A prognostic model for use before elective surgery to estimate the risk of postoperative pulmonary complications (GSU-Pulmonary Score): a development and validation study in three international cohorts

Standard

A prognostic model for use before elective surgery to estimate the risk of postoperative pulmonary complications (GSU-Pulmonary Score): a development and validation study in three international cohorts. / NIHR Global Health Research Unit on Global Surgery; STARSurg Collaborative.

in: LANCET DIGIT HEALTH, Jahrgang 6, Nr. 7, 07.2024, S. e507-e519.

Publikationen: SCORING: Beitrag in Fachzeitschrift/ZeitungSCORING: ZeitschriftenaufsatzForschungBegutachtung

Harvard

APA

Vancouver

Bibtex

@article{4651cadefaf542669c1b12d8b3fb9b91,
title = "A prognostic model for use before elective surgery to estimate the risk of postoperative pulmonary complications (GSU-Pulmonary Score): a development and validation study in three international cohorts",
abstract = "BACKGROUND: Pulmonary complications are the most common cause of death after surgery. This study aimed to derive and externally validate a novel prognostic model that can be used before elective surgery to estimate the risk of postoperative pulmonary complications and to support resource allocation and prioritisation during pandemic recovery.METHODS: Data from an international, prospective cohort study were used to develop a novel prognostic risk model for pulmonary complications after elective surgery in adult patients (aged ≥18 years) across all operation and disease types. The primary outcome measure was postoperative pulmonary complications at 30 days after surgery, which was a composite of pneumonia, acute respiratory distress syndrome, and unexpected mechanical ventilation. Model development with candidate predictor variables was done in the GlobalSurg-CovidSurg Week dataset (global; October, 2020). Two structured machine learning techniques were explored (XGBoost and the least absolute shrinkage and selection operator [LASSO]), and the model with the best performance (GSU-Pulmonary Score) underwent internal validation using bootstrap resampling. The discrimination and calibration of the score were externally validated in two further prospective cohorts: CovidSurg-Cancer (worldwide; February to August, 2020, during the COVID-19 pandemic) and RECON (UK and Australasia; January to October, 2019, before the COVID-19 pandemic). The model was deployed as an online web application. The GlobalSurg-CovidSurg Week and CovidSurg-Cancer studies were registered with ClinicalTrials.gov, NCT04509986 and NCT04384926.FINDINGS: Prognostic models were developed from 13 candidate predictor variables in data from 86 231 patients (1158 hospitals in 114 countries). External validation included 30 492 patients from CovidSurg-Cancer (726 hospitals in 75 countries) and 6789 from RECON (150 hospitals in three countries). The overall rates of pulmonary complications were 2·0% in derivation data, and 3·9% (CovidSurg-Cancer) and 4·7% (RECON) in the validation datasets. Penalised regression using LASSO had similar discrimination to XGBoost (area under the receiver operating curve [AUROC] 0·786, 95% CI 0·774-0·798 vs 0·785, 0·772-0·797), was more explainable, and required fewer covariables. The final GSU-Pulmonary Score included ten predictor variables and showed good discrimination and calibration upon internal validation (AUROC 0·773, 95% CI 0·751-0·795; Brier score 0·020, calibration in the large [CITL] 0·034, slope 0·954). The model performance was acceptable on external validation in CovidSurg-Cancer (AUROC 0·746, 95% CI 0·733-0·760; Brier score 0·036, CITL 0·109, slope 1·056), but with some miscalibration in RECON data (AUROC 0·716, 95% CI 0·689-0·744; Brier score 0·045, CITL 1·040, slope 1·009).INTERPRETATION: This novel prognostic risk score uses simple predictor variables available at the time of a decision for elective surgery that can accurately stratify patients' risk of postoperative pulmonary complications, including during SARS-CoV-2 outbreaks. It could inform surgical consent, resource allocation, and hospital-level prioritisation as elective surgery is upscaled to address global backlogs.FUNDING: National Institute for Health Research.",
keywords = "Humans, Elective Surgical Procedures/adverse effects, Postoperative Complications/epidemiology, Female, Prognosis, Middle Aged, Male, Prospective Studies, Aged, COVID-19/epidemiology, Risk Assessment/methods, Adult, Machine Learning, Risk Factors, Lung Diseases/etiology, Cohort Studies",
author = "{NIHR Global Health Research Unit on Global Surgery} and {STARSurg Collaborative} and Christine Nitschke and Betz, {Christian Stephan} and Julian Bewarder and Johannes Bier and Arne B{\"o}ttcher and Simon Burg and Chia-Jung Busch and Lara Bu{\ss}mann and Martin Gosau and Annika Heuer and Jakob Izbicki and Klatte, {Till Orla} and Daniela K{\"o}nig and Nikolaus M{\"o}ckelmann and Praetorius, {Mark Joachim} and Matthias Priemel and Rupert Stadlhofer and Martin Stangenberg and Uzunoglu, {Faik G{\"u}ntac} and Lukas Wittig and Zech, {Henrike Barbara Antonia Angelika} and Nina Zeller and Marc Dreimann and Karl-Heinz Frosch and Klatte, {Till Orla} and Daniel Perez and Leon-Gordian Leonhardt and Alonja Reiter and Lennart Viezens",
note = "Copyright {\textcopyright} 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.",
year = "2024",
month = jul,
doi = "10.1016/S2589-7500(24)00065-7",
language = "English",
volume = "6",
pages = "e507--e519",
journal = "LANCET DIGIT HEALTH",
issn = "2589-7500",
publisher = "Elsevier Ltd.",
number = "7",

