Figures & data
Figure 1 Screening of CTD-ILD patients.
![Figure 1 Screening of CTD-ILD patients.](/cms/asset/379ef782-54ab-45fd-b13b-2907a9dabc3c/dtcr_a_181043_f0001_c.jpg)
Figure 2 Feature selection.
![Figure 2 Feature selection.](/cms/asset/ef05247a-d21c-490c-9c7d-622e75216715/dtcr_a_181043_f0002_c.jpg)
![Figure 2 Feature selection.](/cms/asset/848e7379-ca36-422c-9f9e-f2c52779f262/dtcr_a_181043_f0002a_b.jpg)
Table 1 Patient characteristics in the training and testing cohorts
Table 2 Characteristics of patients who responded or did not respond to treatment in the training and testing cohorts
Figure 3 Feature selection using the LASSO binary logistic model.
Abbreviation: LASSO, least absolute shrinkage and selection operator.
![Figure 3 Feature selection using the LASSO binary logistic model.](/cms/asset/58353801-8c14-4dd5-97f5-c60314335112/dtcr_a_181043_f0003_c.jpg)
Table 3 LASSO coefficient profiles of the eleven features
Figure 4 ROC curves for machine learning of radiomics to predict treatment response.
Abbreviations: AUC, area under the curve; k-NN, k-nearest neighbors; RF, random forest; ROC, receiver-operating characteristic.
![Figure 4 ROC curves for machine learning of radiomics to predict treatment response.](/cms/asset/ba0d566a-a00d-4ce4-aa86-b2d0f789ed8a/dtcr_a_181043_f0004_c.jpg)
Figure 5 Developed radiomics nomogram.
Abbreviation: ICU, intensive care unit.
![Figure 5 Developed radiomics nomogram.](/cms/asset/5e63b380-bac5-41da-a773-de68fb82367f/dtcr_a_181043_f0005_c.jpg)