Informativeness estimation for the main clinical and laboratory parameters in patients with severe COVID-19

Cover Page

Cite item

Full Text

Abstract

Aim. To conduct a retrospective assessment of the clinical and laboratory data of patients with severe forms of COVID-19 hospitalized in the intensive care and intensive care unit, in order to assess the contribution of various indicators to the likelihood of death.

Materials and methods. A retrospective assessment of data on 224 patients with severe COVID-19 admitted to the intensive care unit was carried out. The analysis included the data of biochemical, clinical blood tests, coagulograms, indicators of the inflammatory response. When transferring to the intensive care units (ICU), the indicators of the formalized SOFA and APACHE scales were recorded. Anthropometric and demographic data were downloaded separately.

Results. Analysis of obtained data, showed that only one demographic feature (age) and a fairly large number of laboratory parameters can serve as possible markers of an unfavorable prognosis. We identified 12 laboratory features the best in terms of prediction: procalcitonin, lymphocytes (absolute value), sodium (ABS), creatinine, lactate (ABS), D-dimer, oxygenation index, direct bilirubin, urea, hemoglobin, C-reactive protein, age, LDH. The combination of these features allows to provide the quality of the forecast at the level of AUC=0.85, while the known scales provided less efficiency (APACHE: AUC=0.78, SOFA: AUC=0.74).

Conclusion. Forecasting the outcome of the course of COVID-19 in patients in ICU is relevant not only from the position of adequate distribution of treatment measures, but also from the point of view of understanding the pathogenetic mechanisms of the development of the disease.

About the authors

Oksana V. Stanevich

Pavlov First Saint Petersburg State Medical University

Email: oksana.stanevich@gmail.com
ORCID iD: 0000-0002-6894-6121

врач-инфекционист отд. эпидемиологии

Russian Federation, Saint Petersburg

Evgeny A. Bakin

Pavlov First Saint Petersburg State Medical University

Email: eugene.bakin@gmail.com
ORCID iD: 0000-0002-5694-4348

PhD, RM Gorbacheva Research Institute senior researcher

Russian Federation, Saint Petersburg

Aleksandra A. Korshunova

Pavlov First Saint Petersburg State Medical University

Author for correspondence.
Email: aftotrof@gmail.com
ORCID iD: 0000-0002-7419-7227

MD, Emergency Deprtment physician

Russian Federation, Saint Petersburg

Alexandra Ya. Gudkova

Pavlov First Saint Petersburg State Medical University

Email: alexagood-1954@mail.ru
ORCID iD: 0000-0003-0156-8821

д-р мед. наук, проф. каф. факультетской терапии, зав. лаб. кардиомиопатий Научно-исследовательского института сердечно-сосудистых заболеваний НКИЦ

Russian Federation, Saint Petersburg

Aleksey A. Afanasev

Pavlov First Saint Petersburg State Medical University

Email: alex-txf@mail.ru
ORCID iD: 0000-0003-0277-3456
SPIN-code: 4389-6271

MD, Cand. Sci. (Med.), Assistant Lecturer

Russian Federation, Saint Petersburg

Irina V. Shlyk

Pavlov First Saint Petersburg State Medical University

Email: irina_shlyk@mail.ru
ORCID iD: 0000-0003-0977-8081
SPIN-code: 1715-1770

MD, Dr. Sci. (Med.), Professor

Russian Federation, Saint Petersburg

Dmitry A. Lioznov

Pavlov First Saint Petersburg State Medical University

Email: dlioznov@yandex.ru
ORCID iD: 0000-0003-3643-7354

д-р мед. наук, зав. каф. инфекционных болезней и эпидемиологии

Russian Federation, Saint Petersburg

Yury S. Polushin

Pavlov First Saint Petersburg State Medical University

Email: polushinyus@1spbgmu.ru
ORCID iD: 0000-0002-6313-5856
SPIN-code: 2006-1194

MD, Dr. Sci. (Med.), Professor, Academician of the RAS

Russian Federation, Saint Petersburg

Alexandr N. Kulikov

Pavlov First Saint Petersburg State Medical University

Email: ankulikov2005@yandex.ru
ORCID iD: 0000-0002-4544-2967
SPIN-code: 3851-6072

