Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2: the COVIDSurg mortality score

COVIDSurg Collaborative; Alf Dorian Binder

doi:10.1093/bjs/znab183

Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2: the COVIDSurg mortality score

COVIDSurg Collaborative
, Alf Dorian Binder

Division of Surgery (University Hospital Tulln)

Research output: Journal article (peer-reviewed) › Journal article

23 Citations (Scopus)

Abstract

To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.

Original language	English
Article number	znab183
Pages (from-to)	1274-1292
Number of pages	19
Journal	British Journal of Surgery
Volume	108
Issue number	11
DOIs	https://doi.org/10.1093/bjs/znab183
Publication status	Published - 01 Jan 2021

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

COVID-19/mortality
Cohort Studies
Datasets as Topic
Humans
Machine Learning
Models, Statistical
Risk Assessment
SARS-CoV-2
Surgical Procedures, Operative/mortality

ASJC Scopus subject areas

General Medicine

Access to Document

10.1093/bjs/znab183

Cite this

@article{a38976bd381b44228e5896e2a63dce10,

title = "Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2: the COVIDSurg mortality score",

abstract = "To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.",

keywords = "COVID-19/mortality, Cohort Studies, Datasets as Topic, Humans, Machine Learning, Models, Statistical, Risk Assessment, SARS-CoV-2, Surgical Procedures, Operative/mortality",

author = "\{COVIDSurg Collaborative\} and Binder, \{Alf Dorian\}",

note = "Funding Information: This report was funded by a National Institute for Health Research (NIHR) Global Health Research Unit Grant (NIHR 16.136.79), Association of Coloproctology of Great Britain and Ireland, Bowel \& Cancer Research, Bowel Research UK, Association of Upper Gastrointestinal Surgeons, British Association of Surgical Oncology, British Gynaecological Cancer Society, European Society of Coloproctology, Medtronic, NIHR Academy, The Urology Foundation, Sarcoma UK, Vascular Society for Great Britain and Ireland, Yorkshire Cancer Research, and the MRC Health Data Research UK (HDRUK/CFC/01), an initiative funded by UK Research and Innovation, Department of Health and Social Care (England) and the devolved administrations, and leading medical research charities. L.B.M. and G.V.G. also acknowledge the Wellcome Trust 4-year studentship programme in mechanisms of inflammatory disease (MIDAS; 215182/Z/19/Z). The funders had no role in study design, data collection, analysis and interpretation, or writing of this report. The views expressed are those of the authors and not necessarily those of the National Health Service, the NIHR, or the UK Department of Health and Social Care.",

year = "2021",

month = jan,

day = "1",

doi = "10.1093/bjs/znab183",

language = "English",

volume = "108",

pages = "1274--1292",

journal = "British Journal of Surgery",

issn = "0007-1323",

publisher = "Oxford University Press",

number = "11",

}

TY - JOUR

T1 - Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2

T2 - the COVIDSurg mortality score

AU - COVIDSurg Collaborative

AU - Binder, Alf Dorian

N1 - Funding Information: This report was funded by a National Institute for Health Research (NIHR) Global Health Research Unit Grant (NIHR 16.136.79), Association of Coloproctology of Great Britain and Ireland, Bowel & Cancer Research, Bowel Research UK, Association of Upper Gastrointestinal Surgeons, British Association of Surgical Oncology, British Gynaecological Cancer Society, European Society of Coloproctology, Medtronic, NIHR Academy, The Urology Foundation, Sarcoma UK, Vascular Society for Great Britain and Ireland, Yorkshire Cancer Research, and the MRC Health Data Research UK (HDRUK/CFC/01), an initiative funded by UK Research and Innovation, Department of Health and Social Care (England) and the devolved administrations, and leading medical research charities. L.B.M. and G.V.G. also acknowledge the Wellcome Trust 4-year studentship programme in mechanisms of inflammatory disease (MIDAS; 215182/Z/19/Z). The funders had no role in study design, data collection, analysis and interpretation, or writing of this report. The views expressed are those of the authors and not necessarily those of the National Health Service, the NIHR, or the UK Department of Health and Social Care.

PY - 2021/1/1

Y1 - 2021/1/1

N2 - To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.

AB - To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.

KW - COVID-19/mortality

KW - Cohort Studies

KW - Datasets as Topic

KW - Humans

KW - Machine Learning

KW - Models, Statistical

KW - Risk Assessment

KW - SARS-CoV-2

KW - Surgical Procedures, Operative/mortality

UR - https://www.scopus.com/pages/publications/85113431484

U2 - 10.1093/bjs/znab183

DO - 10.1093/bjs/znab183

M3 - Journal article

C2 - 34227657

SN - 0007-1323

VL - 108

SP - 1274

EP - 1292

JO - British Journal of Surgery

JF - British Journal of Surgery

IS - 11

M1 - znab183

ER -

Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2: the COVIDSurg mortality score

Abstract

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this