Effect of ferritin, INR, and D-dimer immunological parameters levels as predictors of COVID-19 mortality: A strong prediction with the decision trees

HUYUT M. T., Huyut Z.

Heliyon, vol.9, no.3, 2023 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 9 Issue: 3
  • Publication Date: 2023
  • Doi Number: 10.1016/j.heliyon.2023.e14015
  • Journal Name: Heliyon
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, CAB Abstracts, Food Science & Technology Abstracts, Veterinary Science Database, Directory of Open Access Journals
  • Keywords: COVID-19, Mortality risk biomarkers, Coagulation tests, Immunological tests, Ferritin, CHAID decision Trees, Machine learning, Artificial intelligence
  • Van Yüzüncü Yıl University Affiliated: Yes

Abstract

Background and objective: A hyperinflammatory environment is thought to be the distinctive characteristic of COVID-19 infection and an important mediator of morbidity. This study aimed to determine the effect of other immunological parameter levels, especially ferritin, as a predictor of COVID-19 mortality via decision-trees analysis. Material and method: This is a retrospective study evaluating a total of 2568 patients who died (n = 232) and recovered (n = 2336) from COVID-19 in August and December 2021. Immunological laboratory data were compared between two groups that died and recovered from patients with COVID-19. In addition, decision trees from machine learning models were used to evaluate the performance of immunological parameters in the mortality of the COVID-19 disease. Results: Non-surviving from COVID-19 had 1.75 times higher ferritin, 10.7 times higher CRP, 2.4 times higher D-dimer, 1.14 times higher international-normalized-ratio (INR), 1.1 times higher Fibrinogen, 22.9 times higher procalcitonin, 3.35 times higher troponin, 2.77 mm/h times higher erythrocyte-sedimentation-rate (ESR), 1.13sec times longer prothrombin time (PT) when compared surviving patients. In addition, our interpretable decision tree, which was constructed with only the cut-off values of ferritin, INR, and D-dimer, correctly predicted 99.7% of surviving patients and 92.7% of non-surviving patients. Conclusions: This study perfectly predicted the mortality of COVID-19 with our interpretable decision tree constructed with INR and D-dimer, especially ferritin. For this reason, we think that it may be important to include ferritin, INR, and D-dimer parameters and their cut-off values in the scoring systems to be planned for COVID-19 mortality.