Fig. 4
From: Machine learning models using dual-phase CT radiomics for early detection of PRISm
Performance of clinical, radiomic, and clinical-radiomic models in predicting PRISm using inspiratory-phase, expiratory-phase, and dual-phase CT. (a-c) ROC curves for the clinical model, radiomic model, and clinical-radiomic model based on inspiratory-phase in the training cohort (a), internal test cohort (b), and external test cohort (c), respectively. (d-f) ROC curves for the clinical model, radiomic model, and clinical-radiomic model based on expiratory-phase in the training cohort (d), internal test cohort (e), and external test cohort (f), respectively. (g-i) ROC curves for the clinical model, radiomic model, and clinical-radiomic model based on dual-phase in the training cohort (g), internal test cohort (h), and external test cohort (i), respectively. The red solid line, dark blue dashed line, and light blue solid line represent the predictive performance of the clinical model, radiomics model, and combined model, respectively. Figures were automatically generated using the Onekey AI platform, and font sizes and label styles follow system defaults.
