Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality

Drago Plečko; Nicolas Bennett; Johan Mårtensson; Tariq A Dam; Robert Entjes; Thijs C D Rettig; Dave A Dongelmans; Age D Boelens; Sander Rigter; Stefaan H A Hendriks; Remko de Jong; Marlijn J A Kamps; Marco Peters; Attila Karakus; Diederik Gommers; Dharmanand Ramnarain; Evert-Jan Wils; Sefanja Achterberg; Ralph Nowitzky; Walter van den Tempel; Cornelis P C de Jager; Fleur G C A Nooteboom; Evelien Oostdijk; Peter Koetsier; Alexander D Cornet; Auke C Reidinga; Wouter de Ruijter; Rob J Bosman; Tim Frenzel; Louise C Urlings-Strop; Paul de Jong; Ellen G M Smit; Olaf L Cremer; D Jannet Mehagnoul-Schipper; Harald J Faber; Judith Lens; Gert B Brunnekreef; Barbara Festen-Spanjer; Tom Dormans; Daan P de Bruin; Robbert C A Lalisang; Sebastiaan J J Vonk; Martin E Haan; Lucas M Fleuren; Patrick J Thoral; Paul W G Elbers; Rinaldo Bellomo

doi:10.1111/aas.13991

Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality

Drago Plečko, Nicolas Bennett, Johan Mårtensson, Tariq A Dam, Robert Entjes, Thijs C D Rettig, Dave A Dongelmans, Age D Boelens, Sander Rigter, Stefaan H A Hendriks, Remko de Jong, Marlijn J A Kamps, Marco Peters, Attila Karakus, Diederik Gommers, Dharmanand Ramnarain, Evert-Jan Wils, Sefanja Achterberg, Ralph Nowitzky, Walter van den TempelCornelis P C de Jager, Fleur G C A Nooteboom, Evelien Oostdijk, Peter Koetsier, Alexander D Cornet, Auke C Reidinga, Wouter de Ruijter, Rob J Bosman, Tim Frenzel, Louise C Urlings-Strop, Paul de Jong, Ellen G M Smit, Olaf L Cremer, D Jannet Mehagnoul-Schipper, Harald J Faber, Judith Lens, Gert B Brunnekreef, Barbara Festen-Spanjer, Tom Dormans, Daan P de Bruin, Robbert C A Lalisang, Sebastiaan J J Vonk, Martin E Haan, Lucas M Fleuren, Patrick J Thoral, Paul W G Elbers, Rinaldo Bellomo

Research output: Contribution to journal › Article › Academic › peer-review

5 Downloads (Pure)

Abstract

BACKGROUND: The prediction of in-hospital mortality for ICU patients with COVID-19 is fundamental to treatment and resource allocation. The main purpose was to develop an easily implemented score for such prediction.

METHODS: This was an observational, multicenter, development, and validation study on a national critical care dataset of COVID-19 patients. A systematic literature review was performed to determine variables possibly important for COVID-19 mortality prediction. Using a logistic multivariable model with a LASSO penalty, we developed the Rapid Evaluation of Coronavirus Illness Severity (RECOILS) score and compared its performance against published scores.

RESULTS: Our development (validation) cohort consisted of 1480 (937) adult patients from 14 (11) Dutch ICUs admitted between March 2020 and April 2021. Median age was 65 (65) years, 31% (26%) died in hospital, 74% (72%) were males, average length of ICU stay was 7.83 (10.25) days and average length of hospital stay was 15.90 (19.92) days. Age, platelets, PaO2/FiO2 ratio, pH, blood urea nitrogen, temperature, PaCO2, Glasgow Coma Scale (GCS) score measured within +/-24 h of ICU admission were used to develop the score. The AUROC of RECOILS score was 0.75 (CI 0.71-0.78) which was higher than that of any previously reported predictive scores (0.68 [CI 0.64-0.71], 0.61 [CI 0.58-0.66], 0.67 [CI 0.63-0.70], 0.70 [CI 0.67-0.74] for ISARIC 4C Mortality Score, SOFA, SAPS-III, and age, respectively).

CONCLUSIONS: Using a large dataset from multiple Dutch ICUs, we developed a predictive score for mortality of COVID-19 patients admitted to ICU, which outperformed other predictive scores reported so far.

