Noninvasive radiomic analysis of enhanced CT predicts CTLA4 expression and prognosis in head and neck squamous cell carcinoma

Developing a radiomic model to predict CTLA4 expression levels and assessing its prognostic accuracy for patients. Medical imaging data were sourced from the TCIA database, while transcriptome sequencing data were derived from the TCGA database. We utilized a linear kernel SVM algorithm to develop a radiomic model for predicting CTLA4 gene expression. We then assessed the model’s clinical relevance using survival and Cox regression analyses. Performance evaluations of the model were illustrated through ROC, PR, calibration, and decision curves. (1) Bioinformatics analysis: Kaplan–Meier curves indicated that increased CTLA4 expression correlates with enhanced overall survival (OS) (p