Value of dynamic clinical and biomarker data for mortality risk prediction in COVID-19: a multicentre retrospective cohort studyCitation formats

Standard

Value of dynamic clinical and biomarker data for mortality risk prediction in COVID-19: a multicentre retrospective cohort study. / Berzuini, Carlo; Hannan, Cathal; King, Andrew; Vail, Andy; O'Leary, Claire; Brough, David; Galea, James; Ogungbenro, Kayode; Wright, Megan; Pathmanaban, Omar; Hulme, Sharon; Allan, Stuart; Bernardinelli, Luisa; Patel, Hiren C.

In: BMJ Open, Vol. 10, No. 9, 23.09.2020, p. e041983.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{df831c3afa5f4b499f1f73c01ee359b7,
title = "Value of dynamic clinical and biomarker data for mortality risk prediction in COVID-19: a multicentre retrospective cohort study",
abstract = "OBJECTIVES: Being able to predict which patients with COVID-19 are going to deteriorate is important to help identify patients for clinical and research practice. Clinical prediction models play a critical role in this process, but current models are of limited value because they are typically restricted to baseline predictors and do not always use contemporary statistical methods. We sought to explore the benefits of incorporating dynamic changes in routinely measured biomarkers, non-linear effects and applying 'state-of-the-art' statistical methods in the development of a prognostic model to predict death in hospitalised patients with COVID-19. DESIGN: The data were analysed from admissions with COVID-19 to three hospital sites. Exploratory data analysis included a graphical approach to partial correlations. Dynamic biomarkers were considered up to 5 days following admission rather than depending solely on baseline or single time-point data. Marked departures from linear effects of covariates were identified by employing smoothing splines within a generalised additive modelling framework. SETTING: 3 secondary and tertiary level centres in Greater Manchester, the UK. PARTICIPANTS: 392 hospitalised patients with a diagnosis of COVID-19. RESULTS: 392 patients with a COVID-19 diagnosis were identified. Area under the receiver operating characteristic curve increased from 0.73 using admission data alone to 0.75 when also considering results of baseline blood samples and to 0.83 when considering dynamic values of routinely collected markers. There was clear non-linearity in the association of age with patient outcome. CONCLUSIONS: This study shows that clinical prediction models to predict death in hospitalised patients with COVID-19 can be improved by taking into account both non-linear effects in covariates such as age and dynamic changes in values of biomarkers.",
keywords = "intensive & critical care, respiratory infections, statistics & research methods",
author = "Carlo Berzuini and Cathal Hannan and Andrew King and Andy Vail and Claire O'Leary and David Brough and James Galea and Kayode Ogungbenro and Megan Wright and Omar Pathmanaban and Sharon Hulme and Stuart Allan and Luisa Bernardinelli and Patel, {Hiren C.}",
note = "Publisher Copyright: {\textcopyright} Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY. Published by BMJ. Copyright: This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine",
year = "2020",
month = sep,
day = "23",
doi = "10.1136/bmjopen-2020-041983",
language = "English",
volume = "10",
pages = "e041983",
journal = "BMJ Open",
issn = "2044-6055",
publisher = "BMJ ",
number = "9",

}

RIS

TY - JOUR

T1 - Value of dynamic clinical and biomarker data for mortality risk prediction in COVID-19: a multicentre retrospective cohort study

AU - Berzuini, Carlo

AU - Hannan, Cathal

AU - King, Andrew

AU - Vail, Andy

AU - O'Leary, Claire

AU - Brough, David

AU - Galea, James

AU - Ogungbenro, Kayode

AU - Wright, Megan

AU - Pathmanaban, Omar

AU - Hulme, Sharon

AU - Allan, Stuart

AU - Bernardinelli, Luisa

AU - Patel, Hiren C.

N1 - Publisher Copyright: © Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY. Published by BMJ. Copyright: This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine

PY - 2020/9/23

Y1 - 2020/9/23

N2 - OBJECTIVES: Being able to predict which patients with COVID-19 are going to deteriorate is important to help identify patients for clinical and research practice. Clinical prediction models play a critical role in this process, but current models are of limited value because they are typically restricted to baseline predictors and do not always use contemporary statistical methods. We sought to explore the benefits of incorporating dynamic changes in routinely measured biomarkers, non-linear effects and applying 'state-of-the-art' statistical methods in the development of a prognostic model to predict death in hospitalised patients with COVID-19. DESIGN: The data were analysed from admissions with COVID-19 to three hospital sites. Exploratory data analysis included a graphical approach to partial correlations. Dynamic biomarkers were considered up to 5 days following admission rather than depending solely on baseline or single time-point data. Marked departures from linear effects of covariates were identified by employing smoothing splines within a generalised additive modelling framework. SETTING: 3 secondary and tertiary level centres in Greater Manchester, the UK. PARTICIPANTS: 392 hospitalised patients with a diagnosis of COVID-19. RESULTS: 392 patients with a COVID-19 diagnosis were identified. Area under the receiver operating characteristic curve increased from 0.73 using admission data alone to 0.75 when also considering results of baseline blood samples and to 0.83 when considering dynamic values of routinely collected markers. There was clear non-linearity in the association of age with patient outcome. CONCLUSIONS: This study shows that clinical prediction models to predict death in hospitalised patients with COVID-19 can be improved by taking into account both non-linear effects in covariates such as age and dynamic changes in values of biomarkers.

AB - OBJECTIVES: Being able to predict which patients with COVID-19 are going to deteriorate is important to help identify patients for clinical and research practice. Clinical prediction models play a critical role in this process, but current models are of limited value because they are typically restricted to baseline predictors and do not always use contemporary statistical methods. We sought to explore the benefits of incorporating dynamic changes in routinely measured biomarkers, non-linear effects and applying 'state-of-the-art' statistical methods in the development of a prognostic model to predict death in hospitalised patients with COVID-19. DESIGN: The data were analysed from admissions with COVID-19 to three hospital sites. Exploratory data analysis included a graphical approach to partial correlations. Dynamic biomarkers were considered up to 5 days following admission rather than depending solely on baseline or single time-point data. Marked departures from linear effects of covariates were identified by employing smoothing splines within a generalised additive modelling framework. SETTING: 3 secondary and tertiary level centres in Greater Manchester, the UK. PARTICIPANTS: 392 hospitalised patients with a diagnosis of COVID-19. RESULTS: 392 patients with a COVID-19 diagnosis were identified. Area under the receiver operating characteristic curve increased from 0.73 using admission data alone to 0.75 when also considering results of baseline blood samples and to 0.83 when considering dynamic values of routinely collected markers. There was clear non-linearity in the association of age with patient outcome. CONCLUSIONS: This study shows that clinical prediction models to predict death in hospitalised patients with COVID-19 can be improved by taking into account both non-linear effects in covariates such as age and dynamic changes in values of biomarkers.

KW - intensive & critical care

KW - respiratory infections

KW - statistics & research methods

UR - http://www.scopus.com/inward/record.url?scp=85091546755&partnerID=8YFLogxK

U2 - 10.1136/bmjopen-2020-041983

DO - 10.1136/bmjopen-2020-041983

M3 - Article

C2 - 32967887

VL - 10

SP - e041983

JO - BMJ Open

JF - BMJ Open

SN - 2044-6055

IS - 9

ER -