Research Article

SARS-CoV-2 Prediction Strategy Based on Classification Algorithms from a Full Blood Examination

Table 5

The 14 variables (14 different blood counts) in the construction of the predictive model (regular ward data), ranked according to the best dependency test scores (ANOVA test) with the target (SARS-CoV-2).

Feature nameScore

Eosinophils19.097924
Red blood cells10.508018
Hemoglobin9.878300
Leukocytes9.760907
Hematocrit9.638821
Mean platelet volume5.262199
Platelets4.385559
Red blood cell distribution width (RDW)3.503271
Basophils3.459295
Lymphocytes2.726842
Mean corpuscular volume (MCV)1.767816
Mean corpuscular hemoglobin (MCH)1.447305
Monocytes0.137198
Mean corpuscular hemoglobin concentration (MCHC)0.008929