RESUMEN
Background: Statin therapy is well-established for treating hyperlipidemia and ischemic heart disease (IHD), but its role in Acute Decompensated Heart Failure (ADHF) remains less clear. Despite varying clinical guidelines, the actual utilization and impact of statin therapy initiation in patients with ADHF with an independent indication for statin therapy have not been thoroughly explored. Methods: We conducted a retrospective observational study on 5978 patients admitted with ADHF between January 1st, 2007, and December 31st, 2017. Patients were grouped based on their statin therapy status at admission and discharge. We performed multivariable analyses to identify independent predictors of short-term, intermediate-term, and long-term mortality. A sensitivity analysis was also conducted on patients with an independent indication for statin therapy but who were not on statins at admission. Results: Of the total patient cohort, 73.9% had an indication for statin therapy. However, only 38.2% were treated with statins at admission, and 56.1% were discharged with a statin prescription. Patients discharged with statins were younger, predominantly male, and had a higher prevalence of IHD and other comorbidities. Statin therapy at discharge was an independent negative predictor of 5-year all-cause mortality (hazard ratio 0.80, 95% confidence interval 0.76-0.85). The sensitivity analysis confirmed these findings, demonstrating higher mortality rates in patients not initiated on statins during admission. Conclusions: The study highlights significant underutilization of statin therapy among patients admitted with ADHF, even when there's an independent indication for such treatment. Importantly, initiation of statin therapy during hospital admission was independently associated with improved long-term survival.
RESUMEN
Early detection of left ventricular systolic dysfunction (LVSD) may prompt early care and improve outcomes for asymptomatic patients. Standard 12-lead ECG may be used to predict LVSD. We aimed to compare the performance of Machine Learning Algorithms (MLA) and physicians in predicting LVSD from a standard 12-lead ECG. By utilizing a dataset of 13,820 pairs of ECGs and echocardiography, a deep residual convolutional neural network was trained for predicting LVSD (ejection fraction (EF) < 50%) from ECG. The ECGs of the test set (n = 850) were assessed for LVSD by the MLA and six physicians. The performance was compared using sensitivity, specificity, and C-statistics. The interobserver agreement between the physicians for the prediction of LVSD was moderate (κ = 0.50), with average sensitivity and specificity of 70%. The C-statistic of the MLA was 0.85. Repeating this analysis with LVSD defined as EF < 35% resulted in an improvement in physicians' average sensitivity to 84% but their specificity decreased to 57%. The MLA C-statistic was 0.88 with this threshold. We conclude that although MLA outperformed physicians in predicting LVSD from standard ECG, prior to robust implementation of MLA in ECG machines, physicians should be encouraged to use this approach as a simple and readily available aid for LVSD screening.
