Graft failure in kidney transplants
| Article DOI | https://doi.org/10.1111/petr.70043 |
| Objective | To identify risk factors for chronic rejection-caused graft failure 15 years post-transplant |
| AI Approach | Logistic regression, k-nearest Neighbors, SVM, Decision Tree, ANN, RF |
| Data Source(s) | National Standard Transplant Analysis and Research (STAR) dataset (6604 patients) |
| Model Input | 19 features, including proximity of most and least recent serum crossmatch test, time on waiting list, recipient weight, proximity of first dialysis, recipient height, cold ischemia time, recipient age at listing |
| Model Outcome | Graft survival at 15 years |
| Model Metrics | AUC 0.81, accuracy 74% |
| Model Usability | Dataset is available upon request |
AI = Artificial intelligence, AUC = Area under the receiver operator characteristic
AIPEDURO 
Leave a comment