Original language	English
Pages (from-to)	65-75
Number of pages	11
Journal	Acta Anaesthesiologica Scandinavica
Volume	66
Issue number	1
Early online date	15 Oct 2021
DOIs	https://doi.org/10.1111/aas.13991
Publication status	Published - Jan 2022

Keywords

corona virus
COVID-19
intensive care
mechanical ventilation
respiratory failure

Access to Document

10.1111/aas.13991Licence: CC BY

Acta Anaesthesiol Scand - 2021 - Ple ko - Rapid Evaluation of Coronavirus Illness Severity RECOILS in intensive care Final published version, 853 KBLicence: CC BY

Cite this

Plečko, D., Bennett, N., Mårtensson, J., Dam, T. A., Entjes, R., Rettig, T. C. D., Dongelmans, D. A., Boelens, A. D., Rigter, S., Hendriks, S. H. A., de Jong, R., Kamps, M. J. A., Peters, M., Karakus, A., Gommers, D., Ramnarain, D., Wils, E.-J., Achterberg, S., Nowitzky, R., ... Bellomo, R. (2022). Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality. Acta Anaesthesiologica Scandinavica, 66(1), 65-75. https://doi.org/10.1111/aas.13991

@article{0d21ed55fc7443649fe0e09391a39cb1,

title = "Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality",

abstract = "BACKGROUND: The prediction of in-hospital mortality for ICU patients with COVID-19 is fundamental to treatment and resource allocation. The main purpose was to develop an easily implemented score for such prediction.METHODS: This was an observational, multicenter, development, and validation study on a national critical care dataset of COVID-19 patients. A systematic literature review was performed to determine variables possibly important for COVID-19 mortality prediction. Using a logistic multivariable model with a LASSO penalty, we developed the Rapid Evaluation of Coronavirus Illness Severity (RECOILS) score and compared its performance against published scores.RESULTS: Our development (validation) cohort consisted of 1480 (937) adult patients from 14 (11) Dutch ICUs admitted between March 2020 and April 2021. Median age was 65 (65) years, 31% (26%) died in hospital, 74% (72%) were males, average length of ICU stay was 7.83 (10.25) days and average length of hospital stay was 15.90 (19.92) days. Age, platelets, PaO2/FiO2 ratio, pH, blood urea nitrogen, temperature, PaCO2, Glasgow Coma Scale (GCS) score measured within +/-24 h of ICU admission were used to develop the score. The AUROC of RECOILS score was 0.75 (CI 0.71-0.78) which was higher than that of any previously reported predictive scores (0.68 [CI 0.64-0.71], 0.61 [CI 0.58-0.66], 0.67 [CI 0.63-0.70], 0.70 [CI 0.67-0.74] for ISARIC 4C Mortality Score, SOFA, SAPS-III, and age, respectively).CONCLUSIONS: Using a large dataset from multiple Dutch ICUs, we developed a predictive score for mortality of COVID-19 patients admitted to ICU, which outperformed other predictive scores reported so far.",

keywords = "corona virus, COVID-19, intensive care, mechanical ventilation, respiratory failure",

author = "Drago Ple{\v c}ko and Nicolas Bennett and Johan M{\aa}rtensson and Dam, {Tariq A} and Robert Entjes and Rettig, {Thijs C D} and Dongelmans, {Dave A} and Boelens, {Age D} and Sander Rigter and Hendriks, {Stefaan H A} and {de Jong}, Remko and Kamps, {Marlijn J A} and Marco Peters and Attila Karakus and Diederik Gommers and Dharmanand Ramnarain and Evert-Jan Wils and Sefanja Achterberg and Ralph Nowitzky and {van den Tempel}, Walter and {de Jager}, {Cornelis P C} and Nooteboom, {Fleur G C A} and Evelien Oostdijk and Peter Koetsier and Cornet, {Alexander D} and Reidinga, {Auke C} and {de Ruijter}, Wouter and Bosman, {Rob J} and Tim Frenzel and Urlings-Strop, {Louise C} and {de Jong}, Paul and Smit, {Ellen G M} and Cremer, {Olaf L} and Mehagnoul-Schipper, {D Jannet} and Faber, {Harald J} and Judith Lens and Brunnekreef, {Gert B} and Barbara Festen-Spanjer and Tom Dormans and {de Bruin}, {Daan P} and Lalisang, {Robbert C A} and Vonk, {Sebastiaan J J} and Haan, {Martin E} and Fleuren, {Lucas M} and Thoral, {Patrick J} and Elbers, {Paul W G} and Rinaldo Bellomo",

