Delayed graft function in transplant
| Article DOI | https://doi.org/10.1002/uog.29129 |
| Objective | To develop a predictive model for the risk of delayed graft function (DGF) after pediatric kidney transplantation. |
| AI Approach | RF, LR, linear discriminant analysis, KNN, DT, XGBoost, SVM, GBM, Naive Bayes, Lasso, Ridge, ElasticNet |
| Data Source(s) | Single institutional series (140 patients) |
| Model Input | High-density lipoprotein cholesterol, donor after circulatory death, warm ischemia time, cold ischemia time, gender match, donor creatinine |
| Model Outcome | Delayed graft function |
| Model Metrics | AUC of 0.98 (entire cohort) |
| Model Usability | Code and dataset not publicly available. |
AI = Artificial intelligence, KNN = K-nearest neighbours, SVM = Support vector machines, AUC = Area under the receiver operator characteristic
AIPEDURO 
Leave a comment