MD, Dr. Sci. (Med.), Professor

Russian Federation, Saint Petersburg

References

  1. Xu J, Yang X, Yang L, et al. Clinical course and predictors of 60-day mortality in 239 critically ill patients with COVID-19: a multicenter retrospective study from Wuhan, China. Crit Care. 2020;24(1):394. doi: 10.1186/s13054-020-03098-9
  2. Izquierdo JL, Ancochea J, Savana COVID-19 Research Group, Soriano JB. Clinical Characteristics and Prognostic Factors for Intensive Care Unit Admission of Patients With COVID-19: Retrospective Study Using Machine Learning and Natural Language Processing. J Med Internet Res. 2020;22(10):e21801. doi: 10.2196/21801
  3. Abate SM, Ahmed Ali S, Mantfardo B, Basu B. Rate of Intensive Care Unit admission and outcomes among patients with coronavirus: A systematic review and Meta-analysis. PLOS One. 2020;15(7):e0235653. doi: 10.1371/journal.pone.0235653
  4. Wendel Garcia PD, Fumeaux T, Guerci P, et al; RISC-19-ICU Investigators. Prognostic factors associated with mortality risk and disease progression in 639 critically ill patients with COVID-19 in Europe: Initial report of the international RISC-19-ICU prospective observational cohort. EClinicalMedicine. 2020;25:100449. doi: 10.1016/j.eclinm.2020.100449
  5. Core Team R. A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing, 2019. Available at: https://www.R-project.org/ Accessed: 22.06.2021.
  6. Mendenhall WM, Sincich T. Statistics for engineering and the sciences, Sixth edition. Boca Raton: CRC Press, Taylor & Francis Group, 2016.
  7. Fay MP, Proschan MA. Wilcoxon-Mann-Whitney or t-test? On assumptions for hypothesis tests and multiple interpretations of decision rules. Stat Surv. 2010;4:1-39. doi: 10.1214/09-SS051
  8. Farrar DE, Glauber RR. Multicollinearity in Regression Analysis: The Problem Revisited. Rev Econ Stat. 1967;49(1):92. doi: 10.2307/1937887
  9. Yul Lee K, Weissfeld LA. A multicollinearity diagnostic for the cox model with time dependent covariates. Commun Stat – Simul Comput. 1996;25(1)41-60. doi: 10.1080/03610919608813297
  10. Maalouf M. Logistic regression in data analysis: an overview. Int J Data Anal Tech Strateg. 2011;3(3):281. doi: 10.1504/IJDATS.2011.041335
  11. Breiman L. Random Forests. Mach Learn. 2001;45(1):5-32. doi: 10.1023/A:1010933404324
  12. Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning: data mining, inference, and prediction, 2nd ed. New York, NY: Springer, 2009.
  13. Stone M. Cross-Validatory Choice and Assessment of Statistical Predictions. J R Stat Soc Ser B Methodol. 1974;36(2):111-33. doi: 10.1111/j.2517-6161.1974.tb00994.x
  14. Kuhn M. Caret: Classification and Regression Training. 2020. Available at: https://CRAN.R-project.org/package=caret. Accessed: 22.06.2021.
  15. Wickham H. Ggplot2: elegant graphics for data analysis, Second edition. Cham: Springer, 2016.
  16. Kassambara A, Kosinski M, Biecek P. Survminer: Drawing Survival Curves using „ggplot2“. 2019. Available at: https://CRAN.R-project.org/package=survminer. Accessed: 22.06.2021.
  17. Raivo Kolde. Pheatmap: Pretty Heatmaps. 2019. Available at: https://CRAN.R-project.org/package=pheatmap. Accessed: 22.06.2021.
  18. Gupta S, Hayek SS, Wang W, et al. Factors Associated With Death in Critically Ill Patients With Coronavirus Disease 2019 in the US. JAMA Intern Med. 2020;180(11):1436. doi: 10.1001/jamainternmed.2020.3596
  19. Guillamet MCV, Guillamet RV, Kramer AA, et al. Toward a COVID-19 score-risk assessments and registry. Int Care Crit Care Med. 2020. doi: 10.1101/2020.04.15.20066860
