Aims. Adult spinal deformity (ASD) surgery can reduce pain and disability. However, the actual surgical efficacy of ASD in doing so is far from desirable, with frequent complications and limited improvement in quality of life. The accurate prediction of surgical outcome is crucial to the process of clinical decision-making. Consequently, the aim of this study was to develop and validate a model for predicting an ideal surgical outcome (ISO) two years after ASD surgery. Methods. We conducted a retrospective analysis of 458 consecutive patients who had undergone spinal fusion surgery for ASD between January 2016 and June 2022. The outcome of interest was achievement of the ISO, defined as an improvement in patient-reported outcomes exceeding the minimal clinically important difference, with no postoperative complications. Three machine-learning (ML) algorithms – LASSO, RFE, and Boruta – were used to identify key variables from the collected data. The dataset was randomly split into training (60%) and test (40%) sets. Five different ML models were trained, including logistic regression, random forest, XGBoost, LightGBM, and multilayer perceptron. The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). Results. The analysis included 208 patients (mean age 64.62 years (SD 8.21); 48 male (23.1%), 160 female (76.9%)). Overall, 42.8% of patients (89/208) achieved the ideal surgical outcome. Eight features were identified as key variables affecting prognosis: depression, osteoporosis, frailty, failure of pelvic compensation, relative functional cross-sectional area of the paraspinal muscles, postoperative sacral slope, pelvic tilt match, and sagittal age-adjusted score match. The best prediction model was LightGBM, achieving the following performance metrics: AUROC 0.888 (95% CI 0.810 to 0.966); accuracy 0.843; sensitivity 0.829; specificity 0.854; positive predictive value 0.806; and negative predictive value 0.872. Conclusion. In this prognostic study, we developed a machine-learning model that accurately predicted outcome after surgery for ASD. The model is built on routinely modifiable indicators, thereby facilitating its integration into clinical practice to promote optimized decision-making. Cite this article: Bone Joint J 2025;107-B(3):337–345

Aims. To determine the major risk factors for unplanned reoperations (UROs) following corrective surgery for adult spinal deformity (ASD) and their interactions, using machine learning-based prediction algorithms and game theory. Methods. Patients who underwent surgery for ASD, with a minimum of two-year follow-up, were retrospectively reviewed. In total, 210 patients were included and randomly allocated into training (70% of the sample size) and test (the remaining 30%) sets to develop the machine learning algorithm. Risk factors were included in the analysis, along with clinical characteristics and parameters acquired through diagnostic radiology. Results. Overall, 152 patients without and 58 with a history of surgical revision following surgery for ASD were observed; the mean age was 68.9 years (SD 8.7) and 66.9 years (SD 6.6), respectively. On implementing a random forest model, the classification of URO events resulted in a balanced accuracy of 86.8%. Among machine learning-extracted risk factors, URO, proximal junction failure (PJF), and postoperative distance from the posterosuperior corner of C7 and the vertical axis from the centroid of C2 (SVA) were significant upon Kaplan-Meier survival analysis. Conclusion. The major risk factors for URO following surgery for ASD, i.e. postoperative SVA and PJF, and their interactions were identified using a machine learning algorithm and game theory. Clinical benefits will depend on patient risk profiles. Cite this article: Bone Joint Res 2023;12(4):245–255

