AdaDiag: Adversarial Domain Adaptation of Diagnostic Prediction with Clinical Event Sequences.

AdaDiag: Adversarial Domain Adaptation of Diagnostic Prediction with Clinical Event Sequences.
复制标题

DOI:
10.1016/j.jbi.2022.104168
复制
发表时间:
2022-10
影响因子:
4.5
通讯作者:
Bui, Alex A. T.
Bui, Alex A. T.
中科院分区:
医学3区
文献类型:
--
作者:
Zhang, Tianran;Chen, Muhao;Bui, Alex A. T.

文献摘要

参考文献

被引文献

相似文献

心力衰竭(HF)的早期发现可以为患者提供更及时的干预和更好的疾病管理以及有效利用医疗资源的机会。最近的机器学习(ML)方法在使用电子健康记录(EHR)中的时间序列进行诊断预测方面表现出了良好的性能。然而,在实践中,由于数据集的变化,这些模型可能无法推广到其他人群。数据集的变化可归因于一系列因素,例如人口统计、数据管理方法和医疗保健提供模式的变化。在本文中,我们使用无监督的对抗域适应方法来自适应地减少数据集转移对跨机构传输性能的影响。使用使用掩码语言建模 (MLM) 任务预训练的 BERT 式基于 Transformer 的语言模型,在下次访问 HF 发作预测任务上对所提出的框架进行了验证。我们的模型凭经验证明了在两个不同的临床事件序列数据源的两个传输方向上相对于非对抗性基线的优越预测性能。
Early detection of heart failure (HF) can provide patients with the opportunity for more timely intervention and better disease management, as well as efficient use of healthcare resources. Recent machine learning (ML) methods have shown promising performance on diagnostic prediction using temporal sequences from electronic health records (EHRs). In practice, however, these models may not generalize to other populations due to dataset shift. Shifts in datasets can be attributed to a range of factors such as variations in demographics, data management methods, and healthcare delivery patterns. In this paper, we use unsupervised adversarial domain adaptation methods to adaptively reduce the impact of dataset shift on cross-institutional transfer performance. The proposed framework is validated on a next-visit HF onset prediction task using a BERT-style Transformer-based language model pre-trained with a masked language modeling (MLM) task. Our model empirically demonstrates superior prediction performance relative to non-adversarial baselines in both transfer directions on two different clinical event sequence data sources.
DOI: 10.1093/jamia/ocw112
发表时间: 2017-03-01
期刊: Journal of the American Medical Informatics Association : JAMIA
影响因子: --
作者:
Choi E;Schuetz A;Stewart WF;Sun J
通讯作者: Sun J
基于脑电图的情绪识别的两级域适应神经网络
DOI: 10.3389/fnhum.2020.605246
发表时间: 2020
影响因子: 2.9
作者:
Bao G;Zhuang N;Tong L;Yan B;Shu J;Wang L;Zeng Y;Shen Z
通讯作者: Shen Z
DOI: 10.1007/s41666-019-00062-3
发表时间: 2020-06-01
影响因子: 5.9
作者:
Gupta, Priyanka;Malhotra, Pankaj;Shroff, Gautam
通讯作者: Shroff, Gautam
DOI: 10.1161/01.cir.101.23.e215
发表时间: 2000-06-13
期刊: CIRCULATION
影响因子: 37.8
作者:
Goldberger, AL;Amaral, LAN;Stanley, HE
通讯作者: Stanley, HE
DOI: 10.1177/1178222617712994
发表时间: 2017
期刊: Biomedical informatics insights
影响因子: --
作者:
Desautels T;Calvert J;Hoffman J;Mao Q;Jay M;Fletcher G;Barton C;Chettipally U;Kerem Y;Das R
通讯作者: Das R