteversion after total hip arthroplasty (THA). The CTL measurements may differ by > 10° from CT scan measurements but the reasons for this discrepancy are poorly understood. Anteversion measurements from CTL radiographs and CT scans are compared to identify spinopelvic parameters predictive of inaccuracy. THA patients (n = 47; 27 males, 20 females; mean age 62.9 years (SD 6.95)) with preoperative spinopelvic mobility, radiological analysis, and postoperative CT scans were retrospectively reviewed. Acetabular component anteversion was measured on postoperative CTL radiographs and CT scans using 3D reconstructions of the pelvis. Two cohorts were identified based on a CTL-CT error of ≥ 10° (n = 11) or < 10° (n = 36). Spinopelvic mobility parameters were compared using independent-samples Aims
Methods
Spinal deformity surgery carries the risk of neurological injury. Neurophysiological monitoring allows early identification of intraoperative cord injury which enables early intervention resulting in a better prognosis. Although multimodal monitoring is the ideal, resource constraints make surgeon-directed intraoperative transcranial motor evoked potential (TcMEP) monitoring a useful compromise. Our experience using surgeon-directed TcMEP is presented in terms of viability, safety, and efficacy. We carried out a retrospective review of a single surgeon’s prospectively maintained database of cases in which TcMEP monitoring had been used between 2010 and 2017. The upper limbs were used as the control. A true alert was recorded when there was a 50% or more loss of amplitude from the lower limbs with maintained upper limb signals. Patients with true alerts were identified and their case history analyzed.Aims
Methods
High-grade dysplastic spondylolisthesis is a disabling disorder for which many different operative techniques have been described. The aim of this study is to evaluate Scoliosis Research Society 22-item (SRS-22r) scores, global balance, and regional spino-pelvic alignment from two to 25 years after surgery for high-grade dysplastic spondylolisthesis using an all-posterior partial reduction, transfixation technique. SRS-22r and full-spine lateral radiographs were collected for the 28 young patients (age 13.4 years (SD 2.6) who underwent surgery for high-grade dysplastic spondylolisthesis in our centre (Scottish National Spinal Deformity Service) between 1995 and 2018. The mean follow-up was nine years (2 to 25), and one patient was lost to follow-up. The standard surgical technique was an all-posterior, partial reduction, and S1 to L5 transfixation screw technique without direct decompression. Parameters for segmental (slip percentage, Dubousset’s lumbosacral angle) and regional alignment (pelvic tilt, sacral slope, L5 incidence, lumbar lordosis, and thoracic kyphosis) and global balance (T1 spino-pelvic inclination) were measured. SRS-22r scores were compared between patients with a balanced and unbalanced pelvis at final follow-up.Aims
Methods
To determine the effectiveness of prone traction radiographs in predicting postoperative slip distance, slip angle, changes in disc height, and lordosis after surgery for degenerative spondylolisthesis of the lumbar spine. A total of 63 consecutive patients with a degenerative spondylolisthesis and preoperative prone traction radiographs obtained since 2010 were studied. Slip distance, slip angle, disc height, segmental lordosis, and global lordosis (L1 to S1) were measured on preoperative lateral standing radiographs, flexion-extension lateral radiographs, prone traction lateral radiographs, and postoperative lateral standing radiographs. Patients were divided into two groups: posterolateral fusion or posterolateral fusion with interbody fusion.Aims
Methods
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. A retrospective review of patients treated surgically for Scheuermann’s kyphosis between 2006 and 2014 was performed. A total of 62 patients were identified, with 31 in each group. Parameters were compared to evaluate postoperative outcomes using chi-squared tests, independent-samples Aims
Methods
The aim of this study was to assess whether supine flexibility predicts the likelihood of curve progression in patients with adolescent idiopathic scoliosis (AIS) undergoing brace treatment. This was a retrospective analysis of patients with AIS prescribed with an underarm brace between September 2008 to April 2013 and followed up until 18 years of age or required surgery. Patients with structural proximal curves that preclude underarm bracing, those who were lost to follow-up, and those who had poor compliance to bracing (<16 hours a day) were excluded. The major curve Cobb angle, curve type, and location were measured on the pre-brace standing posteroanterior (PA) radiograph, supine whole spine radiograph, initial in-brace standing PA radiograph, and the post-brace weaning standing PA radiograph. Validation of the previous in-brace Cobb angle regression model was performed. The outcome of curve progression post-bracing was tested using a logistic regression model. The supine flexibility cut-off for curve progression was analyzed with receiver operating characteristic curve.Aims
Methods
