Browsing by Author "Chumbinho, B"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Pancreas Rejection in the Artificial Intelligence Era: New Tool for Signal Patients at RiskPublication . Vigia, E; Ramalhete, L; Ribeiro, R; Barros, I; Chumbinho, B; Filipe, E; Pena, A; Bicho, L; Nobre, A; Carrelha, S; Sobral, M; Lamelas, J; Coelho, JS; Ferreira, A; Pinto Marques, HIntroduction: Pancreas transplantation is currently the only treatment that can re-establish normal endocrine pancreatic function. Despite all efforts, pancreas allograft survival and rejection remain major clinical problems. The purpose of this study was to identify features that could signal patients at risk of pancreas allograft rejection. Methods: We collected 74 features from 79 patients who underwent simultaneous pancreas-kidney transplantation (SPK) and used two widely-applicable classification methods, the Naive Bayesian Classifier and Support Vector Machine, to build predictive models. We used the area under the receiver operating characteristic curve and classification accuracy to evaluate the predictive performance via leave-one-out cross-validation. Results: Rejection events were identified in 13 SPK patients (17.8%). In feature selection approach, it was possible to identify 10 features, namely: previous treatment for diabetes mellitus with long-term Insulin (U/I/day), type of dialysis (peritoneal dialysis, hemodialysis, or pre-emptive), de novo DSA, vPRA_Pre-Transplant (%), donor blood glucose, pancreas donor risk index (pDRI), recipient height, dialysis time (days), warm ischemia (minutes), recipient of intensive care (days). The results showed that the Naive Bayes and Support Vector Machine classifiers prediction performed very well, with an AUROC and classification accuracy of 0.97 and 0.87, respectively, in the first model and 0.96 and 0.94 in the second model. Conclusion: Our results indicated that it is feasible to develop successful classifiers for the prediction of graft rejection. The Naive Bayesian generated nomogram can be used for rejection probability prediction, thus supporting clinical decision making.
- Pancreatic Stone Protein As a Biomarker of SepsisPublication . Lopes, D; Chumbinho, B; Bandovas, JP; Faria, P; Espírito Santo, C; Ferreira, B; Val-Flores, L; Pereira, R; Germano, N; Bento, L
- Predicting Function Delay with a Machine Learning Model: Improve the Long-term Survival of Pancreatic GraftsPublication . Vigia, E; 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, RThe 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.