Citations

BACKGROUND AND OBJECTIVES: Cervical disk arthroplasty (CDA) offers the advantage of motion preservation in the treatment of focal cervical pathology. At present, implant sizing is performed using subjective tactile feedback and imaging of trial cages. This study aims to construct interpretable machine learning (IML) models to accurately predict postoperative range of motion (ROM) and identify the optimal implant sizes that maximize ROM in patients undergoing CDA. METHODS: Adult patients who underwent CDA for single-level disease from 2012 to 2020 were identified. Patient demographics, comorbidities, and outcomes were collected, including symptoms, examination findings, subsidence, and reoperation. Affected disk height, healthy rostral disk height, and implant height were collected at sequential time points. Linear regression and IML models, including bagged regression tree, bagged multivariate adaptive regression spline, and k-nearest neighbors, were used to predict ROM change. Model performance was assessed by calculating the root mean square error (RMSE) between predicted and actual changes in ROM in the validation cohort. Variable importance was assessed using RMSE loss. Area under the curve analyses were performed to identify the ideal implant size cutoffs in predicting improved ROM. RESULTS: Forty-seven patients were included. The average RMSE between predicted and actual ROM was 7.6° (range: 5.8-10.1) in the k-nearest neighbors model, 7.8° (range: 6.5-10.0) in the bagged regression tree model, 7.8° (range: 6.2-10.0) in the bagged multivariate adaptive regression spline model, and 15.8° (range: 14.3-17.5°) in a linear regression model. In the highest-performing IML model, graft size was the most important predictor with RMSE loss of 6.2, followed by age (RMSE loss = 5.9) and preoperative caudal disk height (RMSE loss = 5.8). Implant size at 110% of the normal adjacent disk height was the optimal cutoff associated with improved ROM. CONCLUSION: IML models can reliably predict change in ROM after CDA within an average of 7.6 degrees of error. Implants sized comparably with the healthy adjacent disk may maximize ROM.

BACKGROUND AND OBJECTIVES: Enhanced recovery after surgery (ERAS) protocols aim to optimize patient outcomes by reducing the surgical stress response, expediting recovery, and reducing care costs. We aimed to evaluate the impact of implementing ERAS protocols on the perioperative surgical outcomes and financial implications associated with spine surgeries. METHODS: A systematic review and meta-analysis of peer-reviewed studies directly comparing outcome differences between spine surgeries performed with and without utilization of ERAS pathways was conducted along Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. RESULTS: Of 676 unique articles identified, 59 with 15 198 aggregate patients (7748 ERAS; 7450 non-ERAS) were included. ERAS-treated patients had shorter operative times (mean difference [MD]: 10.2 mins; P < .01), shorter hospitalizations (MD: 1.41 days, P < .01), fewer perioperative complications (relative risk [RR] = 0.64, P < .01), lower postoperative opioid use (MD of morphine equivalent dose: 164.36 mg; P < .01), and more rapid mobilization/time to first out-of-bed ambulation (MD: 0.92 days; P < .01). Spine surgeries employing ERAS were also associated with lower total costs (MD: $1140.26/patient; P < .01), especially in the United States (MD: $2869.11/patient, P < .01) and lower postoperative visual analog pain scores (MD = 0.56, P < .01), without any change in odds of 30-day readmission (RR: 0.80, P = .13) or reoperation (RR: 0.88, P = .60). Subanalyses based on the region of spine showed significantly lower length of stay in both cervical and lumbar surgeries implementing ERAS. Type of procedure showed a significantly lesser time-to-initiate mobilization in fusion surgeries using ERAS protocols compared with decompression. CONCLUSION: The present meta-analysis indicates that current literature supports ERAS implementation as a means of reducing care costs and safely accelerating hospital discharge for patients undergoing spine surgery.

OBJECTIVE The literature on non–small cell lung cancer (NSCLC) brain metastases (BMs) managed using stereotactic radiosurgery (SRS) relies mainly on single-institution studies or randomized controlled trials (RCTs). There is a literature gap on clinical and radiological outcomes of SRS for NSCLC metastases in real-world practice. The objective of this study was to benchmark mortality and progression outcomes in patients undergoing SRS for NSCLC BMs and identify risk factors for these outcomes using a national quality registry. METHODS The SRS Registry of the NeuroPoint Alliance was used for this study. This registry included patients from 16 enrolling sites who underwent SRS from 2017 to 2022. Data are prospectively collected without a prespecified research purpose. The main outcomes of this analysis were overall survival (OS), out-of-field recurrence, local progression, and intracranial progression. All time-to-event investigations included Kaplan-Meier analyses and multivariable Cox regressions. RESULTS Two hundred sixty-four patients were identified, with a mean age of 66.7 years and a female proportion of 48.5%. Most patients (84.5%) had a Karnofsky Performance Status (KPS) score of 80–100, and the mean baseline EQ-5D score was 0.539 quality-adjusted life years. A single lesion was present in 53.4% of the patients, and 29.1% of patients had 3 or more lesions. The median OS was 28.1 months, and independent predictors of mortality included no control of primary tumor (hazard ratio [HR] 2.1), KPS of 80 (HR 2.4) or lower (HR 2.4), coronary artery disease (HR 2.8), and 5 or more lesions present at the time of SRS treatment (HR 2.3). The median out-of-field progression-free survival (PFS) was 24.8 months, and the median local PFS was unreached. Intralesional hemorrhage was an independent risk factor of local progression, with an HR of 6.0. The median intracranial PFS was 14.0 months and was predicted by the number of lesions at the time of SRS (3–4 lesions, HR 2.2; 5–14 lesions, HR 2.5). CONCLUSIONS In this real-world prospective study, the authors used a national quality registry and found favorable OS in patients with NSCLC BMs undergoing SRS compared with results from previously published RCTs. The intracranial PFS was mainly driven by the emergence of new lesions rather than local progression. A greater number of lesions at baseline was associated with out-of-field progression, while intralesional hemorrhage at baseline was associated with local progression.

Spinal cord tumors constitute a diverse group of rare neoplasms associated with significant mortality and morbidity that pose unique clinical and surgical challenges. Diagnostic accuracy and outcome prediction are critical for informed decision making and can promote personalized medicine and facilitate optimal patient management. Machine learning has the ability to analyze and combine vast amounts of data, allowing the identification of patterns and the establishment of clinical associations, which can ultimately enhance patient care. Although artificial intelligence techniques have been explored in other areas of spine surgery, such as spinal deformity surgery, precise machine learning models for spinal tumors are lagging behind. Current applications of machine learning in spinal cord tumors include algorithms that improve diagnostic precision by predicting genetic, molecular, and histopathological profiles. Furthermore, artificial intelligence-based systems can assist surgeons with preoperative planning and surgical resection, potentially reducing the risk of recurrence and consequently improving clinical outcomes. Machine learning algorithms promote personalized medicine by enabling prognostication and risk stratification based on accurate predictions of treatment response, survival, and postoperative complications. Despite their promising potential, machine learning models require extensive validation processes and quality assessments to ensure safe and effective translation to clinical practice.