Predicting NRG1 expression and its molecular-pathological features of bladder cancer through a machine learning-based pathomics model

This study aims to predict the expression of NRG1 in bladder cancer using pathomic techniques. We obtained transcriptomic data, pathological images, and clinical data of bladder cancer patients from TCGA. OTSU algorithm was used to segment images. The features obtained by mRMR_RFE screening were modeled by GBM algorithm. Further, the correlation between the Pathomics score and immune genes was analyzed. A total of 20 features were obtained by mRMR_RFE screening, and a prediction model of NRG1 was constructed. The AUC of the ROC curve in the training set and the validation set are 0.789 and 0.702 respectively. Pathomics score was positively correlated with immune-related genes ( p < 0.05). Silencing NRG1 could suppress BLCA cell proliferation, migration, invasion, whereas its overexpression exhibited contrasting effects. The pathomics model showed moderate discriminatory ability, and pathomics score is positively correlated with immune-related genes.