Heart disease prediction is a Data Science Supervised Machine Learning Project to predict heart disease. Heart diseases are one of the major killers worldwide. Early detection of heart disease such as Global Hypokinesia can reduce this global burden. Computational method has potential to predict disease in early stages automatically and especially helpful in resources limited countries. The project involved analysis of the heart disease patient dataset with proper data processing. Then, different models were trained and and predictions are made with different algorithms KNN, Decision Tree, Random Forest,SVM,Logistic Regression etc This is the jupyter notebook code and dataset I've used for my Kaggle kernel 'Binary Classification with Sklearn and Keras'
Machine Learning algorithms used:
- Logistic Regression (Scikit-learn)
- Naive Bayes (Scikit-learn)
- Support Vector Machine (Linear) (Scikit-learn)
- K-Nearest Neighbours (Scikit-learn)
- Decision Tree (Scikit-learn)
- Random Forest (Scikit-learn)
- XGBoost (Scikit-learn)
- Artificial Neural Network with 1 Hidden layer (Keras)
Accuracy achieved: 95% (Random Forest)