}

RIS

TY - JOUR

T1 - A prognostic model for use before elective surgery to estimate the risk of postoperative pulmonary complications (GSU-Pulmonary Score): a development and validation study in three international cohorts

AU - NIHR Global Health Research Unit on Global Surgery

AU - STARSurg Collaborative

AU - Nitschke, Christine

AU - Betz, Christian Stephan

AU - Bewarder, Julian

AU - Bier, Johannes

AU - Böttcher, Arne

AU - Burg, Simon

AU - Busch, Chia-Jung

AU - Bußmann, Lara

AU - Gosau, Martin

AU - Heuer, Annika

AU - Izbicki, Jakob

AU - Klatte, Till Orla

AU - König, Daniela

AU - Möckelmann, Nikolaus

AU - Praetorius, Mark Joachim

AU - Priemel, Matthias

AU - Stadlhofer, Rupert

AU - Stangenberg, Martin

AU - Uzunoglu, Faik Güntac

AU - Wittig, Lukas

AU - Zech, Henrike Barbara Antonia Angelika

AU - Zeller, Nina

AU - Dreimann, Marc

AU - Frosch, Karl-Heinz

AU - Klatte, Till Orla

AU - Perez, Daniel

AU - Leonhardt, Leon-Gordian

AU - Reiter, Alonja

AU - Viezens, Lennart

N1 - Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved.

PY - 2024/7

Y1 - 2024/7

N2 - BACKGROUND: Pulmonary complications are the most common cause of death after surgery. This study aimed to derive and externally validate a novel prognostic model that can be used before elective surgery to estimate the risk of postoperative pulmonary complications and to support resource allocation and prioritisation during pandemic recovery.METHODS: Data from an international, prospective cohort study were used to develop a novel prognostic risk model for pulmonary complications after elective surgery in adult patients (aged ≥18 years) across all operation and disease types. The primary outcome measure was postoperative pulmonary complications at 30 days after surgery, which was a composite of pneumonia, acute respiratory distress syndrome, and unexpected mechanical ventilation. Model development with candidate predictor variables was done in the GlobalSurg-CovidSurg Week dataset (global; October, 2020). Two structured machine learning techniques were explored (XGBoost and the least absolute shrinkage and selection operator [LASSO]), and the model with the best performance (GSU-Pulmonary Score) underwent internal validation using bootstrap resampling. The discrimination and calibration of the score were externally validated in two further prospective cohorts: CovidSurg-Cancer (worldwide; February to August, 2020, during the COVID-19 pandemic) and RECON (UK and Australasia; January to October, 2019, before the COVID-19 pandemic). The model was deployed as an online web application. The GlobalSurg-CovidSurg Week and CovidSurg-Cancer studies were registered with ClinicalTrials.gov, NCT04509986 and NCT04384926.FINDINGS: Prognostic models were developed from 13 candidate predictor variables in data from 86 231 patients (1158 hospitals in 114 countries). External validation included 30 492 patients from CovidSurg-Cancer (726 hospitals in 75 countries) and 6789 from RECON (150 hospitals in three countries). The overall rates of pulmonary complications were 2·0% in derivation data, and 3·9% (CovidSurg-Cancer) and 4·7% (RECON) in the validation datasets. Penalised regression using LASSO had similar discrimination to XGBoost (area under the receiver operating curve [AUROC] 0·786, 95% CI 0·774-0·798 vs 0·785, 0·772-0·797), was more explainable, and required fewer covariables. The final GSU-Pulmonary Score included ten predictor variables and showed good discrimination and calibration upon internal validation (AUROC 0·773, 95% CI 0·751-0·795; Brier score 0·020, calibration in the large [CITL] 0·034, slope 0·954). The model performance was acceptable on external validation in CovidSurg-Cancer (AUROC 0·746, 95% CI 0·733-0·760; Brier score 0·036, CITL 0·109, slope 1·056), but with some miscalibration in RECON data (AUROC 0·716, 95% CI 0·689-0·744; Brier score 0·045, CITL 1·040, slope 1·009).INTERPRETATION: This novel prognostic risk score uses simple predictor variables available at the time of a decision for elective surgery that can accurately stratify patients' risk of postoperative pulmonary complications, including during SARS-CoV-2 outbreaks. It could inform surgical consent, resource allocation, and hospital-level prioritisation as elective surgery is upscaled to address global backlogs.FUNDING: National Institute for Health Research.

