Representation learning for clinical time series prediction tasks in electronic health records
Representation learning for clinical time series prediction tasks in electronic health records
复制标题
电子健康记录中临床时间序列预测任务的表示学习
DOI：
10.1186/s12911-019-0985-7
复制
发表时间：
2019-12-17
影响因子：
3.5
通讯作者：
Gao, Ju
中科院分区：
文献类型：
--
作者：
Ruan, Tong;Lei, Liqi;Gao, Ju
背景：电子健康记录（EHR）为改善患者护理和促进临床研究提供了可能性。然而，电子病历的应用面临着许多挑战，如时间性、高维性、稀疏性、噪声、随机误差和系统偏差等。特别是，时间信息是难以有效地利用传统的机器学习方法，而EHRs的顺序信息是非常有用的。方法：在本文中，我们提出了一种通用的患者表示学习方法来总结顺序EHRs。具体而言，基于递归神经网络的去噪自动编码器（RNN-DAE）编码成一个低维dense vector.Results：基于收集的EHR数据从曙光医院附属上海中医药大学，我们实验评估我们提出的RNN-DAE方法在死亡率预测任务和合并症预测任务。大量的实验结果表明，我们提出的RNN-DAE方法优于现有的方法。此外，我们应用我们提出的RNN-DAE方法所代表的“深度特征”来跟踪类似的患者与t-SNE，这也取得了一些有趣的observation.Conclusion：我们提出了一个有效的无监督RNN-DAE方法来总结病人的顺序信息EHR数据。我们提出的RNN-DAE方法在死亡率预测任务和并发症预测任务上都是有用的。
Background: Electronic health records (EHRs) provide possibilities to improve patient care and facilitate clinical research. However, there are many challenges faced by the applications of EHRs, such as temporality, high dimensionality, sparseness, noise, random error and systematic bias. In particular, temporal information is difficult to effectively use by traditional machine learning methods while the sequential information of EHRs is very useful.Method: In this paper, we propose a general-purpose patient representation learning approach to summarize sequential EHRs. Specifically, a recurrent neural network based denoising autoencoder (RNN-DAE) is employed to encode inhospital records of each patient into a low dimensional dense vector.Results: Based on EHR data collected from Shuguang Hospital affiliated to Shanghai University of Traditional Chinese Medicine, we experimentally evaluate our proposed RNN-DAE method on both mortality prediction task and comorbidity prediction task. Extensive experimental results show that our proposed RNN-DAE method outperforms existing methods. In addition, we apply the "Deep Feature" represented by our proposed RNN-DAE method to track similar patients with t-SNE, which also achieves some interesting observations.Conclusion: We propose an effective unsupervised RNN-DAEmethod to summarize patient sequential information in EHR data. Our proposed RNN-DAE method is useful on both mortality prediction task and comorbidity prediction task.