Article Text

Download PDFPDF

Towards a decision support tool for intensive care discharge: machine learning algorithm development using electronic healthcare data from MIMIC-III and Bristol, UK
  1. Christopher J McWilliams1,
  2. Daniel J Lawson2,
  3. Raul Santos-Rodriguez1,
  4. Iain D Gilchrist3,
  5. Alan Champneys1,
  6. Timothy H Gould4,
  7. Mathew JC Thomas4,
  8. Christopher P Bourdeaux4
  1. 1 Engineering Mathematics, University of Bristol, Bristol, UK
  2. 2 Integrative Epidemiology Unit, Population Health Sciences, University of Bristol, Bristol, UK
  3. 3 Department of Experimental Psychology, University of Bristol, Bristol, UK
  4. 4 Intensive Care Unit, University Hospitals Bristol NHS Foundation Trust, Bristol, UK
  1. Correspondence to Dr Christopher J McWilliams; chris.mcwilliams{at}


Objective The primary objective is to develop an automated method for detecting patients that are ready for discharge from intensive care.

Design We used two datasets of routinely collected patient data to test and improve on a set of previously proposed discharge criteria.

Setting Bristol Royal Infirmary general intensive care unit (GICU).

Patients Two cohorts derived from historical datasets: 1870 intensive care patients from GICU in Bristol, and 7592 from Medical Information Mart for Intensive Care (MIMIC)-III.

Results In 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.

Conclusions Our 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.

  • cinical audit
  • health informatics
  • information technology

This is an open access article distributed in accordance with the Creative Commons Attribution 4.0 Unported (CC BY 4.0) license, which permits others to copy, redistribute, remix, transform and build upon this work for any purpose, provided the original work is properly cited, a link to the licence is given, and indication of whether changes were made. See:

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.


  • Contributors CJM is the main author and conducted the data processing and analysis. RS-R and DJL made important technical and methodological contributions. IDG, AC and CPB drove the study concept and design. The clinical expertise of THG, MJCT and CPB informed all stages of the project, in particular study design and interpretation of results. All authors contributed to writing the manuscript and approved the final version.

  • Funding This work was supported in part by EurValve (Personalised Decision Supportfor Heart Valve Disease), Project Number: H2020 PHC-30-2015, 689617. CJM was funded by the Elizabeth Blackwell Institute Catalyst Fund. DJL is funded by Wellcome Trust and Royal Society Grant Number WT104125MA.

  • Competing interests None declared.

  • Ethics approval CAG guidelines followed and study protocol presented to University Hospitals Bristol NHS Foundation Trust institutional review board.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data sharing statement Feature matrices will be made available on Dryad. Python code for analysis and processing on request directly from the corresponding author.

  • Patient consent for publication Not required.