Search

Abstract Objective Accurate prediction of survival prognosis is helpful to guide clinical decision-making. The aim of this study was to develop a model using machine learning techniques to predict the occurrence of composite thromboembolic events (CTEs) in elderly patients with atrial fibrillation(AF). These events encompass newly diagnosed cerebral ischemia events, cardiovascular events, pulmonary embolism, and lower extremity arterial embolism. Methods This retrospective study included 6,079 elderly hospitalized patients (≥ 75 years old) with AF admitted to the People’s Liberation Army General Hospital in China from January 2010 to June 2022. Random forest imputation was used for handling missing data. In the descriptive statistics section, patients were divided into two groups based on the occurrence of CTEs, and differences between the two groups were analyzed using chi-square tests for categorical variables and rank-sum tests for continuous variables. In the machine learning section, the patients were randomly divided into a training dataset (n = 4,225) and a validation dataset (n = 1,824) in a 7:3 ratio. Four machine learning models (logistic regression, decision tree, random forest, XGBoost) were trained on the training dataset and validated on the validation dataset. Results The incidence of composite thromboembolic events was 19.53%. The Least Absolute Shrinkage and Selection Operator (LASSO) method, using 5-fold cross-validation, was applied to the training dataset and identified a total of 18 features that exhibited a significant association with the occurrence of CTEs. The random forest model outperformed other models in terms of area under the curve (ACC: 0.9144, SEN: 0.7725, SPE: 0.9489, AUC: 0.927, 95% CI: 0.9105–0.9443). The random forest model also showed good clinical validity based on the clinical decision curve. The Shapley Additive exPlanations (SHAP) showed that the top five features associated with the model were history of ischemic stroke, high triglyceride (TG), high total cholesterol (TC), high plasma D-dimer, age. Conclusions This study proposes an accurate model to stratify patients with a high risk of CTEs. The random forest model has good performance. History of ischemic stroke, age, high TG, high TC and high plasma D-Dimer may be correlated with CTEs.

Abstract Background Postoperative delirium (POD) is a common complication after major surgery, resulting in various adverse reactions. However, incidence and risk factors associated with POD after shoulder arthroplasty (SA) have not been well studied using a large-scale national database. Methods A retrospective database analysis was performed based on the Nationwide Inpatient Sample (NIS) from 2005 to 2014, the largest fully paid hospital care database in the United States. Patients undergoing SA were included. The patient’s demographics, comorbidities, length of stay (LOS), total costs, type of insurance, type of hospital, in-hospital mortality, and medical and surgical perioperative complications were assessed. Results A total of 115,147 SA patients were obtained from the NIS database. The general incidence of delirium after SA was 0.89%, peaking in 2010. Patients with delirium after SA had more comorbidities, prolonged LOS, increased hospitalization costs, and higher in-hospital mortality (P

Abstract Background Limited information exists comparing the perioperative complications of the different inflammatory arthropathies (IAs) after total hip arthroplasty (THA). Our study was aimed to (1) compare perioperative complications and (2) determine the most common complications between the different IA subtypes compared with patients with primary osteoarthritis (OA) undergoing primary THA and (3) find whether the difference in postoperative complications also exists between different IA after THA. Methods The Nationwide Inpatient Sample (NIS) was used to identify patients with Rheumatoid arthritis (RA), psoriatic arthritis, ankylosing spondylitis (AS), and primary OA undergoing unilateral THA between 2005 and 2014. Preoperative diagnosis, comorbidities, and postoperative complications were determined using the International Classification of Disease Clinical Modification version 9 codes. The prevalence of perioperative complications was compared between patients with IA and primary OA and between patients with different IA. Results When compared with patients with primary OA, patients with RA had significantly more postoperative surgical and medical complications. Yet there are just several medical complications differences exist between PA and primary OA or AS and primary OA, including stroke and acute renal failure for psoriatic arthritis and urinary tract infection and pneumonia for AS. What is more, there were also several differences in perioperative medical complications seen in patients with different IA. Conclusion Except for patients with RA, the differences in perioperative complications was small between patients with IA and primary OA and between patients with different types of IA.