Predictive model for graft loss in kidney post-transplantation

• Grant number: 21/06299-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2021
• End date: August 31, 2023
• Field of knowledge: Health Sciences - Medicine - Medical Clinics
• Principal Investigator: Luís Gustavo Modelli de Andrade
• Grantee: Arthur Cesar dos Santos Minato
• Host Institution: Faculdade de Medicina (FMB). Universidade Estadual Paulista (UNESP). Campus de Botucatu. Botucatu , SP, Brazil

Abstract

Kidney transplant is the most used treatment for patients in the final stage of Chronic Kidney Disease because it extends the survival of these individuals and reduces costs to the public health service. However, there are few studies that show post-transplant prognosis, mainly related to graft survival and rejection. Thus, new studies that correlate clinical, surgical (intra and postoperative), and chemical-laboratory variables are needed, in order to obtain a more accurate analysis of multiple possible patient outcomes. Therefore, the objective of this work is to create a predictive model for graft loss using the "machine learning" technique to make predictions based on pre-existing cases, elucidating possible new variables with greater predictive potential and improving interventions performed in the daily care of transplant patients. Methodology: A retrospective study that aims to build a predictive model for graft loss based on 1207 transplanted from living and deceased donors. Variables related to the recipient, donor, transplant, and immediate postoperative period will be studied, as well as the outcomes of the occurrence of graft loss, the reason for its loss and survival, will be evaluated. The data will be collected retrospectively in the hospitalization records and physical and electronic medical records of the service (Data Transplant), and then submitted to statistical analysis. Expected Results: The aim of this work is to identify factors that led to the incidence of graft loss in patients receiving kidney transplantation, creating an effective predictive model of graft loss risk, based on the machine learning technique. (AU)