The following is a summary of “Development and validation of a prediction model for in-hospital death in patients with heart failure and atrial fibrillation,” published in the October 2023 issue of Cardiology by Yan et al.
Researchers started a retrospective study to develop a prediction model for in-hospital mortality of patients with heart failure (HF) and atrial fibrillation (AF).
They involved 10,236 patients with HF and AF admitted to the intensive care unit (ICU) from the Medical Information Mart for Intensive Care (MIMIC). MIMIC-IV subjects were split into training and testing sets to build and assess the prediction model. MIMIC-III and eICU-CRD samples were internal and external validation sets to validate the model’s predictive value. Univariate and multivariable logistic regression analyses were employed to identify predictors for in-hospital death in patients with HF and AF. Receiver operating characteristic (ROC), calibration, and decision curve analysis (DCA) curves were generated to assess the model’s predictive capabilities.
The results showed that the mean survival time for participants from MIMIC-III was 11.29 ± 10.05 days, while for those from MIMIC-IV, it was 10.56 ± 9.19 days. The final model’s predictions included SAPS II, RDW, beta-blocker, race, respiratory rate, urine output, CABG, Charlson comorbidity index, RRT, antiarrhythmic, age, and anticoagulation. The AUC of the prediction model was 0.810 (95% CI: 0.791–0.828) in the training set, 0.757 (95% CI: 0.729–0.786) in the testing set, 0.792 (95% CI: 0.774–0.810) in the internal validation set, and 0.724 (95% CI: 0.687–0.762) in the external validation set. Calibration curves showed slight deviations from the ideal model’s predictive probabilities for in-hospital death in HF/AF patients. DCA curves showed that the prediction model improved net benefit.
They concluded that a prediction model for in-hospital mortality in HF patients with AF may help identify high-risk patients.
Source: bmccardiovascdisord.biomedcentral.com/articles/10.1186/s12872-023-03521-3
Create Post
Twitter/X Preview
Logout