AB - BACKGROUND: Pulmonary complications are the most common cause of death after surgery. This study aimed to derive and externally validate a novel prognostic model that can be used before elective surgery to estimate the risk of postoperative pulmonary complications and to support resource allocation and prioritisation during pandemic recovery.METHODS: Data from an international, prospective cohort study were used to develop a novel prognostic risk model for pulmonary complications after elective surgery in adult patients (aged ≥18 years) across all operation and disease types. The primary outcome measure was postoperative pulmonary complications at 30 days after surgery, which was a composite of pneumonia, acute respiratory distress syndrome, and unexpected mechanical ventilation. Model development with candidate predictor variables was done in the GlobalSurg-CovidSurg Week dataset (global; October, 2020). Two structured machine learning techniques were explored (XGBoost and the least absolute shrinkage and selection operator [LASSO]), and the model with the best performance (GSU-Pulmonary Score) underwent internal validation using bootstrap resampling. The discrimination and calibration of the score were externally validated in two further prospective cohorts: CovidSurg-Cancer (worldwide; February to August, 2020, during the COVID-19 pandemic) and RECON (UK and Australasia; January to October, 2019, before the COVID-19 pandemic). The model was deployed as an online web application. The GlobalSurg-CovidSurg Week and CovidSurg-Cancer studies were registered with ClinicalTrials.gov, NCT04509986 and NCT04384926.FINDINGS: Prognostic models were developed from 13 candidate predictor variables in data from 86 231 patients (1158 hospitals in 114 countries). External validation included 30 492 patients from CovidSurg-Cancer (726 hospitals in 75 countries) and 6789 from RECON (150 hospitals in three countries). The overall rates of pulmonary complications were 2·0% in derivation data, and 3·9% (CovidSurg-Cancer) and 4·7% (RECON) in the validation datasets. Penalised regression using LASSO had similar discrimination to XGBoost (area under the receiver operating curve [AUROC] 0·786, 95% CI 0·774-0·798 vs 0·785, 0·772-0·797), was more explainable, and required fewer covariables. The final GSU-Pulmonary Score included ten predictor variables and showed good discrimination and calibration upon internal validation (AUROC 0·773, 95% CI 0·751-0·795; Brier score 0·020, calibration in the large [CITL] 0·034, slope 0·954). The model performance was acceptable on external validation in CovidSurg-Cancer (AUROC 0·746, 95% CI 0·733-0·760; Brier score 0·036, CITL 0·109, slope 1·056), but with some miscalibration in RECON data (AUROC 0·716, 95% CI 0·689-0·744; Brier score 0·045, CITL 1·040, slope 1·009).INTERPRETATION: This novel prognostic risk score uses simple predictor variables available at the time of a decision for elective surgery that can accurately stratify patients' risk of postoperative pulmonary complications, including during SARS-CoV-2 outbreaks. It could inform surgical consent, resource allocation, and hospital-level prioritisation as elective surgery is upscaled to address global backlogs.FUNDING: National Institute for Health Research.

KW - Humans

KW - Elective Surgical Procedures/adverse effects

KW - Postoperative Complications/epidemiology

KW - Female

KW - Prognosis

KW - Middle Aged

KW - Male

KW - Prospective Studies

KW - Aged

KW - COVID-19/epidemiology

KW - Risk Assessment/methods

KW - Adult

KW - Machine Learning

KW - Risk Factors

KW - Lung Diseases/etiology

KW - Cohort Studies

U2 - 10.1016/S2589-7500(24)00065-7

DO - 10.1016/S2589-7500(24)00065-7

M3 - SCORING: Journal article

C2 - 38906616

VL - 6

SP - e507-e519

JO - LANCET DIGIT HEALTH

JF - LANCET DIGIT HEALTH

SN - 2589-7500

IS - 7

ER -