Skip to main content

Table 2 The performance of different ML models and single omics dataset for COVID-19 severity classification

From: Machine learning to analyse omic-data for COVID-19 diagnosis and prognosis

Model

DNA methylation

Proteomic

Metabolomic

 

AUC

Accuracy

F1-score

AUC

Accuracy

F1-score

AUC

Accuracy

F1-score

SVM

0.54

0.56

0.40

0.52

0.54

0.41

0.50

0.55

0.30

RF

0.68

0.72

0.59

0.68

0.72

0.69

0.67

0.72

0.59

LR

0.70

0.76

0.64

0.60

0.56

0.64

0.58

0.53

0.54

KNN

0.60

0.59

0.51

0.52

0.59

0.48

0.60

0.49

0.51

RUS

0.48

0.53

0.42

0.52

0.59

0.48

0.39

0.35

0.32

MLP

0.69

0.73

0.74

0.66

0.67

0.74

0.68

0.70

0.72

  1. Bold indicates best performing model