Spatially and Temporally Resolving Predictive Biomarkers of Postoperative Recurrence and Complications in Chronic Intestinal Inflammation

Overview

A portion of patients with Inflammatory bowel disease often require surgical intervention since they do not respond to the current therapies. Besides this risk, patients may develop post-operative disease complications, and the factors beneath are far from being understood or predicted. The investigators hypothesize that some priming factors remain in the resection margin after surgery and act as a memory of the evolution of the disease, leading to the recurrence or complications. The following proposals are made: 1. defining and validating in humanized experimental models of intestinal inflammation the spatial and temporal dynamics of the postoperative complications-priming factors 2. integrating them into a machine-learning-driven model to determine risk indices of disease recurrence in IBD patients. This risk prediction model will not change the clinical decision-making process but will only be built for research. Consequently, patients enrolled in this study will be monitored and treated as per the standard of care. This project will reveal possible causes and build methods predictive of postoperative complications ultimately resulting in changes in clinical management in the near future.

A portion of patients with Inflammatory bowel disease often require surgical intervention since they do not respond to the current therapies. Besides this risk, patients may develop post-operative disease complications, and the factors beneath are far from being understood or predicted. The investigators hypothesize that some priming factors remain in the resection margin after surgery and act as a memory of the evolution of the disease, leading to the recurrence or complications. The following proposals are made: 1. defining and validating in humanized experimental models of intestinal inflammation the spatial and temporal dynamics of the postoperative complications-priming factors 2. integrating them into a machine-learning-driven model to determine risk indices of disease recurrence in IBD patients. This risk prediction model will not change the clinical decision-making process but will only be built for research. Consequently, patients enrolled in this study will be monitored and treated as per standard of care. This project will reveal possible causes and build methods that could help predict postoperative complications ultimately resulting in changes in clinical management.