note = "Funding Information: Authors DP and NB are supported by the grant #2017-110 of the Strategic Focal Area “Personalized Health and Related Technologies (PHRT)” of the ETH Domain for the SPHN/PHRT Driver Project {\textquoteleft}Personalized Swiss Sepsis Study{\textquoteright}. Other authors are funded by their respective institutions. From collaborating hospitals having shared data: Remko van den Akker, Intensive Care, Adrz, Goes, The Netherlands, [email protected]; Tom A. Rijpstra, MD, Department of Intensive Care, Amphia Ziekenhuis, Breda, The Netherlands, [email protected]; M.C. Reuland, MD, Department of Intensive Care Medicine, Amsterdam UMC, Universiteit van Amsterdam, Amsterdam, The Netherlands, [email protected]; Klaas Sierk Arnold, MD, Anesthesiology, Antonius Ziekenhuis Sneek, Sneek, The Netherlands, [email protected]; Arend Jan Meinders, MD, Department of Internal Medicine and Intensive Care, St Antonius Hospital, Nieuwegein, The Netherlands, [email protected]; Nicolas Schroten, MD, Intensive Care, Albert Schweitzerziekenhuis, Dordrecht, The Netherlands, [email protected]; Laura van Manen, MD, Department of Intensive Care, BovenIJ Ziekenhuis, Amsterdam, The Netherlands, [email protected]; Leon Montenij, MD, PhD, Department of Anesthesiology, Pain Management and Intensive Care, Catharina Ziekenhuis Eindhoven, Eindhoven, The Netherlands, [email protected]; Julia Koeter, MD, Intensive Care, Canisius Wilhelmina Ziekenhuis, Nijmegen, The Netherlands, [email protected]; J.W. Fijen, MD, PhD, Department of Intensive Care, Diakonessenhuis Hospital, Utrecht, The Netherland, [email protected]; Jasper van Bommel, MD, PhD, Department of Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands, [email protected]; Roy van den Berg, Department of Intensive Care, ETZ Tilburg, Tilburg, The Netherlands, [email protected]; Martha de Bruin, MD, Department of Intensive Care, Franciscus Gasthuis & Vlietland, Rotterdam, The Netherlands, [email protected]; Roger van Rietschote, Business Intelligence, Haaglanden MC, Den Haag, The Netherlands, [email protected]; Ellen van Geest, Department of ICMT, Haga Ziekenhuis, Den Haag, The Netherlands, [email protected]; Koen S. Simons, MD, PhD, Department of Intensive Care, Jeroen Bosch Ziekenhuis, Den Bosch, The Netherlands, [email protected]; Anisa Hana, MD, PhD, Intensive Care, Laurentius Ziekenhuis, Roermond, The Netherlands, [email protected]; Joost Labout, MD, PhD, ICU, Maasstad Ziekenhuis Rotterdam, The Netherlands, [email protected]; Michael Kuiper, Intensive Care, Medisch Centrum Leeuwarden, Leeuwarden, The Netherlands, [email protected]; Albertus Beishuizen, MD, PhD, Department of Intensive Care, Medisch Spectrum Twente, Enschede, The Netherlands, [email protected]; Bart van de Gaauw, MD, PhD, Martiniziekenhuis, Groningen, The Netherlands, [email protected]; Roos Renckens, MD, PhD, Department of Internal Medicine, Northwest Clinics, Alkmaar, the Netherlands, [email protected]; B. van den Bogaard, MD, PhD, ICU, OLVG, Amsterdam, The Netherlands, [email protected]; Prof. Peter Pickkers, Department of Intensive Care Medicine, Radboud University Medical Centre, Nijmegen, The Netherlands, [email protected]; Pim van der Heiden, MD, PhD, Intensive Care, Reinier de Graaf Gasthuis, Delft, The Netherlands, [email protected]; Dennis Geutjes, Department of Information Technology, Slingeland Ziekenhuis, Doetinchem, The Netherlands, [email protected]; Claudia (C.W.) van Gemeren, MD, Intensive Care, Spaarne Gasthuis, Haarlem en Hoofddorp, The Netherlands, [email protected]; Emma Rademaker, MD, MSc, Department of Intensive Care, UMC Utrecht, Utrecht, The Netherlands, [email protected]; Frits H.M. van Osch, PhD, Department of Clinical Epidemiology, VieCuri Medisch Centrum, Venlo, The Netherlands, [email protected]; Johan Lutisan, MD, ICU, WZA, Assen, The Netherlands, [email protected]; Jacomar J.M. van Koesveld, MD, ICU, IJsselland Ziekenhuis, Capelle aan den IJssel, The Netherlands, [email protected]; Bart P. Grady, MD, PhD, Department of Intensive Care, Ziekenhuisgroep Twente, Almelo, The Netherlands, [email protected]; and Martijn de Kruif, MD, PhD, Department of Pulmonology, Zuyderland MC, Heerlen, The Netherlands, [email protected]. From collaborating hospitals having signed the data sharing agreement: Bram Simons, MD, Intensive Care, Bravis Ziekenhuis, Bergen op Zoom en Roosendaal, The Netherlands, [email protected]; A.A. Rijkeboer, MD, ICU, Flevoziekenhuis, Almere, The Netherlands, [email protected]; Annemieke Dijkstra, MD, Department of Intensive Care Medicine, Het Van Weel-Bethesda Ziekenhuis, Dirksland, The Netherlands, [email protected]; Sesmu Arbous, MD, PhD, Intensivist, LUMC, Leiden, The Netherlands, [email protected]; Marcel Aries, MD, PhD, MUMC+, University Maastricht, Maastricht, The Netherlands, [email protected]; Menno Beukema, MD, Department of Intensive Care, Streekziekenhuis Koningin Beatrix, Winterswijk, The Netherlands, [email protected]; Dani{\"e}l Pretorius, MD, Department of