Predicting Function Delay with a Machine Learning Model: Improve the Long-term Survival of Pancreatic Grafts

• Autor(a) principal: Vigia, E
• Data de Publicação: 2022
• Outros Autores: Ramalhete, L, Barros, I, Chumbinho, B, Filipe, E, Pena, A, Bicho, L, Nobre, A, Carrelha, S, Corado, S, Sobral, M, Lamelas, J, Santos Coelho, J, Pinto Marques, H, Pico, P, Costa, S, Rodrigues, F, Bigotte Vieira, M, Magriço, R, Cotovio, P, Caeiro, F, Aires, I, Silva, C, Remédio, F, Martins, A, Ferreira, A, Paulino, J, Nolasco, F, Ribeiro, R
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.17/4632
• topic: Pancreas Transplantation; Graft Rejection; Graft Survival; HCC CHBPT

The impact of delayed graft function on outcomes following various solid organ transplants is well documented and addressed in the literature. Delayed graft function following various solid organ transplants is associated with both short- and long-term graft survival issues. In a retrospective cohort study including 106 patients we evaluated whether pancreas graft survival differs according to moment of insulin therapy following simultaneous pancreaskidney transplant. As a result, we aimed to identify possible risk factors and build a machine-learning-based model that predicts the likelihood of dysfunction following SPK transplant patients based on day zero data after transplant, allowing to enhance pancreatic graft survival. Feature selection by Relief algorithm yielded donor features, age, cause of death, hemoglobin, gender, ventilation days, days in ICU, length of cardiac respiratory arrest and recipient features, gender, long-term insulin, dialysis type, time of diabetes mellitus, vPRA pre-Tx, number of HLA-A mismatches and PRDI, all contributed to the models' strength.