Key points are not available for this paper at this time.
Introduction: Heart failure (HF) and atrial fibrillation (AF) are constantly linked together as predictors of a substantial increase in morbidity and mortality. In this study, we investigated the effects of atrial fibrillation in patients with heart failure. Methods: This study was a prospective observational multicenter national registry encompassing 21 health institutes in Jordan, comprising university hospitals, private hospitals, and private clinics. Patients visiting the cardiology clinic or inpatients admitted due to acute decompensated HF were included. The collected variables included age, sex, BMI, comorbidities, HDL, LDL, triglycerides, BNP, Sodium, potassium, hemoglobin, and creatinine. Results: Our study of 1571 patients showed significant differences between those with and without atrial fibrillation (AF). AF patients included more females (49.4% vs 34.0%), had a higher prevalence of hypertension (88.0% vs 78.5%), and were older (57.8% aged ≥ 70 years). Smoking rates were lower in patients with AF (22.3% vs 37.0%), while dyslipidemia was less common (54.5% vs 65.3%). Patients with AF also had more hospital admissions than those without AF (16% vs 11.6%). In addition, triglyceride levels were notably lower, hemoglobin levels were < 10 g/dL, and eGFR was reduced in patients with AF. In predicting death, the Random Forest Classifier had the highest accuracy (93.02%) and AUC (92.51%), whereas Logistic Regression had higher sensitivity (72.09%). Creatinine, Length of Hospital Stay, and other factors influenced the predictions, with creatinine levels being a strong predictor of patient outcomes. Conclusion: Atrial fibrillation patients were older and had a higher proportion of females compared than non-atrial fibrillation patients. Hypertension, a family history of premature coronary artery disease, and structural heart disease were notably higher in the atrial fibrillation group. Patients with atrial fibrillation had higher rates of hospital admissions than those without atrial fibrillation. Keywords: atrial fibrillation, heart failure, Jordan, registry, machine learning
Izraiq et al. (Sat,) studied this question.