Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol, UK

ObjectiveThe primary objective is to develop an automated method for detecting patients that are ready for discharge from intensive care.DesignWe used two datasets of routinely collected patient data to test and improve on a set of previously proposed discharge criteria.SettingBristol Royal Infirmar...

Full description

Saved in:

Bibliographic Details
Published in:	BMJ open 2019-03, Vol.9 (3), p.e025925-e025925
Main Authors:	McWilliams, Christopher J, Lawson, Daniel J, Santos-Rodriguez, Raul, Gilchrist, Iain D, Champneys, Alan, Gould, Timothy H, Thomas, Mathew JC, Bourdeaux, Christopher P
Format:	Article
Language:	eng
Subjects:	Algorithms Artificial intelligence Clinical decision making Collaboration Critical care Critical Care - organization & administration Decision making Decision support systems Decision Support Techniques Discharge Electronic Health Records England Female Health informatics Humans Intensive Care Length of Stay - statistics & numerical data Machine Learning Male Pain Patient Discharge Patient Readmission - statistics & numerical data Patients
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	ObjectiveThe primary objective is to develop an automated method for detecting patients that are ready for discharge from intensive care.DesignWe used two datasets of routinely collected patient data to test and improve on a set of previously proposed discharge criteria.SettingBristol Royal Infirmary general intensive care unit (GICU).PatientsTwo cohorts derived from historical datasets: 1870 intensive care patients from GICU in Bristol, and 7592 from Medical Information Mart for Intensive Care (MIMIC)-III.ResultsIn both cohorts few successfully discharged patients met all of the discharge criteria. Both a random forest and a logistic classifier, trained using multiple-source cross-validation, demonstrated improved performance over the original criteria and generalised well between the cohorts. The classifiers showed good agreement on which features were most predictive of readiness-for-discharge, and these were generally consistent with clinical experience. By weighting the discharge criteria according to feature importance from the logistic model we showed improved performance over the original criteria, while retaining good interpretability.ConclusionsOur findings indicate the feasibility of the proposed approach to ready-for-discharge classification, which could complement other risk models of specific adverse outcomes in a future decision support system. Avenues for improvement to produce a clinically useful tool are identified.
ISSN:	2044-6055 2044-6055