Machine learning algorithms to predict risk of postoperative pneumonia in elderly with hip fracture.

BACKGROUND: Hip fracture (HF) is one of the most common fractures in the elderly and is significantly associated with high mortality and unfavorable prognosis. Postoperative pneumonia (POP), the most common postoperative complication of HF, can seriously affect patient prognosis and increase the burden on the healthcare system. The aim of this study was to develop machine learning models for identifying elderly patients at high risk of pneumonia after hip fracture surgery. METHODS: From May 2016 to November 2022, patients admitted to a single central hospital for HF served as the study population. We extracted data that could be collected within 24 h of patient admission. The dataset was divided into training and validation sets according to 70:30. Based on the screened risk factors, prediction models were developed using seven machine learning algorithms, namely CART, GBM, KNN, LR, NNet, RF, and XGBoost, and their performance was evaluated. RESULTS: Eight hundred five patients were finally included in the analysis and 75 (9.3%) patients suffered from POP. Age, CI, COPD, WBC, HB, GLU, STB, GLOB, Ka+ which are used as features to build machine learning models. By evaluating the model's AUC value, accuracy, sensitivity, specificity, Kappa value, MCC value, Brier score value, calibration curve, and DCA curve, the model constructed by XGBoost algorithm has the best and near-perfect performance. CONCLUSION: The machine learning model we created is ideal for detecting elderly patients at high risk of POP after HF at an early stage.

Type 2 diabetes and the risk of synovitis-tenosynovitis: a two-sample Mendelian randomization study.

Introduction: It has been shown that people with type 2 diabetes have a higher risk of synovitis and tenosynovitis, but previous studies were mainly observational, which may be biased and does not allow for a cause-and-effect relationship. Therefore, we conducted a two-sample Mendelian randomization (MR) study to investigate the causal relationship. Method: We obtained data on "type 2 diabetes" and "synovitis, tenosynovitis" from published large-scale genome-wide association studies (GWAS). The data were obtained from the FinnGen consortium and UK Biobank, both from European population samples. We used three methods to perform a two-sample MR analysis and also performed sensitivity analysis. Results: The results of all three MR methods we used for the analysis illustrated that T2DM increases the risk factor for the development of synovitis and tenosynovitis. Specifically, for the IVW method as the primary analysis outcome, OR = 1.0015 (95% CI, 1.0005 to 1.0026), P = 0.0047; for the MR Egger method as the supplementary analysis outcome, OR = 1.0032 (95% CI, 1.0007 to 1.0056), P = 0.0161; for the weighted median method, OR = 1.0022 (95% CI, 1.0008 to 1.0037), p = 0.0018. In addition, the results of our sensitivity analysis suggest the absence of heterogeneity and pleiotropy in our MR analysis. Conclusion: In conclusion, the results of our MR analysis suggest that T2DM is an independent risk factor for increased synovitis and tenosynovitis.

Effect of Wu Qin Xi exercises on pain and function in people with knee osteoarthritis: A systematic review and meta-analysis.

Background: As a chronic disease that affects the whole world, there is no definite treatment for knee osteoarthritis (KOA). Wu Qin Xi (WQX) is still in preliminary exploration as a traditional Chinese exercise in the treatment of osteoarthritis of the knee. The purpose of this study was to conduct a meta-analysis of previous studies and to investigate the efficacy of the WQX exercises on pain and function in patients with KOA. Methods: We searched six databases (Pubmed, Embase, Cochrane Library, Wanfang, CQVIP, and CNKI) for articles on WQX for KOA up to May 10, 2022. Literature search, study selection, data extraction, and quality evaluation were performed by two independent authors. In terms of statistical results, we presented mean differences (MD), 95% CI, and I 2 to show heterogeneity, and, based on that, we chose either a random effects model or a fixed effects model. Results: Seven studies were selected for inclusion in this meta-analysis. The WQX intervention group showed statistical differences for both the total Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) score and its various bylaws, the Visual Analogue Score (VAS), and the presence of general functional exercise in the control group. We also demonstrated the clinically meaningful efficacy of WQX treatment by calculating minimum clinical importance difference (MCID) values that met the MCID values on the WOMAC score. A sensitivity analysis was also performed in this study by subgroup analysis for greater heterogeneity, and it was inferred that the difference in follow-up time was a likely source of heterogeneity. Conclusion: Despite some limitations, the current study showed a definite effect of WQX in improving pain symptoms and joint function in patients with KOA. Systematic review registration: https://www.crd.york.ac.uk/prospero/, identifier: CRD42022332209.

Different treatments for 3- or 4-part proximal humeral fractures in the elderly patients: A Bayesian network meta-analysis of randomized controlled trials.

Background: Proximal humeral fractures are the third most common fracture in the body, and their incidence is rising year by year as the population ages. However, the treatment of the proximal humerus in parts 3 and 4 is still debatable, necessitating a network meta-analysis to determine the best treatment for each treatment modality. Methods: We searched PubMed, Embase, Cochrane Library for randomized controlled trials on proximal humeral fractures up to June 21, 2022. We performed data extraction and literature quality assessment by two independent authors and extracted constant score and reoperation rate as indicators for evaluation. Stata software, Revman software, JAGS software and the R-based BlandAltmanLeh package, gemtc package and riags package were used to perform this Bayesian network meta-analysis. Results: Following screening, 11 papers with a total of 648 participants were included in the analysis. The SUCRA values for the constant score were in the following order: RSA, IMN, Conservative, HA, and LP, and the SUCRA values for the reoperation rate were LP, HA, IMN, Conservative, and RSA. Conclusion: The elderly with 3- or 4-part proximal humeral fractures should consider RSA because it received the best evaluation ranking in terms of constant score and reoperation rate. Systematic Review Registration: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022341209, identifier: CRD42022341209.