Heart-Failure-Detection-Using-Machine-Learning-README.md

Short Introduction About 400,000 adults die of heart failure (HF) in the United States every year. HF occurs when the heart cannot pump enough blood to support the organs in the body [CDC]. Cardiovascular research studies have identified correlations between creatine levels, ejection fraction rates, and HF. Using machine learning classifiers, a patient's survival can be predicted based on important clinical features.

Python Script I. Exploratory data analysis

Correlation analysis K-Means clustering Agglomerative hierarchical clustering Principle component analysis II. Heart failure prediction

Splitting dataset into the test set and the training set Model evaluation Accuracy score, precision score, recall score, and f1 score for all the machine learning models Random forest and decision tree predictions Machine learning classifiers used:

Random Forest Classifier Logistic Regression K-Nearest Neighbors Support Vector Classification (linear) Support Vector Classification (radial basis function) Gaussian Naive Bayes Decision Tree XGBoost Original dataset version: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0181001 Link to the dataset: https://archive.ics.uci.edu/ml/datasets/Heart+failure+clinical+records Python packages used: pandas, matplotlib, numpy, scipy, seaborn, xgboost, and sklearn