Prediction of ICU Readmission Using LightGBM Classifier

Decision to discharge a patient from an intensive care unit (ICU) is difficult, with a risk of prolonging unnecessarily the stay and a risk of ICU readmission, which is associated with adverse outcomes. We propose to use light gradient boosting (lightGBM) classifier to build decision-making systems...

Full description

Saved in:
Bibliographic Details
Main Authors: Fathy, Waleed, Emeriaud, Guillaume, Cheriet, Farida
Format: Conference Proceeding
Language:English
Subjects:
Biological system modeling
Boosting
Classification
Decision making
Feature extraction
ICU Readmission
LightGBM
MIMICIII database
MIMICs
Predictive models
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Decision to discharge a patient from an intensive care unit (ICU) is difficult, with a risk of prolonging unnecessarily the stay and a risk of ICU readmission, which is associated with adverse outcomes. We propose to use light gradient boosting (lightGBM) classifier to build decision-making systems to predict which patients are most likely to experience ICU readmission within the first three days. The classifier was developed and tested using MIMICIII database. We extracted many clinical data from the electronic health records (EHR) stored in MIMICIII database. Then, several statistical, temporal and spectral features were extracted. In addition, some feature selection methods were used to select the most informative data. The performance of our LightGBM classifier is superior to the previously tested machine learning (ML) classifiers, as evidenced by an area under the curve (AUC) of 78.6%. The development of our prediction model for ICU readmission offers a more accurate approach to identifying patients at high risk, potentially reducing readmission rates and improving patient outcomes.
ISSN:1945-8452
DOI:10.1109/ISBI53787.2023.10230835