: Background Thromboembolic disease is common in coronavirus disease-19 (COVID-19). There is limited evidence on association of in-hospital anticoagulation (AC) with outcomes and postmortem findings. Objective To examine association of AC with in-hospital outcomes and describe thromboembolic findings on autopsies. Methods A retrospective analysis examining association of AC with mortality, intubation and major bleeding. We also conducted sub-analyses on association of therapeutic vs prophylactic AC initiated ≤48 hours from admission. We describe thromboembolic disease contextualized by pre-mortem AC among consecutive autopsies. Results Among 4,389 patients, median age was 65 years with 44% female. Compared to no AC (n=1530, 34.9%), therapeutic (n=900, 20.5%) and prophylactic AC (n=1959, 44.6%) were associated with lower in-hospital mortality (adjusted hazard ratio [aHR]=0.53; 95%CI: 0.45-0.62, and aHR=0.50; 95%CI: 0.45-0.57, respectively), and intubation (aHR 0.69; 95%CI: 0.51-0.94, and aHR 0.72; 95% CI: 0.58-0.89, respectively). When initiated ≤48 hours from admission, there was no statistically significant difference between therapeutic (n=766) vs. prophylactic AC (n=1860) (aHR 0.86, 95%CI: 0.73-1.02; p=0.08). Overall, 89 patients (2%) had major bleeding adjudicated by clinician review, with 27/900 (3.0%) on therapeutic, 33/1959 (1.7%) on prophylactic, and 29/1,530 (1.9%) on no AC. Of 26 autopsies, 11 (42%) had thromboembolic disease not clinically suspected and 3/11 (27%) were on therapeutic AC. Conclusions AC was associated with lower mortality and intubation among hospitalized COVID-19 patients. Compared to prophylactic AC, therapeutic AC was associated with lower mortality, though not statistically significant. Autopsies revealed frequent thromboembolic disease. These data may inform trials to determine optimal AC regimens.

Study Design. A cross-sectional database study. Objective. The aim of this study was to train and validate machine learning models to identify risk factors for complications following posterior lumbar spine fusion. Summary of Background Data. Machine learning models such as artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex datasets. ANNs have yet to be used for risk factor analysis in orthopedic surgery. Methods. The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent posterior lumbar spine fusion. This query returned 22,629 patients, 70% of whom were used to train our models, and 30% were used to evaluate the models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American Society for Anesthesiology (ASA) class ≥3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating curves (AUC) was used to determine the accuracy of our machine learning models. Results. On the basis of AUC values, ANN and LR both outperformed ASA class for predicting all four types of complications. ANN was the most accurate for predicting cardiac complications, and LR was most accurate for predicting wound complications, VTE, and mortality, though ANN and LR had comparable AUC values for predicting all types of complications. ANN had greater sensitivity than LR for detecting wound complications and mortality. Conclusion. Machine learning in the form of logistic regression and ANNs were more accurate than benchmark ASA scores for identifying risk factors of developing complications following posterior lumbar spine fusion, suggesting they are potentially great tools for risk factor analysis in spine surgery.

Study Design:Meta-analysis.Objective:Proximal junctional kyphosis (PJK) is a complication of surgical management for adult spinal deformity with a multifactorial etiology. Many risk factors are controversial and their relative importance are not fully understood. We aimed to identify the surgical, radiographic, and patient-related risk factors associated with PJK and proximal junctional failure (PJF).Methods:A systematic literature search was performed using PubMed, Cochrane Database of Systematic Reviews, and EMBASE. The inclusion criteria included prospective randomized control trials and prospective/retrospective cohort studies of adult patients with radiographic evidence of PJK, which was defined as a proximal junctional sagittal Cobb angle ≥10° and at least 10° greater than the preoperative measurement. Studies required a minimum of 10 patients and 12 months of follow-up.Results:A total of 14 unique studies, including 1908 patients were included. The pooled analysis showed significant differences between the PJK and non-PJK groups in age (weighted mean difference [WMD] −3.80; P = .03), prevalence of osteopenia/osteoporosis (odds ratio [OR] 1.99; P = .0004), preoperative sagittal vertical axis (SVA) (WMD −17.52; P = .02), preoperative lumbar lordosis (LL) (WMD −1.22; P = .002), pedicle screw instrumentation at the upper instrumented vertebra (UIV) (OR 1.67; P = .02), change in SVA (WMD −11.87; P = .01), fusion to sacrum/pelvis/ilium (OR 2.14; P < .00 001), change in LL (WMD −5.61; P = .01), and postoperative SVA (WMD −7.79; P = .008).Conclusions:Our meta-analysis suggests that age, osteopenia/osteoporosis, high preoperative SVA, high postoperative SVA, low preoperative LL, use of pedicle screws at the UIV, SVA change/correction, LL change/correction, and fusion to sacrum/pelvis/iliac region are risk factors for PJK.

Purpose The purpose of this study is to develop a machine learning algorithm to predict future intubation among patients diagnosed or suspected with COVID-19. Materials and methods This is a retrospective cohort study of patients diagnosed or under investigation for COVID-19. A machine learning algorithm was trained to predict future presence of intubation based on prior vitals, laboratory, and demographic data. Model performance was compared to ROX index, a validated prognostic tool for prediction of mechanical ventilation. Results 4087 patients admitted to five hospitals between February 2020 and April 2020 were included. 11.03% of patients were intubated. The machine learning model outperformed the ROX-index, demonstrating an area under the receiver characteristic curve (AUC) of 0.84 and 0.64, and area under the precision-recall curve (AUPRC) of 0.30 and 0.13, respectively. In the Kaplan-Meier analysis, patients alerted by the model were more likely to require intubation during their admission ( p < 0.0001). Conclusion In patients diagnosed or under investigation for COVID-19, machine learning can be used to predict future risk of intubation based on clinical data which are routinely collected and available in clinical setting. Such an approach may facilitate identification of high-risk patients to assist in clinical care.

ObjectiveMachine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF).MethodsArtificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. ResultsA total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). ConclusionANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.