This study investigates the use of machine learning (ML) models to predict changes in ejection fraction (EF) in heart failure (HF) patients over a one-year period. The study uses data from three different sites (A, B, and C) and employs several ML algorithms, including logistic regression, support vector machines, random forest, XGBoost, K-Nearest Neighbors, and decision trees. Baseline characteristics of the patients are used as features to train and evaluate the models. The results demonstrate the potential of ML in predicting EF changes, which could aid in personalized treatment strategies.