arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.04853cs.LG
收藏

对抗样本增强的领域自适应--基于电子病历的预测建模研究

Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records

IBM Research(IBM研究院)

Yiqin Yu, Pin-Yu Chen, Yuan Zhou, Jing Mei

摘要:

随着机器学习在电子健康记录(EHR)上的成功采用,已经部署了许多计算模型来解决各种临床问题。然而,由于EHR的异质性,在不同患者群体上训练的模型具有较差的泛化能力。如何缓解模型构建的源患者组和模型部署的目标患者组之间的域转移成为一个关键问题。在本文中,我们提出了一种数据增强方法,以促进领域自适应,利用知识的源患者组时,训练模型的目标。具体地,在领域自适应期间使用逆向生成的样本来填充两个患者组之间的泛化间隙。通过MIMIC-III EHR数据集上不同预测建模任务的案例研究,对所提出的方法进行了评估。结果证实了我们的方法的有效性和不同任务的通用性。

英文摘要:

With the successful adoption of machine learning on electronic health records (EHRs), numerous computational models have been deployed to address a variety of clinical problems. However, due to the heterogeneity of EHRs, models trained on different patient groups suffer from poor generalizability. How to mitigate domain shifts between the source patient group where the model is built upon and the target one where the model will be deployed becomes a critical issue. In this paper, we propose a data augmentation method to facilitate domain adaptation, which leverages knowledge from the source patient group when training model on the target one. Specifically, adversarially generated samples are used during domain adaptation to fill the generalization gap between the two patient groups. The proposed method is evaluated by a case study on different predictive modeling tasks on MIMIC-III EHR dataset. Results confirm the effectiveness of our method and the generality on different tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