Systematization of an Artificial Intelligence system for Improved Infectious Diseases Outcomes in Kidney Transplant Recipients

• Grant number: 25/02134-1
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: May 01, 2025
• End date: October 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: José Fernando Rodrigues Júnior
• Grantee: Ivar Vargas Belizario
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 24/04761-0 - Artificial Intelligence for Improved Infectious Diseases Outcomes in Kidney Transplant Recipients (AIIDKIT), AP.R

Abstract

This project focuses on Artificial Intelligence for enhanced outcomes in infectious diseases among kidney transplant recipients; it taps into rich datasets from Brazilian and Swiss kidney transplants to advance predictive modeling in transplantation medicine. Utilizing data from varied patient demographics and healthcare frameworks, the project aims to advance the prediction of infection risks in kidney transplant recipients through deep learning methodologies. This strategy seeks to improve prognostic accuracy and deliver tailored insights into patients' health progressions by benefiting from longitudinal data from transplant cohorts. Led by a cross-disciplinary team from the University of São Paulo, the Paulista State University, and the University of Geneva, this endeavor is a step towards advancing AI-enabled healthcare. The project's methodology involves analyzing data, refining predictive models, and exploring innovative ways to represent data, aiming to create a predictive system capable of explaining the complex dynamics of kidney transplants. By leveraging attention-based models to process transplant trajectory data, the project will provide predictions on patient outcomes and infection risk. The initiative is designed to support clinical decisions on prophylactic and preemptive measures.