Aims. The T1 pelvic angle (T1PA) provides a consistent global measure of sagittal alignment independent of compensatory mechanisms and positional changes. However, it may not explicitly reflect alignment goals that correlate with a lower risk of complications. This study assessed the value of T1PA in achieving sagittal alignment goals in patients with an adult spinal deformity (ASD). Methods. Patients aged ≥ 18 years who had undergone surgery for ASD and had complete baseline data and at least two-year postoperative, radiological, and health-related quality of life follow-up were included. A total of 596 patients met the inclusion criteria (mean age 61.5 years (SD 13.4); 78.8% females; mean BMI 27.8 kg/m. 2. (SD 5.9); mean Charlson Comorbidity Index 1.9 (SD 1.8)). The primary outcome was development of mechanical complications. Cohorts were based on postoperative T1PA (T1PA < 10° or > 30° = unfavourable vs T1PA 10° to 30° = favourable). Adjustments for confounders with separate analyses were done using multivariable logistic regression analysis. Results. Postoperatively, 363 patients (60.9%) had a favourable T1PA and 233 (39.1%) did not. Those with a favourable T1PA had a significantly higher rate of proximal junctional kyphosis (PJK) than those with an unfavourable T1PA (52.0% vs 48.0%; p = 0.035). Having adjusted for confounders, those with a favourable T1PA had a decreased risk of proximal junctional kyphosis (OR 0.532 (95% CI 0.288 to 0.985); p = 0.045). Conclusion. The T1PA gives valuable information about global alignment, but fails to recognize and adjust for the great variation in patients with ASD. As such, we recommend combining the T1PA with alternative alignment strategies to better inform clinical care. Cite this article: Bone Joint J 2025;107-B(3):346–352

Aims. Postoperative complication rates remain relatively high after adult spinal deformity (ASD) surgery. The extent to which modifiable patient-related factors influence complication rates in patients with ASD has not been effectively evaluated. The aim of this retrospective cohort study was to evaluate the association between modifiable patient-related factors and complications after corrective surgery for ASD. Methods. ASD patients with two-year data were included. Complications were categorized as follows: any complication, major, medical, surgical, major mechanical, major radiological, and reoperation. Modifiable risk factors included smoking, obesity, osteoporosis, alcohol use, depression, psychiatric diagnosis, and hypertension. Patients were stratified by the degree of baseline deformity (low degree of deformity (LowDef)/high degree of deformity (HighDef): below or above 20°) and age (Older/Younger: above or below 65 years). Complication rates were compared for modifiable risk factors in each age/deformity group, using multivariable logistic regression analysis to adjust for confounders. Results. A total of 480 ASD patients met the inclusion criteria. By two years, complication rates were 72% ≥ one complication, 28% major, 21% medical, 27% surgical, 11% major radiological, 8% major mechanical, and 22% required reoperation. Younger LowDef patients with osteoporosis were more likely to suffer either a major mechanical (odds ratio (OR) 5.9 (95% confidence interval (CI) 1.1 to 36.9); p = 0.048) or radiological complication (OR 7.0 (95% CI 1.9 to 25.9); p = 0.003). Younger HighDef patients were much more likely to develop complications if obese, especially major mechanical complications (OR 2.8 (95% CI 1.1 to 8.6); p = 0.044). Older HighDef patients developed more complications when diagnosed with depression, including major radiological complications (OR 3.5 (95% CI 1.1 to 10.6); p = 0.033). Overall, a diagnosis of depression proved to be a risk factor for the development of major radiological complications (OR 2.4 (95% CI 1.3 to 4.5); p = 0.005). Conclusion. Certain modifiable patient-related factors, especially osteoporosis, obesity, and mental health status, are associated with an increased risk of complications after surgery for spinal deformity. Surgeons should look for these conditions when assessing a patient for surgery, and optimize them to the fullest extent possible before proceeding to surgical correction so as to minimize the prospect of postoperative morbidity. Cite this article: Bone Joint J 2022;104-B(11):1249–1255

The February 2025 Spine Roundup³⁶⁰ looks at: The effect of thoraco-lumbo-sacral orthosis wear time and clinical risk factors on curve progression for individuals with adolescent idiopathic scoliosis; Does operative level impact dysphagia severity after anterior cervical discectomy and fusion? A multicentre prospective analysis; Who gets better after surgery for degenerative cervical myelopathy? A responder analysis from the multicentre Canadian spine outcomes and research network; Do obese patients have worse outcomes in adult spinal deformity surgeries?; An update to the management of spinal cord injury; Classifying thoracolumbar injuries; High- versus moderate-density constructs in adolescent idiopathic scoliosis are equivalent at two years; Romosozumab for protecting against proximal junctional kyphosis in deformity surgery.

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.