Intelligent algorithms applied to decision making in liver transplantation

• Grant number: 13/05300-2
• Support Opportunities: Regular Research Grants
• Start date: September 01, 2013
• End date: August 31, 2015
• Field of knowledge: Health Sciences - Medicine - Surgery
• Principal Investigator: Luciana Bertocco de Paiva Haddad
• Grantee: Luciana Bertocco de Paiva Haddad
• Host Institution: Faculdade de Medicina (FM). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated researchers: Alex Jones Flores Cassenote ; Cristina Correa de Oliveira ; Jair Minoro Abe ; Luiz Augusto Carneiro D'Albuquerque ; Neli Regina Siqueira Ortega ; Rodrigo Bronze de Martino ; Wellington Andraus

Abstract

Liver transplantation is the only therapeutic option for patients with end stage liver disease. However, due to lower supply of donors compared to patients on waiting list, it is essential to an appropriate selection of grafts. A better matching donor and recipient may use a larger number of offered organs without significant increase in morbidity and mortality post-transplant. Objectives: To examine the criteria proposed in the literature for decision on use of a liver graft in the Brazilian population, assessing which of these is the best criterion in this population. Furthermore, establishing a new criterion using adaptation and creation of algorithms with classical and non-classical logic can contribute to the modeling of uncertainty in decision-making. Methods: donor and recipient data after liver transplantation were provided by Central of Transplantation. The assessed endpoints in this research are graft loss and death of the receptor. To evaluate the effect of associated factors will be adopted as a measure of the effect hazard ratio (HR), estimated by the multivariate Cox. It will be create algorithms using expert systems or fuzzy logic and paraconsistent annotated non-classical logics suited to modeling uncertainty in decision-making. The evaluation of the results of the systems developed will face assessments by experts in liver transplant or other existing methods may be used tests Kappa agreement, for algorithms that result in a continuous quantitative variable, the ROC's curve will be used for comparisons possible. At the end, it is expected to have a group concerned with content developed and settled individually and collectively, with published scientific articles and software/registered in order to face new challenges. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

HADDAD, LUCIANA; FLORES CASSENOTE, ALEX JONES; ANDRAUS, WELLINGTON; DE MARTINO, RODRIGO BRONZE; DE SIQUEIRA ORTEGA, NELI REGINA; ABE, JAIR MINORO; CARNEIRO D'ALBUQUERQUE, LUIZ AUGUSTO. Factors Associated with Mortality and Graft Failure in Liver Transplants: A Hierarchical Approach. PLoS One, v. 10, n. 8, AUG 14 2015. (13/05300-2, 13/18158-0)