Citations

OBJECTIVE Chordomas are slow-growing tumors derived from notochord remnants. Despite margin-negative excision and postoperative radiation therapy, spinal chordomas (SCs) often progress. The potential of immunohistochemical (IHC) markers, such as epithelial membrane antigen (EMA), combined with machine learning algorithms to predict long-term (≥ 12 months) postoperative tumor progression, has been understudied. The authors aimed to identify IHC markers using trained tree-based algorithms to predict long-term (≥ 12 months) postoperative tumor progression. METHODS The authors reviewed the records of patients who underwent resection of SCs between January 2017 and June 2021 across the Mayo Clinic enterprise. Demographics, type of treatment, histopathology, and other relevant clinical factors were abstracted from each patient’s record. Low tumor progression was defined as more than a 94.3-mm3 decrease in the tumor size at the latest radiographic follow-up. Decision trees and random forest classifiers were trained and tested to predict the long-term volumetric progression after an 80/20 data split. RESULTS Sixty-two patients diagnosed with and surgically treated for SC were identified, of whom 31 were found to have a more advanced tumor progression based on the tumor volume change cutoff of 94.3 mm3. The mean age was 54.3 ± 13.8 years, and most patients were male (62.9%) and White (98.4%). The most common treatment modality was subtotal resection with radiation therapy (35.5%), with proton beam therapy being the most common (71%). Most SCs were sacrococcygeal (41.9%), followed by cervical (32.3%). EMA-positive SCs had a postoperative progression risk of 67%. Pancytokeratin-positive SCs had a progression rate of 67%; however, patients with S100 protein–positive SCs had a 54% risk of progression. The accuracy of this model in predicting the progression of unseen test data was 66%. Pancytokeratin (mean minimal depth = 1.57), EMA (mean minimal depth = 1.58), cytokeratin A1/A3 (mean minimal depth = 1.59), and S100 protein (mean minimal depth = 1.6) predicted the long-term volumetric progression. Multiway variable importance plots show the relative importance of the top 10 variables based on three measures of varying significance and their predictive role. CONCLUSIONS These IHC variables with tree-based machine learning tools successfully demonstrate a high capacity to identify a patient’s tumor progression pattern with an accuracy of 66%. Pancytokeratin, EMA, cytokeratin A1/A3, and S100 protein were the IHC drivers of a low tumor progression. This shows the power of machine learning algorithms in analyzing and predicting outcomes of rare conditions in a small sample size.

OBJECTIVE The authors sought to determine how the temporal proximity of lumbar epidural spinal injection prior to surgery impacts clinical outcomes (e.g., 30-day readmission, postoperative complications, CSF leak) in patients undergoing lumbar decompression without fusion. METHODS The authors queried their institutional registry to identify patients who underwent elective lumbar decompression for spondylotic pathology between January 2019 and March 2022 at multiple centers within the same hospital network. Patients were divided into groups based on the time between their surgical date and the most recent preoperative spinal injection: group 1, patients with duration < 1 month; group 2, 1–3 months; and group 3, no spinal injection within 3 months. Primary outcomes of interest were the length of hospital stay, postoperative complications, rate of intraoperative CSF leak, and rates of reoperation and hospital readmission. For patients in groups 1 and 2, the authors also recorded the number of injections within 12 months prior to surgery to better understand the effect of multiple recent injections. The independent Student t-test and Pearson’s chi-square test were mainly performed for univariate analyses of the continuous and categorical variables, respectively. RESULTS A total of 121 and 283 patients received a spinal injection at < 1 month and 1–3 months prior to surgery, respectively, and were separately matched in a 3:1 ratio with 2562 patients with no history of preoperative spinal injection within 3 months before surgery. Among the matched cohorts, patients who received spinal injections < 1 month before lumbar decompression had significantly higher risks of 30-day complication (7.4% vs 0.8%, OR 9.6, p < 0.001), 30-day readmission (5.8% vs 2.2%, OR 3.5, p = 0.049), and 90-day readmission (9.1% vs 2.8%, OR 3.5, p = 0.003) than patients with no history of spinal injection. However, compared with patients with no history of spinal injection, the patients who received spinal injections 1–3 months before surgery were not at higher risk for postoperative complications or readmission. The CSF leak rates were significantly different between the three patient cohorts (10.7% vs 6.7% vs 4.9% for the < 1 month, 1–3 months, and no injection cohorts, respectively; p = 0.02). CONCLUSIONS Lumbar decompression within 1 month of preoperative spinal injection was associated with higher risks of readmission and postoperative complications, including CSF leak. However, with the exception of CSF leak, these risks were no longer observed when spinal injection occurred 1–3 months prior to lumbar decompression.