Intensive Care Medicine, Hospital St Jansdal, Harderwijk, The Netherlands, [email protected]; Rutger van Raalte, Department of Intensive Care, Tergooi hospital, Hilversum, The Netherlands, [email protected]; Martijn van Tellingen, MD, EDIC, Department of Intensive Care Medicine, afdeling Intensive Care, ziekenhuis Tjongerschans, Heerenveen, The Netherlands, [email protected]; Niels C. Gritters van den Oever, MD, Intensive Care, Treant Zorggroep, Emmen, The Netherlands, [email protected]. From the Laboratory for Critical Care Computational Intelligence: Armand R.J. Girbes, MD, PhD, EDIC, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Amsterdam, The Netherlands, [email protected]; Luca Roggeveen, MD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Dagmar M. Ouweneel, PhD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Ronald Driessen, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Jan Peppink, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; H.J. de Grooth, MD, PhD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; G.J. Zijlstra, MD, PhD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; A.J. van Tienhoven, MD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Evelien van der Heiden, MD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Jan Jaap Spijkstra, MD, PhD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Hans van der Spoel, MD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Angelique de Man, MD, PhD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Thomas Klausch, PhD, Department of Clinical Epidemiology, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Heder J. de Vries, MD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Mark Hoogendoorn, PhD, Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; Fuda van Diggelen, MSc, Quantitative Data Analytics Group, Department of Computer Sciences, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; Ali el Hassouni, PhD, Quantitative Data Analytics Group, Department of Computer Sciences, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; David Romero Guzman, PhD, Quantitative Data Analytics Group, Department of Computer Sciences, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; Sandjai Bhulai, PhD, Analytics and Optimization Group, Department of Mathematics, Faculty of Science, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]. From Pacmed: Michele Tonutti, MRes, Pacmed, Amsterdam, The Netherlands, [email protected]; Mattia Fornasa, PhD, Pacmed, Amsterdam, The Netherlands, [email protected]; Tomas Machado, Pacmed, Amsterdam, The Netherlands, [email protected]; Adam Izdebski, Pacmed, Amsterdam, The Netherlands, [email protected]; Taco Houwert, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Hidde Hovenkamp, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Roberto Noorduijn Londono, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Davide Quintarelli, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Martijn G. Scholtemeijer, MD, Pacmed, Amsterdam, The Netherlands, [email protected]; Aletta A. de Beer, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Giovanni Cin{\`a}, PhD, Pacmed, Amsterdam, The Netherlands, [email protected]; Willem E. Herter, BSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Michael de Neree tot Babberich, Pacmed, Amsterdam, The Netherlands, [email protected]; Olivier Thijssens, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Lot Wagemakers, Pacmed, Amsterdam, The Netherlands, [email protected]; Hilde G.A. van der Pol, Pacmed, Amsterdam, The Netherlands, [email protected]; Tom Hendriks, Pacmed, Amsterdam, The Netherlands, [email protected]; Julie Berend, Pacmed, Amsterdam, The Netherlands, [email protected]; Virginia Ceni Silva, Pacmed, Amsterdam, The Netherlands, [email protected]; Robert F.J. Kullberg, MD, Pacmed, Amsterdam, The Netherlands, [email protected]. From RCCnet: Leo Heunks, MD, PhD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Nicole Juffermans, MD, PhD, ICU, OLVG, Amsterdam, The Netherlands, [email protected]; Arjen J.C. Slooter, MD, PhD, Department of Intensive Care Medicine, UMC Utrecht, Utrecht University, Utrecht, the Netherlands, [email protected]. From other collaborating partners:Martijn Beudel, MD, PhD, Department of Neurology, Amsterdam UMC, Universiteit van Amsterdam, Amsterdam, The Netherlands, [email protected]; Nicolet F. de Keizer, PhD, Department of Clinical Informatics, Amsterdam UMC, Amsterdam, The Netherlands, [email protected]. Funding Information: Authors DP and NB are supported by the grant #2017‐110 of the Strategic Focal Area “Personalized Health and Related Technologies (PHRT)” of the ETH Domain for the SPHN/PHRT Driver Project {\textquoteleft}Personalized Swiss Sepsis Study{\textquoteright}. Other authors are funded by their respective institutions. Publisher Copyright: {\textcopyright} 2021 The Authors. Acta Anaesthesiologica Scandinavica published by John Wiley & Sons Ltd on behalf of Acta Anaesthesiologica Scandinavica Foundation.",

