Preoperative prediction of gastric cancer T-staging based on ordinal regression models

Abstract

Objectives. Study of ordinal regressions presented via the set of binary logistic regressions and their application in clinical practice for T-staging of gastric cancer.
Methods. Methods of ordinal regression statistical models, model performance assessment, and survival analysis were used.
Results. Basic ordinal regression models have been studied and applied to the clinical data of gastric cancer. Some clinical predictors have been added to the well-known prognostic criteria according to the TNM classification in the multifactor regression model, results seem appropriate for a personalized approach when planning the treatment volume for improving efficacy.
Conclusion. The study showed that the analysis of ordinal models, along with multinomial ones, provides additional information that helps to understand the behavior of the latent variable in the complex cancer processes. The clinical part of the study facilitates a differentiated approach to preoperative planning of the treatment volume for patients with the same T-stage, based on modeling results.