Early risk assessment for COVID-19 patients from emergency department data using machine learning

Abstract Since its emergence in late 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic with more than 55 million reported cases and 1.3 million estimated deaths worldwide. While epidemiological and clinical characteristics of COVID-19 have been reported, ri...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Frank S. Heldt, Marcela P. Vizcaychipi, Sophie Peacock, Mattia Cinelli, Lachlan McLachlan, Fernando Andreotti, Stojan Jovanović, Robert Dürichen, Nadezda Lipunova, Robert A. Fletcher, Anne Hancock, Alex McCarthy, Richard A. Pointon, Alexander Brown, James Eaton, Roberto Liddi, Lucy Mackillop, Lionel Tarassenko, Rabia T. Khan
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/3a7ab14094eb4060a2ca9e6827b2ed55
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3a7ab14094eb4060a2ca9e6827b2ed55
record_format dspace
spelling oai:doaj.org-article:3a7ab14094eb4060a2ca9e6827b2ed552021-12-02T14:21:53ZEarly risk assessment for COVID-19 patients from emergency department data using machine learning10.1038/s41598-021-83784-y2045-2322https://doaj.org/article/3a7ab14094eb4060a2ca9e6827b2ed552021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83784-yhttps://doaj.org/toc/2045-2322Abstract Since its emergence in late 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic with more than 55 million reported cases and 1.3 million estimated deaths worldwide. While epidemiological and clinical characteristics of COVID-19 have been reported, risk factors underlying the transition from mild to severe disease among patients remain poorly understood. In this retrospective study, we analysed data of 879 confirmed SARS-CoV-2 positive patients admitted to a two-site NHS Trust hospital in London, England, between January 1st and May 26th, 2020, with a majority of cases occurring in March and April. We extracted anonymised demographic data, physiological clinical variables and laboratory results from electronic healthcare records (EHR) and applied multivariate logistic regression, random forest and extreme gradient boosted trees. To evaluate the potential for early risk assessment, we used data available during patients’ initial presentation at the emergency department (ED) to predict deterioration to one of three clinical endpoints in the remainder of the hospital stay: admission to intensive care, need for invasive mechanical ventilation and in-hospital mortality. Based on the trained models, we extracted the most informative clinical features in determining these patient trajectories. Considering our inclusion criteria, we have identified 129 of 879 (15%) patients that required intensive care, 62 of 878 (7%) patients needing mechanical ventilation, and 193 of 619 (31%) cases of in-hospital mortality. Our models learned successfully from early clinical data and predicted clinical endpoints with high accuracy, the best model achieving area under the receiver operating characteristic (AUC-ROC) scores of 0.76 to 0.87 (F1 scores of 0.42–0.60). Younger patient age was associated with an increased risk of receiving intensive care and ventilation, but lower risk of mortality. Clinical indicators of a patient’s oxygen supply and selected laboratory results, such as blood lactate and creatinine levels, were most predictive of COVID-19 patient trajectories. Among COVID-19 patients machine learning can aid in the early identification of those with a poor prognosis, using EHR data collected during a patient’s first presentation at ED. Patient age and measures of oxygenation status during ED stay are primary indicators of poor patient outcomes.Frank S. HeldtMarcela P. VizcaychipiSophie PeacockMattia CinelliLachlan McLachlanFernando AndreottiStojan JovanovićRobert DürichenNadezda LipunovaRobert A. FletcherAnne HancockAlex McCarthyRichard A. PointonAlexander BrownJames EatonRoberto LiddiLucy MackillopLionel TarassenkoRabia T. KhanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Frank S. Heldt
Marcela P. Vizcaychipi
Sophie Peacock
Mattia Cinelli
Lachlan McLachlan
Fernando Andreotti
Stojan Jovanović
Robert Dürichen
Nadezda Lipunova
Robert A. Fletcher
Anne Hancock
Alex McCarthy
Richard A. Pointon
Alexander Brown
James Eaton
Roberto Liddi
Lucy Mackillop
Lionel Tarassenko
Rabia T. Khan
Early risk assessment for COVID-19 patients from emergency department data using machine learning