year = "2022",

month = jan,

doi = "10.1111/aas.13991",

language = "English",

volume = "66",

pages = "65--75",

journal = "Acta Anaesthesiologica Scandinavica",

issn = "0001-5172",

publisher = "Blackwell Munksgaard",

number = "1",

}

Plečko, D, Bennett, N, Mårtensson, J, Dam, TA, Entjes, R, Rettig, TCD, Dongelmans, DA, Boelens, AD, Rigter, S, Hendriks, SHA, de Jong, R, Kamps, MJA, Peters, M, Karakus, A, Gommers, D, Ramnarain, D, Wils, E-J, Achterberg, S, Nowitzky, R, van den Tempel, W, de Jager, CPC, Nooteboom, FGCA, Oostdijk, E, Koetsier, P, Cornet, AD, Reidinga, AC, de Ruijter, W, Bosman, RJ, Frenzel, T, Urlings-Strop, LC, de Jong, P, Smit, EGM, Cremer, OL, Mehagnoul-Schipper, DJ, Faber, HJ, Lens, J, Brunnekreef, GB, Festen-Spanjer, B, Dormans, T, de Bruin, DP, Lalisang, RCA, Vonk, SJJ, Haan, ME, Fleuren, LM, Thoral, PJ, Elbers, PWG & Bellomo, R 2022, 'Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality', Acta Anaesthesiologica Scandinavica, vol. 66, no. 1, pp. 65-75. https://doi.org/10.1111/aas.13991

Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality. / Plečko, Drago; Bennett, Nicolas; Mårtensson, Johan et al.
In: Acta Anaesthesiologica Scandinavica, Vol. 66, No. 1, 01.2022, p. 65-75.

