Table 2 Discrimination and calibration for predicting exacerbation within 2 days (validation cohort).

From: Machine learning did not beat logistic regression in time series prediction for severe asthma exacerbations

 

AUC

Calibration intercept

Calibration slope

XGBoost

0.81 (0.78, 0.84)

0.32 (0.15, 0.48)

0.56 (0.5, 0.61)

Logistic regression

0.88 (0.86, 0.90)

0.75 (0.6, 0.90)

1.02 (0.93, 1.10)

  1. XGBoost gradient boosted decision trees, AUC area under the receiver operating characteristics curve.
Back to article page