Coronary heart disease is a condition that remains one of the leading causes of death worldwide. Over the years, its prevalence has increased due to several factors, including lifestyle, misdiagnosis, and delays in treatment due to the late identification of this disease. Thus, the research implemented Machine Learning algorithms to detect coronary heart disease based on longitudinal biomedical data. A four-phase methodology was applied: dataset acquisition; preprocessing (missing values, label encoding, and standardization); implementation of Machine Learning algorithms (LR, RF, KNN, and SVM); and evaluation. The best result was obtained by the RF algorithm, with the following metrics: 96% precision, 97% accuracy, 94% recall, 95% F1 score, and an AUC of 0.95 on the ROC curve. The optimal hyperparameters were n_estimators: 200, max_depth: 10, and min_samples_split: 5. In conclusion, the results demonstrate that well-applied Machine Learning algorithms are highly effective in predicting coronary heart disease using longitudinal biomedical data, which can help facilitate timely diagnosis and treatment.