Research output: Contribution to journal › Article › Academic › peer-review

TY - JOUR

T1 - Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care

T2 - Development and validation of a prognostic tool for in-hospital mortality

AU - Plečko, Drago

AU - Bennett, Nicolas

AU - Mårtensson, Johan

AU - Dam, Tariq A

AU - Entjes, Robert

AU - Rettig, Thijs C D

AU - Dongelmans, Dave A

AU - Boelens, Age D

AU - Rigter, Sander

AU - Hendriks, Stefaan H A

AU - de Jong, Remko

AU - Kamps, Marlijn J A

AU - Peters, Marco

AU - Karakus, Attila

AU - Gommers, Diederik

AU - Ramnarain, Dharmanand

AU - Wils, Evert-Jan

AU - Achterberg, Sefanja

AU - Nowitzky, Ralph

AU - van den Tempel, Walter

AU - de Jager, Cornelis P C

AU - Nooteboom, Fleur G C A

AU - Oostdijk, Evelien

AU - Koetsier, Peter

AU - Cornet, Alexander D

AU - Reidinga, Auke C

AU - de Ruijter, Wouter

AU - Bosman, Rob J

AU - Frenzel, Tim

AU - Urlings-Strop, Louise C

AU - de Jong, Paul

AU - Smit, Ellen G M

AU - Cremer, Olaf L

AU - Mehagnoul-Schipper, D Jannet

AU - Faber, Harald J

AU - Lens, Judith

AU - Brunnekreef, Gert B

AU - Festen-Spanjer, Barbara

AU - Dormans, Tom

AU - de Bruin, Daan P

AU - Lalisang, Robbert C A

AU - Vonk, Sebastiaan J J

AU - Haan, Martin E

AU - Fleuren, Lucas M

AU - Thoral, Patrick J

AU - Elbers, Paul W G

AU - Bellomo, Rinaldo

N1 - Funding Information: Authors DP and NB are supported by the grant #2017-110 of the Strategic Focal Area “Personalized Health and Related Technologies (PHRT)” of the ETH Domain for the SPHN/PHRT Driver Project ‘Personalized Swiss Sepsis Study’. Other authors are funded by their respective institutions. From collaborating hospitals having shared data: Remko van den Akker, Intensive Care, Adrz, Goes, The Netherlands, [email protected]; Tom A. Rijpstra, MD, Department of Intensive Care, Amphia Ziekenhuis, Breda, The Netherlands, [email protected]; M.C. Reuland, MD, Department of Intensive Care Medicine, Amsterdam UMC, Universiteit van Amsterdam, Amsterdam, The Netherlands, [email protected]; Klaas Sierk Arnold, MD, Anesthesiology, Antonius Ziekenhuis Sneek, Sneek, The Netherlands, [email protected]; Arend Jan Meinders, MD, Department of Internal Medicine and Intensive Care, St Antonius Hospital, Nieuwegein, The Netherlands, [email protected]; Nicolas Schroten, MD, Intensive Care, Albert Schweitzerziekenhuis, Dordrecht, The Netherlands, [email protected]; Laura van Manen, MD, Department of Intensive Care, BovenIJ Ziekenhuis, Amsterdam, The Netherlands, [email protected]; Leon Montenij, MD, PhD, Department of Anesthesiology, Pain Management and Intensive Care, Catharina Ziekenhuis Eindhoven, Eindhoven, The Netherlands, [email protected]; Julia Koeter, MD, Intensive Care, Canisius Wilhelmina Ziekenhuis, Nijmegen, The Netherlands, [email protected]; J.W. Fijen, MD, PhD, Department of Intensive Care, Diakonessenhuis Hospital, Utrecht, The Netherland, [email protected]; Jasper van Bommel, MD, PhD, Department of Intensive Care, Erasmus Medical Center, Rotterdam, The Netherlands, [email protected]; Roy van den Berg, Department of Intensive Care, ETZ Tilburg, Tilburg, The Netherlands, [email protected]; Martha de Bruin, MD, Department of Intensive Care, Franciscus Gasthuis & Vlietland, Rotterdam, The Netherlands, [email protected]; Roger van Rietschote, Business Intelligence, Haaglanden MC, Den Haag, The Netherlands, [email protected]; Ellen van Geest, Department of ICMT, Haga Ziekenhuis, Den Haag, The Netherlands, [email protected]; Koen S. Simons, MD, PhD, Department of Intensive Care, Jeroen Bosch Ziekenhuis, Den Bosch, The Netherlands, [email protected]; Anisa Hana, MD, PhD, Intensive Care, Laurentius Ziekenhuis, Roermond, The Netherlands, [email protected]; Joost Labout, MD, PhD, ICU, Maasstad Ziekenhuis Rotterdam, The Netherlands, [email protected]; Michael Kuiper, Intensive Care, Medisch Centrum Leeuwarden, Leeuwarden, The Netherlands, [email protected]; Albertus Beishuizen, MD, PhD, Department of Intensive Care, Medisch Spectrum Twente, Enschede, The Netherlands, [email protected]; Bart van de Gaauw, MD, PhD, Martiniziekenhuis, Groningen, The Netherlands, [email protected]; Roos Renckens, MD, PhD, Department of Internal Medicine, Northwest Clinics, Alkmaar, the Netherlands, [email protected]; B. van den Bogaard, MD, PhD, ICU, OLVG, Amsterdam, The Netherlands, [email protected]; Prof. Peter Pickkers, Department of Intensive Care Medicine, Radboud University Medical Centre, Nijmegen, The Netherlands, [email protected]; Pim van der Heiden, MD, PhD, Intensive Care, Reinier de Graaf Gasthuis, Delft, The Netherlands, [email protected]; Dennis Geutjes, Department of Information Technology, Slingeland Ziekenhuis, Doetinchem, The Netherlands, [email protected]; Claudia (C.W.) van Gemeren, MD, Intensive Care, Spaarne Gasthuis, Haarlem en Hoofddorp, The Netherlands, [email protected]; Emma Rademaker, MD, MSc, Department of Intensive Care, UMC Utrecht, Utrecht, The Netherlands, [email protected]; Frits H.M. van Osch, PhD, Department of Clinical Epidemiology, VieCuri Medisch Centrum, Venlo, The Netherlands, [email protected]; Johan Lutisan, MD, ICU, WZA, Assen, The Netherlands, [email protected]; Jacomar J.M. van Koesveld, MD, ICU, IJsselland Ziekenhuis, Capelle aan den IJssel, The Netherlands, [email protected]; Bart P. Grady, MD, PhD, Department of Intensive Care, Ziekenhuisgroep Twente, Almelo, The Netherlands, [email protected]; and Martijn de Kruif, MD, PhD, Department of Pulmonology, Zuyderland MC, Heerlen, The Netherlands, [email protected]. From collaborating hospitals having signed the data sharing agreement: Bram Simons, MD, Intensive Care, Bravis Ziekenhuis, Bergen op Zoom en Roosendaal, The Netherlands, [email protected]; A.A. Rijkeboer, MD, ICU, Flevoziekenhuis, Almere, The