Prediction of intensive care admission and hospital mortality in COVID-19 patients using demographics and baseline laboratory data

Imagem de Miniatura
Citações na Scopus
Tipo de produção
Data de publicação
Título da Revista
ISSN da Revista
Título do Volume
CLINICS, v.78, article ID 100183, 8p, 2023
Projetos de Pesquisa
Unidades Organizacionais
Introduction: Optimized allocation of medical resources to patients with COVID-19 has been a critical concern since the onset of the pandemic.Methods: In this retrospective cohort study, the authors used data from a Brazilian tertiary university hospital to explore predictors of Intensive Care Unit (ICU) admission and hospital mortality in patients admitted for COVID19. Our primary aim was to create and validate prediction scores for use in hospitals and emergency departments to aid clinical decisions and resource allocation. Results: The study cohort included 3,022 participants, of whom 2,485 were admitted to the ICU; 1968 survived, and 1054 died in the hospital. From the complete cohort, 1,496 patients were randomly assigned to the derivation sample and 1,526 to the validation sample. The final scores included age, comorbidities, and baseline laboratory data. The areas under the receiver operating characteristic curves were very similar for the derivation and validation samples. Scores for ICU admission had a 75% accuracy in the validation sample, whereas scores for death had a 77% accuracy in the validation sample. The authors found that including baseline flu-like symptoms in the scores added no significant benefit to their accuracy. Furthermore, our scores were more accurate than the previously published NEWS-2 and 4C Mortality Scores.Discussion and conclusions: The authors developed and validated prognostic scores that use readily available clinical and laboratory information to predict ICU admission and mortality in COVID-19. These scores can become valuable tools to support clinical decisions and improve the allocation of limited health resources.
COVID-19, SARS-CoV-2, Critical Care, Mortality, Intensive Care, Risk Score, Prediction
  1. Alencar J, 2022, FRONT MED-LAUSANNE, V9, DOI 10.3389/fmed.2022.779516
  2. Alhalaseh YN, 2021, FRONT MED-LAUSANNE, V7, DOI 10.3389/fmed.2020.616277
  3. Bolourani S, 2021, J MED INTERNET RES, V23, DOI 10.2196/24246
  4. Bradley P, 2020, BMJ OPEN RESPIR RES, V7, DOI 10.1136/bmjresp-2020-000729
  5. Clift AK, 2020, BMJ-BRIT MED J, V371, DOI 10.1136/bmj.m3731
  6. covid19.who, WHO CORONAVIRUS COVI
  7. Daniels JP, 2021, EVERYTHING IS COLLAP
  8. Das AK, 2020, PEERJ, V8, DOI 10.7717/peerj.10083
  9. Emanuel EJ, 2020, NEW ENGL J MED, V382, P2049, DOI 10.1056/NEJMsb2005114
  10. Ferreira JC, 2021, ANN INTENSIVE CARE, V11, DOI 10.1186/s13613-021-00882-w
  11. Goodacre S, 2021, PLOS ONE, V16, DOI 10.1371/journal.pone.0245840
  12. Harris PA, 2009, J BIOMED INFORM, V42, P377, DOI 10.1016/j.jbi.2008.08.010
  13. Islam N, 2021, BMJ-BRIT MED J, V375, DOI 10.1136/bmj-2021-066768
  14. Knight SR, 2020, BMJ-BRIT MED J, V370, DOI 10.1136/bmj.m3339
  15. Kuhn A., 2020, S KOREAN CITY IS CHA
  16. Kurtz P, 2021, INTENS CARE MED, V47, P538, DOI 10.1007/s00134-021-06388-0
  17. Liao XL, 2020, INTENS CARE MED, V46, P357, DOI 10.1007/s00134-020-05954-2
  18. Liu H, 2021, MED N Y, V2, P4
  19. Livingston E, 2020, JAMA-J AM MED ASSOC, V323, P1912, DOI 10.1001/jama.2020.5317
  20. Lopez-Escobar A, 2021, DIAGNOSTICS, V11, DOI 10.3390/diagnostics11040596
  21. McMahon DE, 2020, PLOS NEGLECT TROP D, V14, DOI 10.1371/journal.pntd.0008412
  22. Miller JL, 2022, ACAD EMERG MED, V29, P206, DOI 10.1111/acem.14447
  23. Mounk Y., 2020, ATLANTIC
  24. Neto FL, 2021, CLIN MICROBIOL INFEC, V27, DOI 10.1016/j.cmi.2021.03.002
  26. Phillips T, 2021, COMPLETE MASSACRE HO
  27. Ranney ML, 2020, NEW ENGL J MED, V382, DOI 10.1056/NEJMp2006141
  28. Ranzani OT, 2021, LANCET RESP MED, V9, P407, DOI 10.1016/S2213-2600(20)30560-9
  29. Schumaker E, 2021, COMPLETE COLLAPSE PR
  30. Wollenstein-Betech Salomon, 2020, Int J Med Inform, V142, P104258, DOI [10.1016/j.ijmedinf.2020.104258, 10.1101/2020.05.03.20089813]