The aim of this study was to determine the influence of developmental spinal stenosis (DSS) on the risk of re-operation at an adjacent level. This was a retrospective study of 235 consecutive patients who had undergone decompression-only surgery for lumbar spinal stenosis and had a minimum five-year follow-up. There were 106 female patients (45.1%) and 129 male patients (54.9%), with a mean age at surgery of 66.8 years (Aims
Patients and Methods
The aim of this study was to compare the peak pull-out force
(PPF) of pedicle-lengthening screws (PLS) and traditional pedicle
screws (TPS) using instant and cyclic fatigue testing. A total of 60 lumbar vertebrae were divided into six groups:
PLS submitted to instant pull-out and fatigue-resistance testing
(groups A1 and A2, respectively), TPS submitted to instant pull-out
and fatigue-resistance testing (groups B1 and B2, respectively)
and PLS augmented with 2 ml polymethylmethacrylate, submitted to
instant pull-out and fatigue-resistance testing (groups C1 and C2,
respectively). The PPF and normalized PPF (PPFn) for bone mineral density
(BMD) were compared within and between all groups.Aims
Materials and Methods
Intraoperative 3D navigation (ION) allows high accuracy to be achieved in spinal surgery, but poor workflow has prevented its widespread uptake. The technical demands on ION when used in patients with adolescent idiopathic scoliosis (AIS) are higher than for other more established indications. Lean principles have been applied to industry and to health care with good effects. While ensuring optimal accuracy of instrumentation and safety, the implementation of ION and its associated productivity was evaluated in this study for AIS surgery in order to enhance the workflow of this technique. The aim was to optimize the use of ION by the application of lean principles in AIS surgery. A total of 20 consecutive patients with AIS were treated with ION corrective spinal surgery. Both qualitative and quantitative analysis was performed with real-time modifications. Operating time, scan time, dose length product (measure of CT radiation exposure), use of fluoroscopy, the influence of the reference frame, blood loss, and neuromonitoring were assessed.Aims
Methods
Tuberculosis (TB) remains endemic in many parts
of the developing world and is increasingly seen in the developed world
due to migration. A total of 1.3 million people die annually from
the disease. Spinal TB is the most common musculoskeletal manifestation,
affecting about 1 to 2% of all cases of TB. The coexistence of HIV,
which is endemic in some regions, adds to the burden and the complexity
of management. This review discusses the epidemiology, clinical presentation,
diagnosis, impact of HIV and both the medical and surgical options
in the management of spinal TB. Cite this article:
Spinal tuberculosis (TB) remains an important concern. Although spinal TB often has sequelae such as myelopathy after treatment, the predictive factors affecting such unfavourable outcomes are not yet established. We investigated the clinical manifestations and predictors of unfavourable treatment outcomes in patients with spinal TB. We performed a multicentre retrospective cohort study of patients with spinal TB. Unfavourable outcome was defined according to previous studies. The prognostic factors for unfavourable outcomes as the primary outcome were determined using multivariable logistic regression analysis and a linear mixed model was used to compare time course of inflammatory markers during treatment. A total of 185 patients were included, of whom 59 patients had unfavourable outcomes.Aims
Patients and Methods
Although we often encounter patients with an aortic aneurysm
who also have diffuse idiopathic skeletal hyperostosis (DISH), there
are no reports to date of an association between these two conditions
and the pathogenesis of DISH remains unknown. This study therefore
evaluated the prevalence of DISH in patients with a thoracic aortic
aneurysm (AA). The medical records of 298 patients who underwent CT scans for
a diagnosis of an AA or following high-energy trauma were retrospectively
examined. A total of 204 patients underwent surgery for an AA and
94 had a high-energy injury and formed the non-AA group. The prevalence
of DISH was assessed on CT scans of the chest and abdomen and the
relationship between DISH and AA by comparison between the AA and
non-AA groups.Aims
Patients and Methods
This study aimed to evaluate the incidence and prognosis of patients with spinal metastasis as the initial manifestation of malignancy (SM-IMM). We retrospectively reviewed the electronic medical records of 338 patients who underwent surgical treatment for metastatic spinal disease. The enrolled patients were divided into two groups. The SM-IMM group included patients with no history of malignancy whose site of primary malignancy was diagnosed after the identification of spinal metastasis. The other group included patients with a history of treatment for primary malignancy who then developed spinal metastasis (SM-DTM). The incidence of SM-IMM by site of primary malignancy was calculated. The difference between prognoses after surgical treatment for SM-IMM and SM-DTM was established.Aims
Patients and Methods
