Heart failure and cardiac decompensation, often leading to recurrent hospitalizations, significantly impair quality of life and life expectancy. Monitoring hydration status is crucial in managing these patients. Although body impedance analysis (BIA) is a simple, cost-effective, and noninvasive method, its clinical application remains underutilized worldwide. Given its potential to improve therapy management, this study aimed to evaluate the feasibility of repetitive BIA measurements in patients hospitalized for acute heart failure in a real-world clinical setting. Thirty two patients hospitalized for acute heart failure were enrolled in this prospective cohort study between June 8, 2021, and May 16, 2022. Repetitive measurements of body weight and composition were performed on admission, day 3, and day 6. All measurements were performed by previously untrained medical staff after a 10-minute introduction. We observed a significant decrease in body weight by 2.02 kg ( P < .001) within the first 3 days under diuretic therapy, which corresponded to a significant loss of body water (−1.51 kg; P = .013) and a slight loss of body fat (−1.41 kg; P = .002). Subsequent measurements on day 6 showed variable results. An additional loss of body weight (−1.63 kg; P ≤ 0.001) was mainly driven by a reduction of fat (−1.01 kg; P = .040) and body cell mass (−1.91 kg; P = .027). Only few patients benefited from further intensified diuretic therapy with a subsequent loss of body water (−0.51 kg; P = .580). BIA provides essential data on body composition, which cannot be assessed by simple weight measurements as these may be altered by simultaneous changes in fat or body cell mass. BIA measurements are feasible and easy to learn and should be implemented in routine cardiovascular care.
Background: Left ventricular (LV) function and lactate dynamics are major prognostic markers after ST-segment elevation myocardial infarction (STEMI). Early identification of patients at risk for impaired LV function or systemic hypoperfusion may improve outcomes. Machine learning (ML) can enhance predictive accuracy beyond traditional statistical methods, yet most prior studies were limited by small sample sizes and categorical outcomes. Methods: We retrospectively analyzed 2132 consecutive STEMI patients admitted to LMU Hospital (2014–2023). After preprocessing, 1608 patients with complete data were included. Thirty-eight demographic, clinical, procedural, and laboratory variables were used to train Decision Tree, Random Forest, and XGBoost regression models for predicting continuous left ventricular ejection fraction (LVEF) at discharge and lactate levels during hospitalization. Model performance was evaluated using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and mean absolute percentage error (MAPE). Feature importance and Shapley additive explanations (SHAP) were applied for interpretability. Results: Ensemble models outperformed single trees. XGBoost achieved the best performance for LVEF prediction (MSE = 0.008, RMSE = 0.086, MAE = 0.068, R2 = 0.35). Lactate prediction showed moderate accuracy (R2 = 0.42 for admission and 0.47 for peak levels). Key predictors included cardiogenic shock, left anterior descending (LAD) culprit lesions, and peak lactate. Conclusions: ML enables individualized prediction of LV function and lactate dynamics after STEMI using routinely available clinical and laboratory data. Ensemble models, particularly XGBoost, demonstrated consistent and clinically meaningful predictive performance and generalizability, supporting their potential for early, data-driven risk stratification in acute cardiac care.