Predicting whether cardiac dysfunction is present or not was accomplished using machine learning models, on a comprehensive collection. Important medical etc. socioeconomic variables from the dataset were age, sex, kind of chest discomfort, resting blood pressure, cholesterol levels, and other relevant indicators. Data preprocessing involved meticulous steps, including cleaning, normalization, and one-hot encoding, ensuring the data was prepared for accurate analysis. After then, the dataset was divided at a split of 80/20 between tests and training sets. Critical performance indicators, including as Precision, Recall, F1-Score, and Accuracy, were used to assess both models. The Random Forest model demonstrated superior performance, achieving an accuracy of 85%, compared to 82% for Logistic Regression. Additionally, the Precision for detecting heart disease was 86% for Random Forest and 82% for Logistic Regression, indicating a better capability of Random Forest in minimizing false positives. These results suggest that the Random Forest model is particularly effective in predicting heart disease, making it a more reliable choice for clinical applications.