Research
Print page Print page
Switch language
Rigshospitalet - a part of Copenhagen University Hospital
Published

Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Infants with congenital heart defects have reduced brain volumes

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. De novo electrocardiographic abnormalities in persons living with HIV

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Effect of liraglutide on expression of inflammatory genes in type 2 diabetes

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Extrarenal expression of α-klotho, the kidney related longevity gene, in Heterocephalus glaber, the long living Naked Mole Rat

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Postoperative complications: an observational study of trends in the United States from 2012 to 2018

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Handling oxygenation targets in ICU patients with COVID-19-Protocol and statistical analysis plan in the HOT-COVID trial

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Low-dose hydrocortisone in patients with COVID-19 and severe hypoxia: the COVID STEROID randomised, placebo-controlled trial

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Use of crystalloids and colloids in Europe per year from 2010 to 2019: Protocol for an international descriptive study

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.

Original languageEnglish
Article number18959
JournalScientific Reports
Volume11
Issue number1
Pages (from-to)18959
ISSN2045-2322
DOIs
Publication statusPublished - 23 Sep 2021

Bibliographical note

© 2021. The Author(s).

ID: 67997895