Prediction performance of COXEN predictors.

The overall predictability (AUC) of identical COXEN predictors are summarized on the Dressman-119 and UVA-55 cohorts by AUC values with their 95% CIs and p-values. Cutoff values of COXEN predictors we

NIAID Data Ecosystem20

Prediction performances, based on the training dataset are given for the 10 compared predictors.

For each method, the accuracy, the sensitivity, the specificity and the Matthews correlation coefficients (MCC) are reported. Numbers in brackets correspond to 95% confidence intervals (95% C.I.) that

Figshare2015-12-02 更新00

Summary of predictive performance per dataset when using clinical predictors.

We predicted patient states using clinical predictors only (Analysis 2). For each combination of dataset, class variable, and classification algorithm, we calculated the arithmetic mean of area under

Figshare2022-03-11 更新00