RESUMO
BACKGROUND AND OBJECTIVES: Contrast agents directly cause kidney toxicity in patients undergoing Percutaneous Intervention for cardiovascular disease with Type 2 diabetes. This meta-analysis aims to evaluate the effects of SGLT2-i on renal function in individuals undergoing Percutaneous Intervention. METHODS: The databases used for the search included PubMed, Scopus, Cochrane Central Registry of Controlled Trials, and Google Scholar. We considered Randomized controlled trials and observational studies published from January 2013 to August 2023. The eligibility to include the studies was assessed independently. The Cochrane modified data extraction form, and Joanna Briggs Institute was used. The Cochrane risk of bias tool and Newcastle-Ottawa quality assessment scale were used to assess the quality of the studies. The certainty of the evidence was assessed using GradePro software. RESULTS: The pooled estimate showed a substantial reduction in serum creatinine levels at 48- and 72-hours post-PCI who received SGLT2i (MD -9.57; 95% CI -18.36, -0.78; p-value 0.03) and (MD -14.40; 95% CI -28.57, -0.22; p-value 0.05). There was a decrease in the incidence of the CI-AKI among SGT2i users (RR: 0.46; 95% CI: 0.32, 0.67; p value< 0.0001). There was no significant difference in the number of patients requiring hemodialysis, but a smaller number of patients required hemodialysis among the SGLT2i users (RR: 0.88; 95% CI: 0.19, 4.07; p-value = 0.87). CONCLUSIONS: The use of SGLT2i confers substantial beneficial effects on kidney function and reduction of incidence of Contrast-induced acute kidney injury among patients undergoing PCI procedures for cardiovascular disease with diabetes.
RESUMO
STUDY OBJECTIVE: Performing hip or knee arthroplasty as an outpatient surgery has been shown to be operationally and financially beneficial for selected patients. By applying machine learning models to predict patients suitable for outpatient arthroplasty, health care systems can better utilize resources efficiently. The goal of this study was to develop predictive models for identifying patients likely to be discharged same-day following hip or knee arthroplasty. DESIGN: Model performance was assessed with 10-fold stratified cross-validation, evaluated over baseline determined by the proportion of eligible outpatient arthroplasty over sample size. The models used for classification were logistic regression, support vector classifier, balanced random forest, balanced bagging XGBoost classifier, and balanced bagging LightGBM classifier. SETTING: The patient records were sampled from arthroplasty procedures at a single institution from October 2013 to November 2021. PATIENTS: The electronic intake records of 7322 knee and hip arthroplasty patients were sampled for the dataset. After data processing, 5523 records were kept for model training and validation. INTERVENTIONS: None. MEASUREMENTS: The primary measures for the models were the F1-score, area under the receiver operating characteristic curve (ROCAUC), and area under the precision-recall curve. To measure feature importance, the SHapley Additive exPlanations value (SHAP) were reported from the model with the highest F1-score. RESULTS: The best performing classifier (balanced random forest classifier) achieved an F1-score of 0.347: an improvement of 0.174 over baseline and 0.031 over logistic regression. The ROCAUC for this model was 0.734. Using SHAP, the top determinant features of the model included patient sex, surgical approach, surgery type, and body mass index. CONCLUSIONS: Machine learning models may utilize electronic health records to screen arthroplasty procedures for outpatient eligibility. Tree-based models demonstrated superior performance in this study.