  20. Wynants L, Van Calster B, Collins GS, et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ. 2020:m1328. doi: 10.1136/bmj.m1328
  21. Zhang H, Shi T, Wu X, et al. Risk prediction for poor outcome and death in hospital in-patients with COVID-19: derivation in Wuhan, China and external validation in London, UK. Public and Global Health. 2020. doi: 10.1101/2020.04.28.20082222
  22. Levy TJ, Richardson S, Coppa K, et al. A predictive model to estimate survival of hospitalized COVID-19 patients from admission data. Health Informatics. 2020. doi: 10.1101/2020.04.22.20075416
  23. Han Y, Zhang H, Mu S, et al. Lactate dehydrogenase, an independent risk factor of severe COVID-19 patients: a retrospective and observational study. Aging. 2020;12(12):11245-58. doi: 10.18632/aging.103372
  24. Chen Z, Hu J, Liu L, et al. Clinical Characteristics of Patients with Severe and Critical COVID-19 in Wuhan: A Single-Center, Retrospective Study. Infect Dis Ther. 2021;10(1):421-38. doi: 10.1007/s40121-020-00379-2
  25. Hu C, Liu Z, Jiang Y, et al. Early prediction of mortality risk among patients with severe COVID-19, using machine learning. Int J Epidemiol. 2021;49(6):1918-29. doi: 10.1093/ije/dyaa171
  26. Rod JE, Oviedo-Trespalacios O, Cortes-Ramirez J. A brief-review of the risk factors for covid-19 severity. Rev Saúde Pública. 2020;54:60. doi: 10.11606/s1518-8787.2020054002481
  27. Tan L, Wang Q, Zhang D, et al. Lymphopenia predicts disease severity of COVID-19: a descriptive and predictive study. Signal Transduct Target Ther. 2020;5(1):33. doi: 10.1038/s41392-020-0148-4
  28. Carfora V, Spiniello G, Ricciolino R, et al. Anticoagulant treatment in COVID-19: a narrative review. J Thromb Thrombolysis. 2021;51(3):642-8. doi: 10.1007/s11239-020-02242-0
  29. Pourhomayoun M, Shakibi M. Predicting mortality risk in patients with COVID-19 using machine learning to help medical decision-making. Smart Health. 2021;20:100178. doi: 10.1016/j.smhl.2020.100178
  30. Singh K, Valley TS, Tang S, et al. Evaluating a Widely Implemented Proprietary Deterioration Index Model among Hospitalized COVID-19 Patients. Ann Am Thorac Soc. 2021;18(7):1129-37. doi: 10.1513/AnnalsATS.202006-698OC
  31. Hu H, Yao N, Qiu Y. Comparing Rapid Scoring Systems in Mortality Prediction of Critically Ill Patients With Novel Coronavirus Disease. Acad Emerg Med. 2020;27(6):461-8. doi: 10.1111/acem.13992
  32. Williamson EJ, Walker AJ, Bhaskaran K, et al. Factors associated with COVID-19-related death using OpenSAFELY. Nature. 2020;584(7821):430-6. doi: 10.1038/s41586-020-2521-4

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Research scheme.

Download (120KB)
Indexing metadata
3. Fig. 2. Graphs of cumulative incidence for events "improvement" ("discharge") and "death" in the population of patients admitted to the department of intensive care and intensive care (n=211).

Download (97KB)
Indexing metadata
4. Fig. 3. Correlation matrix for the features with statistically significant difference between groups.

Download (198KB)
Indexing metadata
5. Fig. 4. Analysis of clinical and laboratory features: a – ROC analysis for the complete set of features; b – the list of features ranked by importance; c – ROC analysis for the 12 most important features; c – comparisons with the SOFA and APACHE scores.

Download (424KB)
Indexing metadata

Copyright (c) 2022 Consilium Medicum

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
 
 


This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies