Overview This project aims to predict the likelihood of heart disease in patients based on various health-related features. By leveraging machine learning techniques, we can assist healthcare professionals in early detection and prevention.
Dataset We used the Heart Disease UCI dataset, which contains information on patients’ age, sex, cholesterol levels, blood pressure, and other relevant attributes. The goal is to build a robust predictive model.
Features Age: Age of the patient Sex: 0 for female, 1 for male Cholesterol: Serum cholesterol level (mg/dL) Blood Pressure: Resting blood pressure (mm Hg) … (other features) Model Selection We experimented with several machine learning algorithms, including:
Logistic Regression Random Forest Support Vector Machines (SVM) Neural Networks Evaluation Metrics We evaluated our models using the following metrics:
Accuracy: Overall correctness of predictions Precision: Proportion of true positive predictions Recall: Proportion of actual positives correctly predicted F1-Score: Harmonic mean of precision
Results Our best-performing model achieved an accuracy of 85% on the test set. Further improvements can be made by fine-tuning hyperparameters and exploring feature engineering techniques.