🔎 We performed a predictive data analysis in Python to predict the presence of heart disease using the health data collected for 1000+ patients. Libraries used include pandas, NumPy, Matplotlib, scikit-learn, and seaborn.
💓 The dataset is from UC Irvine Machine Learning Repository that has 14 health attributes from patients, including their heart disease diagnosis. Approximately half of the patients were diagnosed with heart disease.
💻 Four different models were trained on the UC Ivrine dataset, including Logistic Regression, Neural Network, SVM, and Random Forest.
📈 We produced a 70-100% prediction accuracy with each of the four models.