/Heart-Failure-Prediction-UCI

This repository contains the analysis of features and building a predictive model to predict the death event for patient with heart failure disease.

Primary LanguageJupyter Notebook

Heart-Failure-Prediction-UCI

Introduction

Heart failure is a medical condition where the heart muscle is having difficulty to pump the blood to circulate around the body. This is a medical condition that has a higher chance of threatening the lives of patients if left untreated. One of the major concerns on heart failure conditions that are developed over time is that it is a chronic condition that does not have any cure. It can only be improved with medication but will never be recovered. Moreover, the mortality rate of patients having heart failure is high after a certain follow up period. However, early identification of the condition of a patient having heart failure can help to improve their condition before worsen or at least higher chances of avoiding sudden death due to heart failure

Dataset

The dataset was obtained from UCI Machine Learning Repository https://archive.ics.uci.edu/ml/datasets/Heart+failure+clinical+records

Attribute / Features

Attributes/Features Measurement Range
Age Years [40...95]
Anaemia Text 0,1
Creatine Phosphokinase mcg/L [23...7861]
Diabetes Boolean 0,1
Ejection Fraction Percentage [14...80]
High Blood Pressure Boolean P0,1
Platelets kiloplatelets/mL [25100...850000]
Serum Creatinine mg/dL [0.5...9.4]
Serum Sodium mEq/L [113...148]
Sex Binary 0,1
Smoking Boolean 0,1
Time Days [4...285]
Death Event Boolean 0,1

NOTE: mcg/L: micrograms per liter. mL: microliter. mEq/L: milliequivalents per litre