Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jun 28;9(1):32.
doi: 10.1186/s40635-021-00397-5.

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

Lucas M Fleuren #  1 , Michele Tonutti #  2 , Daan P de Bruin  2 , Robbert C A Lalisang  2 , Tariq A Dam  3 , Diederik Gommers  4 , Olaf L Cremer  5 , Rob J Bosman  6 , Sebastiaan J J Vonk  2 , Mattia Fornasa  2 , Tomas Machado  2 , Nardo J M van der Meer  7 , Sander Rigter  8 , Evert-Jan Wils  9 , Tim Frenzel  10 , Dave A Dongelmans  3 , Remko de Jong  11 , Marco Peters  12 , Marlijn J A Kamps  13 , Dharmanand Ramnarain  14 , Ralph Nowitzky  15 , Fleur G C A Nooteboom  16 , Wouter de Ruijter  17 , Louise C Urlings-Strop  18 , Ellen G M Smit  19 , D Jannet Mehagnoul-Schipper  20 , Tom Dormans  21 , Cornelis P C de Jager  22 , Stefaan H A Hendriks  23 , Evelien Oostdijk  24 , Auke C Reidinga  25 , Barbara Festen-Spanjer  26 , Gert Brunnekreef  27 , Alexander D Cornet  28 , Walter van den Tempel  29 , Age D Boelens  30 , Peter Koetsier  31 , Judith Lens  32 , Sefanja Achterberg  33 , Harald J Faber  34 , A Karakus  35 , Menno Beukema  36 , Robert Entjes  37 , Paul de Jong  38 , Taco Houwert  2 , Hidde Hovenkamp  2 , Roberto Noorduijn Londono  2 , Davide Quintarelli  2 , Martijn G Scholtemeijer  2 , Aletta A de Beer  2 , Giovanni Cinà  2 , Martijn Beudel  39 , Nicolet F de Keizer  40 , Mark Hoogendoorn  41 , Armand R J Girbes  3 , Willem E Herter  2 , Paul W G Elbers  3 , Patrick J Thoral  3 ; Dutch ICU Data Sharing Against COVID-19 Collaborators
Collaborators, Affiliations

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

Lucas M Fleuren et al. Intensive Care Med Exp. .

Abstract

Background: The identification of risk factors for adverse outcomes and prolonged intensive care unit (ICU) stay in COVID-19 patients is essential for prognostication, determining treatment intensity, and resource allocation. Previous studies have determined risk factors on admission only, and included a limited number of predictors. Therefore, using data from the highly granular and multicenter Dutch Data Warehouse, we developed machine learning models to identify risk factors for ICU mortality, ventilator-free days and ICU-free days during the course of invasive mechanical ventilation (IMV) in COVID-19 patients.

Methods: The DDW is a growing electronic health record database of critically ill COVID-19 patients in the Netherlands. All adult ICU patients on IMV were eligible for inclusion. Transfers, patients admitted for less than 24 h, and patients still admitted at time of data extraction were excluded. Predictors were selected based on the literature, and included medication dosage and fluid balance. Multiple algorithms were trained and validated on up to three sets of observations per patient on day 1, 7, and 14 using fivefold nested cross-validation, keeping observations from an individual patient in the same split.

Results: A total of 1152 patients were included in the model. XGBoost models performed best for all outcomes and were used to calculate predictor importance. Using Shapley additive explanations (SHAP), age was the most important demographic risk factor for the outcomes upon start of IMV and throughout its course. The relative probability of death across age values is visualized in Partial Dependence Plots (PDPs), with an increase starting at 54 years. Besides age, acidaemia, low P/F-ratios and high driving pressures demonstrated a higher probability of death. The PDP for driving pressure showed a relative probability increase starting at 12 cmH2O.

Conclusion: Age is the most important demographic risk factor of ICU mortality, ICU-free days and ventilator-free days throughout the course of invasive mechanical ventilation in critically ill COVID-19 patients. pH, P/F ratio, and driving pressure should be monitored closely over the course of mechanical ventilation as risk factors predictive of these outcomes.

Keywords: COVID-19; Machine learning; Mortality prediction; Risk factors.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Importance of the top 10 predictors for the prediction of ICU mortality and ICU free days, as well as the difference for predictors over time. A ICU mortality. B ICU-free days
Fig. 2
Fig. 2
Partial dependence plots. PDP for age, pH, and driving pressure. The median value of all observations is indicated with a red vertical line
Fig. 3
Fig. 3
Course of pH and driving pressure. Plots show the course of pH and driving pressure only for patients intubated at least 7 (left) or 14 (right) days, respectively
See this image and copyright information in PMC

References

    1. Dong E, Du H, Gardner L. An interactive web-based dashboard to track COVID-19 in real time. Lancet Infect Dis. 2020;20:533–534. doi: 10.1016/S1473-3099(20)30120-1. - DOI - PMC - PubMed
    1. Quah P, Li A, Phua J. Mortality rates of patients with COVID-19 in the intensive care unit: a systematic review of the emerging literature. Crit Care. 2020;24:285. doi: 10.1186/s13054-020-03006-1. - DOI - PMC - PubMed
    1. Grasselli G, Greco M, Zanella A, et al. Risk factors associated with mortality among patients with COVID-19 in intensive care units in Lombardy, Italy. JAMA Intern Med. 2020 doi: 10.1001/jamainternmed.2020.3539. - DOI - PMC - PubMed
    1. Richardson S, Hirsch JS, Narasimhan M, et al. Presenting characteristics, comorbidities, and outcomes among 5700 patients hospitalized with COVID-19 in the New York City area. JAMA. 2020;323:2052–2059. doi: 10.1001/jama.2020.6775. - DOI - PMC - PubMed
    1. Karagiannidis C, Mostert C, Hentschker C, et al. Case characteristics, resource use, and outcomes of 10 021 patients with COVID-19 admitted to 920 German hospitals: an observational study. Lancet Respir Med. 2020;8:853–862. doi: 10.1016/S2213-2600(20)30316-7. - DOI - PMC - PubMed

LinkOut - more resources