IMPORTANCEPatients undergoing spine surgery often experience severe pain. The optimal dosage of pregabalin and gabapentin for pain control and safety in these patients has not been well established.OBJECTIVETo evaluate the associations of pain, opioid consumption, and adverse events with different dosages of pregabalin and gabapentin in patients undergoing spine surgery.DATA SOURCESPubMed/MEDLINE, Embase, Web of Science, Cochrane library, and Scopus databases were searched for articles until August 7, 2021.STUDY SELECTIONRandomized clinical trials conducted among patients who received pregabalin or gabapentin while undergoing spine surgery were included.DATA EXTRACTION AND SYNTHESISTwo investigators independently performed data extraction following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) reporting guideline. The network meta-analysis was conducted from August 2022 to February 2023 using a random-effects model.MAIN OUTCOMES AND MEASURESThe primary outcome was pain intensity measured using the Visual Analog Scale (VAS), and secondary outcomes included opioid consumption and adverse events.RESULTSTwenty-seven randomized clinical trials with 1861 patients (median age, 45.99 years [range, 20.00-70.00 years]; 759 women [40.8%]) were included in the systematic review and network meta-analysis. Compared with placebo, the VAS pain score was lowest with gabapentin 900 mg per day, followed by gabapentin 1200 mg per day, gabapentin 600 mg per day, gabapentin 300 mg per day, pregabalin 300 mg per day, pregabalin 150 mg per day, and pregabalin 75 mg per day. Additionally, gabapentin 900 mg per day was found to be associated with the lowest opioid consumption among all dosages of gabapentin and pregabalin, with a mean difference of −22.07% (95% CI, −33.22% to −10.92%) for the surface under the cumulative ranking curve compared with placebo. There was no statistically significant difference in adverse events (nausea, vomiting, and dizziness) among all treatments. No substantial inconsistency between direct and indirect evidence was detected for all outcomes.CONCLUSIONS AND RELEVANCEThese findings suggest that gabapentin 900 mg per day before spine surgery is associated with the lowest VAS pain score among all dosages. In addition, no differences in adverse events were noted among all treatments.

OBJECTIVE Vertebral artery injury (VAI), a complication of blunt trauma, may cause posterior circulation stroke. An association of disease severity, classified in Denver grades, with stroke risk has not been shown. Using a literature-based analysis, the authors estimated the incidence of VAI following blunt trauma with the aim to investigate the impact of Denver grade and bilateral VAI on stroke occurrence. METHODS A systematic review of the literature on VAI following blunt trauma was conducted, and data on its incidence, the severity per Denver grade, and stroke occurrence were collected. The incidence of VAI and stroke occurrence were analyzed cumulatively and between Denver grades. A meta-analysis with random-effects models was performed. RESULTS Fifty-six studies including 2563 patients were identified. The overall incidence of VAI was 0.49% among blunt trauma cases and 14.5% among patients screened via any type of angiography. The incidence rates of bilateral VAI and concurrent carotid injury among all VAIs were 12.3% and 19.2%, respectively. VAI severity by Denver grade was as follows: grade I, 23.4%; grade II, 28.2%; grade III, 5.8%; grade IV, 42.1%; and grade V, 0.5%. The overall stroke risk was 5.32%, differing significantly among lesions of different Denver grades (p = 0.02). Grade III and IV lesions had the highest stroke prevalence (9.8% and 10.9% respectively), while strokes occurred significantly less frequently in patients with grade I and II lesions (1.9% and 3.0%, respectively). Denver grade V cases were too rare for meaningful analysis. Bilateral VAI was associated with a 33.2% stroke prevalence. The association between Denver grade and stroke occurrence persisted in a sensitivity subanalysis including only unilateral cases (p = 0.03). CONCLUSIONS VAI complicates a small yet nontrivial fraction of blunt trauma cases, with Denver grade IV lesions being the most common. This is the first study to document a significantly higher stroke prevalence among grade III and IV VAIs compared with grade I and II VAIs independently from bilaterality. Bilateral VAIs carry a significantly higher stroke rate.

