Characterization of Temporal Trajectories of Autoimmune Atrophic Gastritis Using a Graph Representation Learning Pipeline

Autoimmune atrophic gastritis (AAG) is a chronic autoimmune disease affecting the stomach. Its diagnosis is based on serologic profiles, histological evaluations and esophagogastroduodenoscopies (EGDSs). AAG is characterized by a progressively increasing mucosal damage that can lead to several complications, however the specific temporal dynamics of this disease have not been fully characterized yet. This paper presents an exploratory study of the application of a graph representation learning method to model the AAG progression by identifying temporal phenotypes. We employed a procedure that combines Topological Data Analysis (TDA) and Minimum Spanning Tree filters, on a longitudinal dataset of patients that underwent multiple EGDSs, obtained from a multicentric Italian cohort. The dataset includes histological evaluations and clinical observations derived from text notes that were annotated in a previous study, with a total of 236 patients, 836 EGDSs performed, and 18 variables. Using our algorithm, we obtained a graph with weights representing the temporal progression. Five possible disease trajectories were identified through a Minimum Spanning Tree. Statistical tests and Cox Hazard Analysis demonstrated the existence of significant differences in the development of complications timing within these trajectories, proving that our approach is able to characterize the AAG evolution even in a relatively small dataset.