A machine learning framework to predict kidney graft failure with class imbalance using Red Deer algorithm
作者：
Highlights：
• A three-phase RDA-based clustering undersampling method to handle class imbalance.
• An RDA-based clustering feature extraction technique to reduce data dimensionality.
• The proposed method could efficiently address the class imbalance problem.
• The performance of SVM, ANN, KNN, DT, and an ensemble method is compared.
• Decision tree outperformed other classifiers with the value of 0.95 for AUC.
摘要
•A three-phase RDA-based clustering undersampling method to handle class imbalance.•An RDA-based clustering feature extraction technique to reduce data dimensionality.•The proposed method could efficiently address the class imbalance problem.•The performance of SVM, ANN, KNN, DT, and an ensemble method is compared.•Decision tree outperformed other classifiers with the value of 0.95 for AUC.
论文关键词：Kidney transplantation,Graft rejection,Machine learning,Imbalanced data,Red deer algorithm
论文评审过程：Received 9 April 2022, Revised 27 July 2022, Accepted 9 August 2022, Available online 12 August 2022, Version of Record 22 August 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118515
