Heart Disease Prediction

Overview

Heart Disease accounts for nearly 700,000 deaths annually in the US, which is approximately 1 in 5 deaths. The objective of this data project was to implement a machine learning model using logistic regression, to accurately predict whether a patient has heart disease or not depending on a set of select features:
• Age
• Sex
• Chest Pain Type (4 values)
• Blood Pressure
• Cholesterol Level
• Blood Sugar Level
• Resting ElectrocardiographicRresults (values 0,1,2)
• Maximum Heart Rate
• Exercise Induced Angina (values 1,0)
• ST depression induced by exercise relative to rest
• Slope of the peak exercise ST segment
• Number of major vessels (0-3) colored by flourosopy
• Thalassemia: 0 = normal; 1 = fixed defect; 2 = reversable defect

Programming Languages / Libraries

• Python
• NumPy
• Pandas
• Scikit-learn
• Flask
• HTML

Data

The dataset used can be found here:
https://www.kaggle.com/datasets/johnsmith88/heart-disease-dataset

File Descriptions

'HeartDiseasePrediction.ipynb'

• Jupyter notebook containing the logistic regression machine learning model predicting whether the patient has heart disease or not

'app.py'

• Python file containing code implementing a flask application and integrating the ML model with the HTML frontend

'heart.csv'

• CSV file containing the heart disease prediction dataset used in the project

'index.html'

• HTML file containing the app's frontend

'model.py'

• Python file containing the code for the logistic regression predictive model