College of Biomedical Engineering and Instrument Science, Zhejiang University, PR China.
Department of Cardiology, Chinese PLA General Hospital, PR China.
J Biomed Inform. 2018 Nov;87:118-130. doi: 10.1016/j.jbi.2018.10.002. Epub 2018 Oct 15.
The detection of Adverse Medical Events (AMEs) plays an important role in disease management in ensuring efficient treatment delivery and quality improvement of health services. Recently, with the rapid development of hospital information systems, a large volume of Electronic Health Records (EHRs) have been produced, in which AMEs are regularly documented in a free-text manner. In this study, we are concerned with the problem of AME detection by utilizing a large volume of unstructured EHR data. To address this challenge, we propose a neural attention network-based model to incorporate the contextual information of words into AME detection. Specifically, we develop a context-aware attention mechanism to locate salient words with respect to the target AMEs in patient medical records. And then we combine the proposed context attention mechanism with the deep learning tactic to boost the performance of AME detection. We validate our proposed model on a real clinical dataset that consists of 8845 medical records of patients with cardiovascular diseases. The experimental results show that our proposed model advances state-of-the-art models and achieves competitive performance in terms of AME detection.
不良医疗事件（AMEs）的检测在疾病管理中起着重要作用，可确保高效的治疗提供和医疗服务质量的提高。最近，随着医院信息系统的快速发展，产生了大量的电子健康记录（EHRs），其中定期以自由文本的方式记录 AMEs。在本研究中，我们关注的是利用大量非结构化 EHR 数据进行 AME 检测的问题。为了解决这一挑战，我们提出了一种基于神经注意网络的模型，将单词的上下文信息纳入 AME 检测中。具体来说，我们开发了一种上下文感知注意力机制，以便在患者病历中找到与目标 AMEs 相关的突出单词。然后，我们将提出的上下文注意机制与深度学习策略相结合，以提高 AME 检测的性能。我们在包含 8845 例心血管疾病患者病历的真实临床数据集上验证了我们提出的模型。实验结果表明，我们提出的模型优于最先进的模型，在 AME 检测方面具有竞争优势。