Netherlands, [email protected]; Annemieke Dijkstra, MD, Department of Intensive Care Medicine, Het Van Weel-Bethesda Ziekenhuis, Dirksland, The Netherlands, [email protected]; Sesmu Arbous, MD, PhD, Intensivist, LUMC, Leiden, The Netherlands, [email protected]; Marcel Aries, MD, PhD, MUMC+, University Maastricht, Maastricht, The Netherlands, [email protected]; Menno Beukema, MD, Department of Intensive Care, Streekziekenhuis Koningin Beatrix, Winterswijk, The Netherlands, [email protected]; Daniël Pretorius, MD, Department of Intensive Care Medicine, Hospital St Jansdal, Harderwijk, The Netherlands, [email protected]; Rutger van Raalte, Department of Intensive Care, Tergooi hospital, Hilversum, The Netherlands, [email protected]; Martijn van Tellingen, MD, EDIC, Department of Intensive Care Medicine, afdeling Intensive Care, ziekenhuis Tjongerschans, Heerenveen, The Netherlands, [email protected]; Niels C. Gritters van den Oever, MD, Intensive Care, Treant Zorggroep, Emmen, The Netherlands, [email protected]. From the Laboratory for Critical Care Computational Intelligence: Armand R.J. Girbes, MD, PhD, EDIC, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Amsterdam, The Netherlands, [email protected]; Luca Roggeveen, MD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Dagmar M. Ouweneel, PhD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Ronald Driessen, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Jan Peppink, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; H.J. de Grooth, MD, PhD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; G.J. Zijlstra, MD, PhD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; A.J. van Tienhoven, MD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Evelien van der Heiden, MD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Jan Jaap Spijkstra, MD, PhD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Hans van der Spoel, MD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Angelique de Man, MD, PhD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Thomas Klausch, PhD, Department of Clinical Epidemiology, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Heder J. de Vries, MD, Department of Intensive Care Medicine, Laboratory for Critical Care Computational Intelligence, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Mark Hoogendoorn, PhD, Quantitative Data Analytics Group, Department of Computer Science, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; Fuda van Diggelen, MSc, Quantitative Data Analytics Group, Department of Computer Sciences, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; Ali el Hassouni, PhD, Quantitative Data Analytics Group, Department of Computer Sciences, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; David Romero Guzman, PhD, Quantitative Data Analytics Group, Department of Computer Sciences, Faculty of Science, VU University, Amsterdam, The Netherlands, [email protected]; Sandjai Bhulai, PhD, Analytics and Optimization Group, Department of Mathematics, Faculty of Science, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]. From Pacmed: Michele Tonutti, MRes, Pacmed, Amsterdam, The Netherlands, [email protected]; Mattia Fornasa, PhD, Pacmed, Amsterdam, The Netherlands, [email protected]; Tomas Machado, Pacmed, Amsterdam, The Netherlands, [email protected]; Adam Izdebski, Pacmed, Amsterdam, The Netherlands, [email protected]; Taco Houwert, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Hidde Hovenkamp, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Roberto Noorduijn Londono, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Davide Quintarelli, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Martijn G. Scholtemeijer, MD, Pacmed, Amsterdam, The Netherlands, [email protected]; Aletta A. de Beer, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Giovanni Cinà, PhD, Pacmed, Amsterdam, The Netherlands, [email protected]; Willem E. Herter, BSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Michael de Neree tot Babberich, Pacmed, Amsterdam, The Netherlands, [email protected]; Olivier Thijssens, MSc, Pacmed, Amsterdam, The Netherlands, [email protected]; Lot Wagemakers, Pacmed, Amsterdam, The Netherlands, [email protected]; Hilde G.A. van der Pol, Pacmed, Amsterdam, The Netherlands, [email protected]; Tom Hendriks, Pacmed, Amsterdam, The Netherlands, [email protected]; Julie Berend, Pacmed, Amsterdam, The Netherlands, [email protected]; Virginia Ceni Silva, Pacmed, Amsterdam, The Netherlands, [email protected]; Robert F.J. Kullberg, MD, Pacmed, Amsterdam, The Netherlands, [email protected]. From RCCnet: Leo Heunks, MD, PhD, Department of Intensive Care Medicine, Amsterdam Medical Data Science, Amsterdam UMC, Vrije Universiteit, Amsterdam, The Netherlands, [email protected]; Nicole Juffermans, MD, PhD, ICU, OLVG, Amsterdam, The Netherlands, [email protected]; Arjen J.C. Slooter, MD, PhD, Department of Intensive Care Medicine, UMC Utrecht, Utrecht University, Utrecht, the Netherlands, [email protected]. From other collaborating partners:Martijn Beudel, MD, PhD, Department of Neurology, Amsterdam UMC, Universiteit van Amsterdam, Amsterdam, The Netherlands, [email protected]; Nicolet F. de Keizer, PhD, Department of Clinical Informatics, Amsterdam UMC, Amsterdam, The Netherlands, [email protected]. Funding Information: Authors DP and NB are supported by the grant #2017‐110 of the Strategic Focal Area “Personalized Health and Related Technologies (PHRT)” of the ETH Domain for the SPHN/PHRT Driver Project ‘Personalized Swiss Sepsis Study’. Other authors are funded by their respective institutions. Publisher Copyright: © 2021 The Authors. Acta Anaesthesiologica Scandinavica published by John Wiley & Sons Ltd on behalf of Acta Anaesthesiologica Scandinavica Foundation.

