Research Paper Volume 14, Issue 2 pp 907—922

A radiomics model predicts the response of patients with advanced gastric cancer to PD-1 inhibitor treatment


Figure 2. A flow chart of the radiomics analysis. Based on CT images, important imaging features were screened and combined with important clinical risk factors to generate radiomics nomograms. The performance and clinical utility of the radiomics model to predict anti-PD-1 treatment efficacy were evaluated through receiver operator characteristic (ROC), calibration and decision curve analyses. Survival prediction was also explored.