OBJECTIVE Spondylolisthesis is a common operative disease in the United States, but robust predictive models for patient outcomes remain limited. The development of models that accurately predict postoperative outcomes would be useful to help identify patients at risk of complicated postoperative courses and determine appropriate healthcare and resource utilization for patients. As such, the purpose of this study was to develop k-nearest neighbors (KNN) classification algorithms to identify patients at increased risk for extended hospital length of stay (LOS) following neurosurgical intervention for spondylolisthesis. METHODS The Quality Outcomes Database (QOD) spondylolisthesis data set was queried for patients receiving either decompression alone or decompression plus fusion for degenerative spondylolisthesis. Preoperative and perioperative variables were queried, and Mann-Whitney U-tests were performed to identify which variables would be included in the machine learning models. Two KNN models were implemented (k = 25) with a standard training set of 60%, validation set of 20%, and testing set of 20%, one with arthrodesis status (model 1) and the other without (model 2). Feature scaling was implemented during the preprocessing stage to standardize the independent features. RESULTS Of 608 enrolled patients, 544 met prespecified inclusion criteria. The mean age of all patients was 61.9 ± 12.1 years (± SD), and 309 (56.8%) patients were female. The model 1 KNN had an overall accuracy of 98.1%, sensitivity of 100%, specificity of 84.6%, positive predictive value (PPV) of 97.9%, and negative predictive value (NPV) of 100%. Additionally, a receiver operating characteristic (ROC) curve was plotted for model 1, showing an overall area under the curve (AUC) of 0.998. Model 2 had an overall accuracy of 99.1%, sensitivity of 100%, specificity of 92.3%, PPV of 99.0%, and NPV of 100%, with the same ROC AUC of 0.998. CONCLUSIONS Overall, these findings demonstrate that nonlinear KNN machine learning models have incredibly high predictive value for LOS. Important predictor variables include diabetes, osteoporosis, socioeconomic quartile, duration of surgery, estimated blood loss during surgery, patient educational status, American Society of Anesthesiologists grade, BMI, insurance status, smoking status, sex, and age. These models may be considered for external validation by spine surgeons to aid in patient selection and management, resource utilization, and preoperative surgical planning.

OBJECTIVE The purpose of this study was to evaluate the performance of different supervised machine learning algorithms to predict achievement of minimum clinically important difference (MCID) in neck pain after surgery in patients with cervical spondylotic myelopathy (CSM). METHODS This was a retrospective analysis of the prospective Quality Outcomes Database CSM cohort. The data set was divided into an 80% training and a 20% test set. Various supervised learning algorithms (including logistic regression, support vector machine, decision tree, random forest, extra trees, gaussian naïve Bayes, k–nearest neighbors, multilayer perceptron, and extreme gradient boosted trees) were evaluated on their performance to predict achievement of MCID in neck pain at 3 and 24 months after surgery, given a set of predicting baseline features. Model performance was assessed with accuracy, F1 score, area under the receiver operating characteristic curve, precision, recall/sensitivity, and specificity. RESULTS In total, 535 patients (46.9%) achieved MCID for neck pain at 3 months and 569 patients (49.9%) achieved it at 24 months. In each follow-up cohort, 501 patients (93.6%) were satisfied at 3 months after surgery and 569 patients (100%) were satisfied at 24 months after surgery. Of the supervised machine learning algorithms tested, logistic regression demonstrated the best accuracy (3 months: 0.76 ± 0.031, 24 months: 0.773 ± 0.044), followed by F1 score (3 months: 0.759 ± 0.019, 24 months: 0.777 ± 0.039) and area under the receiver operating characteristic curve (3 months: 0.762 ± 0.027, 24 months: 0.773 ± 0.043) at predicting achievement of MCID for neck pain at both follow-up time points, with fair performance. The best precision was also demonstrated by logistic regression at 3 (0.724 ± 0.058) and 24 (0.780 ± 0.097) months. The best recall/sensitivity was demonstrated by multilayer perceptron at 3 months (0.841 ± 0.094) and by extra trees at 24 months (0.817 ± 0.115). Highest specificity was shown by support vector machine at 3 months (0.952 ± 0.013) and by logistic regression at 24 months (0.747 ± 0.18). CONCLUSIONS Appropriate selection of models for studies should be based on the strengths of each model and the aims of the studies. For maximally predicting true achievement of MCID in neck pain, of all the predictions in this balanced data set the appropriate metric for the authors’ study was precision. For both short- and long-term follow-ups, logistic regression demonstrated the highest precision of all models tested. Logistic regression performed consistently the best of all models tested and remains a powerful model for clinical classification tasks.