PY - 2022/1

Y1 - 2022/1

N2 - BACKGROUND: The prediction of in-hospital mortality for ICU patients with COVID-19 is fundamental to treatment and resource allocation. The main purpose was to develop an easily implemented score for such prediction.METHODS: This was an observational, multicenter, development, and validation study on a national critical care dataset of COVID-19 patients. A systematic literature review was performed to determine variables possibly important for COVID-19 mortality prediction. Using a logistic multivariable model with a LASSO penalty, we developed the Rapid Evaluation of Coronavirus Illness Severity (RECOILS) score and compared its performance against published scores.RESULTS: Our development (validation) cohort consisted of 1480 (937) adult patients from 14 (11) Dutch ICUs admitted between March 2020 and April 2021. Median age was 65 (65) years, 31% (26%) died in hospital, 74% (72%) were males, average length of ICU stay was 7.83 (10.25) days and average length of hospital stay was 15.90 (19.92) days. Age, platelets, PaO2/FiO2 ratio, pH, blood urea nitrogen, temperature, PaCO2, Glasgow Coma Scale (GCS) score measured within +/-24 h of ICU admission were used to develop the score. The AUROC of RECOILS score was 0.75 (CI 0.71-0.78) which was higher than that of any previously reported predictive scores (0.68 [CI 0.64-0.71], 0.61 [CI 0.58-0.66], 0.67 [CI 0.63-0.70], 0.70 [CI 0.67-0.74] for ISARIC 4C Mortality Score, SOFA, SAPS-III, and age, respectively).CONCLUSIONS: Using a large dataset from multiple Dutch ICUs, we developed a predictive score for mortality of COVID-19 patients admitted to ICU, which outperformed other predictive scores reported so far.

AB - BACKGROUND: The prediction of in-hospital mortality for ICU patients with COVID-19 is fundamental to treatment and resource allocation. The main purpose was to develop an easily implemented score for such prediction.METHODS: This was an observational, multicenter, development, and validation study on a national critical care dataset of COVID-19 patients. A systematic literature review was performed to determine variables possibly important for COVID-19 mortality prediction. Using a logistic multivariable model with a LASSO penalty, we developed the Rapid Evaluation of Coronavirus Illness Severity (RECOILS) score and compared its performance against published scores.RESULTS: Our development (validation) cohort consisted of 1480 (937) adult patients from 14 (11) Dutch ICUs admitted between March 2020 and April 2021. Median age was 65 (65) years, 31% (26%) died in hospital, 74% (72%) were males, average length of ICU stay was 7.83 (10.25) days and average length of hospital stay was 15.90 (19.92) days. Age, platelets, PaO2/FiO2 ratio, pH, blood urea nitrogen, temperature, PaCO2, Glasgow Coma Scale (GCS) score measured within +/-24 h of ICU admission were used to develop the score. The AUROC of RECOILS score was 0.75 (CI 0.71-0.78) which was higher than that of any previously reported predictive scores (0.68 [CI 0.64-0.71], 0.61 [CI 0.58-0.66], 0.67 [CI 0.63-0.70], 0.70 [CI 0.67-0.74] for ISARIC 4C Mortality Score, SOFA, SAPS-III, and age, respectively).CONCLUSIONS: Using a large dataset from multiple Dutch ICUs, we developed a predictive score for mortality of COVID-19 patients admitted to ICU, which outperformed other predictive scores reported so far.

KW - corona virus

KW - COVID-19

KW - intensive care

KW - mechanical ventilation

KW - respiratory failure

UR - http://www.scopus.com/inward/record.url?scp=85116967229&partnerID=8YFLogxK

U2 - 10.1111/aas.13991

DO - 10.1111/aas.13991

M3 - Article

C2 - 34622441

SN - 0001-5172

VL - 66

SP - 65

EP - 75

JO - Acta Anaesthesiologica Scandinavica

JF - Acta Anaesthesiologica Scandinavica

IS - 1

ER -

Rapid evaluation of Coronavirus Illness Severity (RECOILS) in intensive care: Development and validation of a prognostic tool for in-hospital mortality

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this