Skip to main content

Table 11 Mean ROC-AUC with 95% confidence interval (5-Fold cross-validation) at different times after diagnosis using three distinct classifiers: XGBoost (XGB), multilayer perceptron (MLP), decision trees (DT), and logistic regression (LR)

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

Time

Variables

Model

ROC-AUC (95% CI)

90-day

Selected

XGB

0.82 (0.78 \( - \) 0.85)

MLP

0.80 (0.76 \( - \) 0.85)

DT

0.77 (0.70 \( - \) 0.84)

LR

0.78 (0.72 \( - \) 0.85)

All

XGB

0.80 (0.77 \( - \) 0.84)

MLP

0.75 (0.69 \( - \) 0.81)

DT

0.69 (0.65 \( - \) 0.74)

LR

0.74 (0.65 \( - \) 0.82)

6-month

Selected

XGB

0.84 (0.79 \( - \) 0.89)

MLP

0.81 (0.73 \( - \) 0.88)

DT

0.78 (0.72 \( - \) 0.84)

LR

0.82 (0.75 \( - \) 0.89)

All

XGB

0.84 (0.75 \( - \) 0.92)

MLP

0.79 (0.75 \( - \) 0.83)

DT

0.74 (0.69 \( - \) 0.79)

LR

0.79 (0.69 \( - \) 0.89)

1-year

Selected

XGB

0.82 (0.76 \( - \) 0.87)

MLP

0.82 (0.75 \( - \) 0.89)

DT

0.81 (0.77 \( - \) 0.85)

LR

0.83 (0.79 \( - \) 0.87)

All

XGB

0.84 (0.82 \( - \) 0.87)

MLP

0.75 (0.63 \( - \) 0.86)

DT

0.72 (0.70 \( - \) 0.75)

LR

0.77 (0.71 \( - \) 0.83)