Development and multicentric external validation of a prognostic COVID-19 severity model based on thoracic CT

Table 5 Receiver operating characteristic (ROC) area under the curve (AUC) on the holdout set of the best models from the four-fold cross-validation experiments

Model	AUC
Mean Teacher ConvNeXt	0.81
Logistic regression with features added to the baseline model:
Volume fractions	0.74
Volume fractions, mean intensity, kurtosis and skewness	0.82
Best three radiomic features from univariate selection	0.71
Volume fractions, best three radiomic features from univariate selection	0.72
Volume fractions, best three radiomic features from multivariate selection	0.73

For the logistic regression, the baseline model considers the patient age and sex. Volume fractions include the respective values for ground glass opacity (GGO) and consolidation separately. Mean intensity, kurtosis and skewness include the values for healthy lung parenchyma, GGO and consolidation separately. Best three radiomic features from univariate feature selection: lbp-3D-k_glszm_ZoneVariance, original_shape_Maximum2DDiameterColumn, lbp-3D-m1_glrlm_LongRunLowGrayLevelEmphasis. Best three radiomic features from multivariate feature selection: wavelet-HLL_glcm_MaximumProbability, wavelet-LLL_glrlm_HighGrayLevelRunEmphasis, wavelet-LHL_glcm_Correlation

ISSN: 1472-6947