Family History Information Extraction With Neural Attention and an Enhanced Relation-Side Scheme: Algorithm Development and Validation.
Family History Information Extraction With Neural Attention and an Enhanced Relation-Side Scheme: Algorithm Development and Validation.
复制标题
DOI：
10.2196/21750
复制
发表时间：
2020-12-01
影响因子：
3.2
通讯作者：
Jonnagaddala J
中科院分区：
文献类型：
--
作者：
Dai HJ;Lee YQ;Nekkantti C;Jonnagaddala J
从临床报告中识别和提取家族史信息对识别疾病易感性具有重要意义。然而，FHI通常在患者的电子健康记录中以叙述的方式描述，这需要应用自然语言处理技术来自动提取这些信息，以向医生提供更全面的以患者为中心的信息。本研究旨在克服在以前的研究中观察到的两个主要挑战，重点是FHI提取。一个是需要开发后处理规则来推断家庭提及的成员和边信息。二是有效地利用句内和句间信息来辅助FHI抽取。我们将该任务制定为一个顺序标记问题，并提出了一个增强的关系侧方案，该方案对所需的家庭成员属性进行编码，不仅消除了对后处理规则的需求，还减轻了训练实例不足的问题。此外，提出了一种基于注意力的神经网络结构，利用跨句信息来识别需要跨句推理的FHI及其属性。使用2019年n2 c2/OHNLP家族史提取任务发布的数据集来评估所提出方法的性能。我们首先比较了传统的神经序列模型与普通方案和增强方案的性能。接下来，我们通过与传统网络的性能比较，研究了所提出的注意力增强神经网络的有效性。据观察，利用增强的方案，可以提高神经网络的召回率，导致F分数增加0.024。提出的神经注意机制提高了召回率和准确率，并导致F分数提高了0.807，在共享任务中排名第四。我们提出了一个基于注意力的神经网络沿着一个增强的标签方案，使神经网络模型能够学习和解释跨句子识别的家庭成员的隐式关系和边信息，而不依赖于启发式规则。
Identifying and extracting family history information (FHI) from clinical reports are significant for recognizing disease susceptibility. However, FHI is usually described in a narrative manner within patients’ electronic health records, which requires the application of natural language processing technologies to automatically extract such information to provide more comprehensive patient-centered information to physicians. This study aimed to overcome the 2 main challenges observed in previous research focusing on FHI extraction. One is the requirement to develop postprocessing rules to infer the member and side information of family mentions. The other is to efficiently utilize intrasentence and intersentence information to assist FHI extraction. We formulated the task as a sequential labeling problem and propose an enhanced relation-side scheme that encodes the required family member properties to not only eliminate the need for postprocessing rules but also relieve the insufficient training instance issues. Moreover, an attention-based neural network structure was proposed to exploit cross-sentence information to identify FHI and its attributes requiring cross-sentence inference. The dataset released by the 2019 n2c2/OHNLP family history extraction task was used to evaluate the performance of the proposed methods. We started by comparing the performance of the traditional neural sequence models with the ordinary scheme and enhanced scheme. Next, we studied the effectiveness of the proposed attention-enhanced neural networks by comparing their performance with that of the traditional networks. It was observed that, with the enhanced scheme, the recall of the neural network can be improved, leading to an increase in the F score of 0.024. The proposed neural attention mechanism enhanced both the recall and precision and resulted in an improved F score of 0.807, which was ranked fourth in the shared task. We presented an attention-based neural network along with an enhanced tag scheme that enables the neural network model to learn and interpret the implicit relationship and side information of the recognized family members across sentences without relying on heuristic rules.
登录
查看更多内容
影响因子：
45.3
作者：
Wood, Marie E.;Kadlubek, Pamela;Hughes, Kevin S.
通讯作者：
Hughes, Kevin S.
影响因子：
4.5
作者：
Claassen, Liesbeth;Henneman, Lidewij;Timmermans, Danielle R. M.
通讯作者：
Timmermans, Danielle R. M.
影响因子：
--
作者：
Dai HJ;Syed-Abdul S;Chen CW;Wu CC
通讯作者：
Wu CC
影响因子：
5.5
作者：
Murff, HJ;Byrne, D;Syngal, S
通讯作者：
Syngal, S
影响因子：
3.5
作者：
Dai, Hong-Jie
通讯作者：
Dai, Hong-Jie