Skip to main content

Table 1 Performance summary of relevant works in the literature. When available, results from external cohort validation are reported. Three metrics are shown: ROC-AUC, sensitivity (True Positive Rate or TPR), and specificity (True Negative Rate or TNR)

From: Identification of relevant features using SEQENS to improve supervised machine learning models predicting AML treatment outcome

Study

Prediction objective

Method

ROC-AUC

TPR

TNR

[7]

AML survival rate

RelieF + GBT

0.93

0.72

0.91

[9]

CML 5-year survival

mRMR + SVM

0.85

0.86

0.85

[13]

AML inpatient mortality

Random Forest

0.78

0.09

0.99

[14]

AML complete remission

SVM

0.80

0.77

0.51

[14]

AML 2-year survival

SVM

0.75

0.67

0.74

[15]

Red-blood-cells in AML

LassoLR

0.88

[15]

Platelets in AML

SVM

0.70

[16]

ALL mortality in children

ANN

0.74

0.80

0.68

[16]

ALL relapse in children

Boosting

0.84

0.97

0.71

[17]

90-day AML complications

XGBoost

0.7

0.57

0.79