Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts
<p><Strong>Rationale:</strong> Intensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with Early Warning Score (EWS) systems being use...
Main Authors: | , , , , , , , , |
---|---|
Format: | Journal article |
Language: | English |
Published: |
BMJ Publishing Group
2024
|
_version_ | 1811139620866359296 |
---|---|
author | Pimentel, MAF Johnson, A Darbyshire, JL Tarassenko, L Clifton, DA Walden, A Rechner, I Watkinson, PJ Young, JD |
author_facet | Pimentel, MAF Johnson, A Darbyshire, JL Tarassenko, L Clifton, DA Walden, A Rechner, I Watkinson, PJ Young, JD |
author_sort | Pimentel, MAF |
collection | OXFORD |
description | <p><Strong>Rationale:</strong> Intensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with Early Warning Score (EWS) systems being used to identify those at risk of deterioration.</p>
<br>
<p><Strong>Objectives:</strong> We report the development and validation of an enhanced continuous scoring system for predicting adverse events, which combines vital signs measured routinely on acute care wards (as used by most EWS systems) with a risk score of a future adverse event calculated on discharge from the ICU.</p>
<br>
<p><strong>Design:</strong> A modified Delphi process identified candidate variables commonly available in electronic records as the basis for a ‘static’ score of the patient’s condition immediately after discharge from the ICU. L1-regularised logistic regression was used to estimate the in-hospital risk of future adverse event. We then constructed a model of physiological normality using vital sign data from the day of hospital discharge. This is combined with the static score and used continuously to quantify and update the patient’s risk of deterioration throughout their hospital stay.</p>
<br>
<p><strong>Setting:</strong> Data from two National Health Service Foundation Trusts (UK) were used to develop and (externally) validate the model.</p>
<br>
<p><strong>Participants:</strong> A total of 12 394 vital sign measurements were acquired from 273 patients after ICU discharge for the development set, and 4831 from 136 patients in the validation cohort.</p>
<br>
<p><Strong>Results:</strong> Outcome validation of our model yielded an area under the receiver operating characteristic curve of 0.724 for predicting ICU readmission or in-hospital death within 24 hours. It showed an improved performance with respect to other competitive risk scoring systems, including the National EWS (0.653).</p>
<br>
<p><strong>Conclusions:</strong> We showed that a scoring system incorporating data from a patient’s stay in the ICU has better performance than commonly used EWS systems based on vital signs alone.</p>
<br>
<p><strong>Trial registration number:</strong> ISRCTN32008295.</p> |
first_indexed | 2024-09-25T04:08:59Z |
format | Journal article |
id | oxford-uuid:752d8609-cb14-4205-8898-5db86c4496e5 |
institution | University of Oxford |
language | English |
last_indexed | 2024-09-25T04:08:59Z |
publishDate | 2024 |
publisher | BMJ Publishing Group |
record_format | dspace |
spelling | oxford-uuid:752d8609-cb14-4205-8898-5db86c4496e52024-06-07T15:37:36ZDevelopment of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation TrustsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:752d8609-cb14-4205-8898-5db86c4496e5EnglishSymplectic ElementsBMJ Publishing Group2024Pimentel, MAFJohnson, ADarbyshire, JLTarassenko, LClifton, DAWalden, ARechner, IWatkinson, PJYoung, JD<p><Strong>Rationale:</strong> Intensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with Early Warning Score (EWS) systems being used to identify those at risk of deterioration.</p> <br> <p><Strong>Objectives:</strong> We report the development and validation of an enhanced continuous scoring system for predicting adverse events, which combines vital signs measured routinely on acute care wards (as used by most EWS systems) with a risk score of a future adverse event calculated on discharge from the ICU.</p> <br> <p><strong>Design:</strong> A modified Delphi process identified candidate variables commonly available in electronic records as the basis for a ‘static’ score of the patient’s condition immediately after discharge from the ICU. L1-regularised logistic regression was used to estimate the in-hospital risk of future adverse event. We then constructed a model of physiological normality using vital sign data from the day of hospital discharge. This is combined with the static score and used continuously to quantify and update the patient’s risk of deterioration throughout their hospital stay.</p> <br> <p><strong>Setting:</strong> Data from two National Health Service Foundation Trusts (UK) were used to develop and (externally) validate the model.</p> <br> <p><strong>Participants:</strong> A total of 12 394 vital sign measurements were acquired from 273 patients after ICU discharge for the development set, and 4831 from 136 patients in the validation cohort.</p> <br> <p><Strong>Results:</strong> Outcome validation of our model yielded an area under the receiver operating characteristic curve of 0.724 for predicting ICU readmission or in-hospital death within 24 hours. It showed an improved performance with respect to other competitive risk scoring systems, including the National EWS (0.653).</p> <br> <p><strong>Conclusions:</strong> We showed that a scoring system incorporating data from a patient’s stay in the ICU has better performance than commonly used EWS systems based on vital signs alone.</p> <br> <p><strong>Trial registration number:</strong> ISRCTN32008295.</p> |
spellingShingle | Pimentel, MAF Johnson, A Darbyshire, JL Tarassenko, L Clifton, DA Walden, A Rechner, I Watkinson, PJ Young, JD Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts |
title | Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts |
title_full | Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts |
title_fullStr | Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts |
title_full_unstemmed | Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts |
title_short | Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts |
title_sort | development of an enhanced scoring system to predict icu readmission or in hospital death within 24 hours using routine patient data from two nhs foundation trusts |
work_keys_str_mv | AT pimentelmaf developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT johnsona developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT darbyshirejl developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT tarassenkol developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT cliftonda developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT waldena developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT rechneri developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT watkinsonpj developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts AT youngjd developmentofanenhancedscoringsystemtopredicticureadmissionorinhospitaldeathwithin24hoursusingroutinepatientdatafromtwonhsfoundationtrusts |