description Abstract Since its emergence in late 2019, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a pandemic with more than 55 million reported cases and 1.3 million estimated deaths worldwide. While epidemiological and clinical characteristics of COVID-19 have been reported, risk factors underlying the transition from mild to severe disease among patients remain poorly understood. In this retrospective study, we analysed data of 879 confirmed SARS-CoV-2 positive patients admitted to a two-site NHS Trust hospital in London, England, between January 1st and May 26th, 2020, with a majority of cases occurring in March and April. We extracted anonymised demographic data, physiological clinical variables and laboratory results from electronic healthcare records (EHR) and applied multivariate logistic regression, random forest and extreme gradient boosted trees. To evaluate the potential for early risk assessment, we used data available during patients’ initial presentation at the emergency department (ED) to predict deterioration to one of three clinical endpoints in the remainder of the hospital stay: admission to intensive care, need for invasive mechanical ventilation and in-hospital mortality. Based on the trained models, we extracted the most informative clinical features in determining these patient trajectories. Considering our inclusion criteria, we have identified 129 of 879 (15%) patients that required intensive care, 62 of 878 (7%) patients needing mechanical ventilation, and 193 of 619 (31%) cases of in-hospital mortality. Our models learned successfully from early clinical data and predicted clinical endpoints with high accuracy, the best model achieving area under the receiver operating characteristic (AUC-ROC) scores of 0.76 to 0.87 (F1 scores of 0.42–0.60). Younger patient age was associated with an increased risk of receiving intensive care and ventilation, but lower risk of mortality. Clinical indicators of a patient’s oxygen supply and selected laboratory results, such as blood lactate and creatinine levels, were most predictive of COVID-19 patient trajectories. Among COVID-19 patients machine learning can aid in the early identification of those with a poor prognosis, using EHR data collected during a patient’s first presentation at ED. Patient age and measures of oxygenation status during ED stay are primary indicators of poor patient outcomes.
format article
author Frank S. Heldt
Marcela P. Vizcaychipi
Sophie Peacock
Mattia Cinelli
Lachlan McLachlan
Fernando Andreotti
Stojan Jovanović
Robert Dürichen
Nadezda Lipunova
Robert A. Fletcher
Anne Hancock
Alex McCarthy
Richard A. Pointon
Alexander Brown
James Eaton
Roberto Liddi
Lucy Mackillop
Lionel Tarassenko
Rabia T. Khan
author_facet Frank S. Heldt
Marcela P. Vizcaychipi
Sophie Peacock
Mattia Cinelli
Lachlan McLachlan
Fernando Andreotti
Stojan Jovanović
Robert Dürichen
Nadezda Lipunova
Robert A. Fletcher
Anne Hancock
Alex McCarthy
Richard A. Pointon
Alexander Brown
James Eaton
Roberto Liddi
Lucy Mackillop
Lionel Tarassenko
Rabia T. Khan
author_sort Frank S. Heldt
title Early risk assessment for COVID-19 patients from emergency department data using machine learning
title_short Early risk assessment for COVID-19 patients from emergency department data using machine learning
title_full Early risk assessment for COVID-19 patients from emergency department data using machine learning
title_fullStr Early risk assessment for COVID-19 patients from emergency department data using machine learning
title_full_unstemmed Early risk assessment for COVID-19 patients from emergency department data using machine learning
title_sort early risk assessment for covid-19 patients from emergency department data using machine learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/3a7ab14094eb4060a2ca9e6827b2ed55
work_keys_str_mv AT franksheldt earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT marcelapvizcaychipi earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT sophiepeacock earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT mattiacinelli earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT lachlanmclachlan earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT fernandoandreotti earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT stojanjovanovic earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT robertdurichen earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT nadezdalipunova earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT robertafletcher earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT annehancock earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT alexmccarthy earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT richardapointon earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT alexanderbrown earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT jameseaton earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT robertoliddi earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT lucymackillop earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT lioneltarassenko earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
AT rabiatkhan earlyriskassessmentforcovid19patientsfromemergencydepartmentdatausingmachinelearning
_version_ 1718391479486906368