This project aims to predict the likelihood of a myocardial infarction (heart attack) based on various medical parameters. Utilizing a range of machine learning classification algorithms, we assess the risk factors and predict future heart attack occurrences with a focus on accuracy and early detection.
- Data Preprocessing: Cleansing and preparing data for analysis.
- Feature Selection: Identifying the most significant factors contributing to heart attacks.
- Model Training: Using algorithms like Logistic Regression, Naive Bayes, SVM, Random Forest, and KNN.
- Evaluation: Comparing the performance of each algorithm to select the best predictor.
- Prediction: Estimating the probability of a heart attack for new patients.
- Logistic Regression
- Naive Bayes
- Support Vector Machine (SVM)
- Random Forest
- K-Nearest Neighbors (KNN)
To run this project, please follow the steps below:
- Clone the repository to your local machine.
- Run the Jupyter notebooks to train the models.
- Use the trained models to make predictions on new data.
- Python 3.x
- Pandas
- NumPy
- Scikit-learn
- Matplotlib
- Jupyter Notebook
To predict myocardial infarction risk, input the patient's medical parameters into the model. The output will be the predicted risk category.