Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning
Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning
复制标题
DOI：
10.48550/arxiv.2302.09400
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Sirui Ding;Ruixiang Tang;D. Zha;Na Zou;Kai Zhang;Xiaoqian Jiang;Xia Hu
中科院分区：
文献类型：
--
作者：
Sirui Ding;Ruixiang Tang;D. Zha;Na Zou;Kai Zhang;Xiaoqian Jiang;Xia Hu
肝移植是治疗严重肝病的基本疗法。肝脏资源的稀缺使得器官分配至关重要。终末期肝病模型（MELD）评分是决定器官分布时广泛采用的标准。然而，它忽略了移植后结果和器官/供体特征。这些限制促使了机器学习（ML）模型的出现。不幸的是，ML模型可能是不公平的，并引发对某些人群的偏见。为了解决这个问题，这项工作提出了一个公平的机器学习框架，目标是肝移植中的移植失败预测。具体来说，知识蒸馏是用来处理密集和稀疏的功能，结合树模型和神经网络的优点。一个两步去偏的方法是针对这个框架，以提高公平性。实验分析了现有模型中存在的不公平问题，并证明了该方法在预测和公平性能方面的优越性。
Liver transplant is an essential therapy performed for severe liver diseases. The fact of scarce liver resources makes the organ assigning crucial. Model for End-stage Liver Disease (MELD) score is a widely adopted criterion when making organ distribution decisions. However, it ignores post-transplant outcomes and organ/donor features. These limitations motivate the emergence of machine learning (ML) models. Unfortunately, ML models could be unfair and trigger bias against certain groups of people. To tackle this problem, this work proposes a fair machine learning framework targeting graft failure prediction in liver transplant. Specifically, knowledge distillation is employed to handle dense and sparse features by combining the advantages of tree models and neural networks. A two-step debiasing method is tailored for this framework to enhance fairness. Experiments are conducted to analyze unfairness issues in existing models and demonstrate the superiority of our method in both prediction and fairness performance.