Table 1. Open in new tab Model...

Table 1.

Open in new tab

Model Performance Using the Selected MPAs Variables to Discriminate EOS vs HC, AOS vs HC, and EOS vs AOS

Training set

Validation set

EOS vs HC

Models

AUC

Accuracy

Sensitivity

Specificity

AUC

Accuracy

Sensitivity

Specificity

Logistic regression

0.88

0.80

0.77

0.85

0.79

0.71

0.83

Elastic net

0.88

0.78

0.80

0.77

0.85

0.78

0.75

0.76

Random forest

0.91

0.80

0.83

0.79

0.90

0.82

0.84

0.81

SVM

0.93

0.84

0.85

0.83

0.91

0.88

0.86

0.85

XGBoost

0.94

0.85

0.86

0.84

0.93

0.86

0.87

0.85

AOS vs HC

Logistic regression

0.82

0.75

0.77

0.73

0.83

0.77

0.70

0.83

Elastic net

0.80

0.72

0.73

0.71

0.80

0.74

0.75

0.73

Random forest

0.86

0.76

0.78

0.75

0.85

0.79

0.80

0.78

SVM

0.86

0.75

0.76

0.73

0.85

0.78

0.80

0.77

XGBoost

0.87

0.77

0.79

0.76

0.87

0.78

0.80

0.77

EOS vs AOS

Logistic regression

0.69

0.64

0.66

0.62

0.67

0.61

0.62

0.60

Elastic net

0.69

0.64

0.66

0.62

0.67

0.61

0.62

0.60

Random forest

0.73

0.66

0.73

0.66

0.69

0.64

SVM

0.75

0.68

0.71

0.66

0.74

0.69

0.71

0.68

XGBoost

0.77

0.70

0.72

0.70

0.75

0.68

0.73

0.65

Abbreviations: AOS, adult-onset schizophrenia; EOS, early-onset schizophrenia; HC, healthy controls; SVM, support vector machine; SZ, schizophrenia; XGBoost, eXtreme gradient boosting.

This Feature Is Available To Subscribers Only