Heart failure clinical records

This dataset contains the medical records of 299 patients who had heart failure, collected during their follow-up period, where each patient profile has 13 clinical features.

Characteristics
Multivariate
Subject Area
Health and Medicine
Associated Tasks
Classification, Regression, Clustering

Attribute Type
--
# Instances
299
# Attributes
12

Info

A detailed description of the dataset can be found in the Dataset section of the following paper:

Davide Chicco, Giuseppe Jurman: "Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone". BMC Medical Informatics and Decision Making 20, 16 (2020). https://doi.org/10.1186/s12911-020-1023-5


Introductory Paper

Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone

By D. Chicco, Giuseppe Jurman. 2020

Published in BMC Medical Informatics and Decision Making

Provided by
University of California, Irvine


Creators

DOI

10.24432/C5Z89R

Login to Download

New to AIM-AHEAD Connect?
Create an account!

Features

Attribute Name Role Type Demographic Description Units Missing Values
age Feature Integer Age age of the patient years no
anaemia Feature Binary decrease of red blood cells or hemoglobin no
creatinine_phosphokinase Feature Integer level of the CPK enzyme in the blood mcg/L no
diabetes Feature Binary if the patient has diabetes no
ejection_fraction Feature Integer percentage of blood leaving the heart at each contraction % no
high_blood_pressure Feature Binary if the patient has hypertension no
platelets Feature Continuous platelets in the blood kiloplatelets/mL no
serum_creatinine Feature Continuous level of serum creatinine in the blood mg/dL no
serum_sodium Feature Integer level of serum sodium in the blood mEq/L no
sex Feature Binary Sex woman or man no
smoking Feature Binary if the patient smokes or not no
time Feature Integer follow-up period days no
death_event Target Binary if the patient died during the follow-up period no