Predicting mortality of individual COVID-19 patients: A multicenter Dutch cohort

  1. Maarten C. Ottenhoff
  2. Lucas L. Ramos
  3. Wouter Potters
  4. Marcus L.F. Janssen
  5. Deborah Hubers
  6. Dan Piña-Fuentes
  7. Rajat Thomas
  8. Iwan C.C. van der Horst
  9. Christian Herff
  10. Pieter Kubben
  11. Paul W.G. Elbers
  12. Henk A. Marquering
  13. Max Welling
  14. Shi Hu
  15. Suat Simsek
  16. Martijn D. de Kruif
  17. Tom Dormans
  18. Lucas M. Fleuren
  19. Michiel Schinkel
  20. Peter G. Noordzij
  21. Joop P. van den Bergh
  22. Caroline E. Wyers
  23. David T. B. Buis
  24. Joost Wiersinga
  25. Ella H.C. van den Hout
  26. Auke C. Reidinga
  27. Daisy Rusch
  28. Kim C.E. Sigaloff
  29. Renée Douma
  30. Lianne de Haan
  31. Egill A. Fridgeirsson
  32. Niels C. Gritters van den Oever
  33. Roger J.M.W. Rennenberg
  34. Guido A. van Wingen
  35. Marcel J.H. Aries
  36. Martijn Beudel
1 evaluations Published on
Read the full article Related papers
This article on Sciety

Abstract

Objective

Develop and validate models that predict mortality of SARS-CoV-2 infected patients admitted to the hospital.

Design

Retrospective cohort study

Setting

A multicenter cohort across ten Dutch hospitals including patients from February 27 to June 8 2020.

Participants

SARS-CoV-2 positive patients (age ≥ 18) admitted to the hospital.

Main Outcome Measures

21-day mortality evaluated by the area under the receiver operatory curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The predictive value of age was explored by comparison with age-based rules used in practice and by excluding age from analysis.

Results

2273 patients were included, of whom 516 had died or discharged to palliative care within 21 days after admission. Five feature sets, including premorbid, clinical presentation and laboratory & radiology values, were derived from 80 features. Additionally, an ANOVA-based data-driven feature selection selected the ten features with the highest F-values: age, number of home medications, urea nitrogen, lactate dehydrogenase, albumin, oxygen saturation (%), oxygen saturation is measured on room air, oxygen saturation is measured on oxygen therapy, blood gas pH and history of chronic cardiac disease. A linear logistic regression (LR) and non-linear tree-based gradient boosting (XGB) algorithm fitted the data with an AUC of 0.81 (95% confidence interval 0.77 to 0.85) and 0.82 (0.79 to 0.85), respectively, using the ten selected features. Both models outperformed age-based decision rules used in practice (AUC of 0.69, 0.65 to 0.74 for age > 70). Furthermore, performance remained stable when excluding age as predictor (AUC of 0.78, 0.75 to 0.81)

Conclusion

Both models showed excellent performance and had better test characteristics than age-based decision rules, using ten admission features readily available in Dutch hospitals. The models hold promise to aid decision making during a hospital bed shortage.

Related articles

Related articles are currently not available for this article.