Heart failure occurs when the heart is not able to pump enough blood to the body.
HF are only a subgroup of all the cardiovascular diseases that comprehend also coronary heart diseases (heart attacks), cerebrovascular diseases (strokes) and other pathologies that altogether kill every year approximately 17 million people around the world.
Machine learning applied to medical records can be useful to predict the survival of a patient, highlighting patterns and even ranking the features to understand which are risk factors, possibly undetectable by doctors.
In this notebook the analisys will be done starting from an EDA to understand the dataset and applying some preprocessing to be able to learn properly from it.
Then will follow a number of machine learning models trained on the preprocessed dataset, aiming to predict the survival of patients that suffered HF.
The results are presented at the end of the notebook.
The rendered notebook can be viewed here