Skip to main content

Table 4 The validation of models on AL diagnosis for Out-Sample Test

From: Mathematical models of amino acid panel for assisting diagnosis of children acute leukemia

 

Diagnosis (model/clinical diagnosis)

χ2

Kappa value

p value

AUCi

+/+ a

b

±c

−/−d

Result-SVMh

237

43

46

262

0.1011

0.697

0.751

0.788

Sensitivitye (%)

84.64

    

Specificityf (%)

85.06

    

Accuracyg (%)

84.86

    

Result-RFh

231

49

38

270

1.3908

0.703

0.238

0.803

Sensitivitye (%)

82.50

    

Specificityf (%)

87.66

    

Accuracyg (%)

85.20

    

Result-XGBh

252

28

34

274

0.2903

0.789

0.446

0.830

Sensitivitye (%)

90.00

    

Specificityf (%)

88.96

    

Accuracyg (%)

89.46

    
  1. SVM: support vector machine; RF: random forest; XGB: XGBoot; FN: false negative; FP: false positive; AUC: area under curve
  2. aOur model or clinical diagnosis were both positive-children were with leukemia
  3. bOur model diagnosed children as normal, but the clinical diagnosis of them was leukemia
  4. cOur model diagnosed children as leukemia, but the clinical diagnosis of them was normal
  5. dOur model or clinical diagnosis were both negative, and children were normal
  6. eNumber of +/+ for each model/(number of +/+ for each model plus number of for each model) × 100%
  7. fNumber of −/− for each model/(number of −/− for each model plus number of ± for each model) × 100%
  8. g(Number of −/− for each model plus number of +/+ for each model)/588 × 100%
  9. hMcNemar’s test
  10. iROC analysis