A system for automatically extracting clinical events with temporal information

Zhijing Li,Xuan Wang,Chen Li,Yu Long

doi:10.1186/s12911-020-01208-9

Zhijing Li, Xuan Wang + Show 2 more

Open Access

https://doi.org/10.1186/s12911-020-01208-9

Copy DOI

Abstract

BackgroundThe popularization of health and medical informatics yields huge amounts of data. Extracting clinical events on a temporal course is the foundation of enabling advanced applications and research. It is a structure of presenting information in chronological order. Manual extraction would be extremely challenging due to the quantity and complexity of the records.MethodsWe present an recurrent neural network- based architecture, which is able to automatically extract clinical event expressions along with each event’s temporal information. The system is built upon the attention-based and recursive neural networks and introduce a piecewise representation (we divide the input sentences into three pieces to better utilize the information in the sentences), incorporates semantic information by utilizing word representations obtained from BioASQ and Wikipedia.ResultsThe system is evaluated on the THYME corpus, a set of manually annotated clinical records from Mayo Clinic. In order to further verify the effectiveness of the system, the system is also evaluated on the TimeBank _Dense corpus. The experiments demonstrate that the system outperforms the current state-of-the-art models. The system also supports domain adaptation, i.e., the system may be used in brain cancer data while its model is trained in colon cancer data.ConclusionOur system extracts temporal expressions, event expressions and link them according to actually occurring sequence, which may structure the key information from complicated unstructured clinical records. Furthermore, we demonstrate that combining the piecewise representation method with attention mechanism can capture more complete features. The system is flexible and can be extended to handle other document types.

Highlights

The popularization of health and medical informatics yields huge amounts of data
Six methods of temporal expression extraction. 1) a rule-based method; 2) a system based on Conditional random field (CRF); 3) a system based on general recurrent neural network (RNN) without any attention mechanism or context (RNN); 4) a system based on RNN with easy attention mechanism but without any context words (RNN-att); 5) our proposed method, a RNN system with attention mechanism and context words; 6) a system combines the CRF and RNN network
Through careful observation of data, we found that many time expressions always show up behind a preposition, we judge whether those five words are related to time expressions

Summary

Introduction

Extracting clinical events on a temporal course is the foundation of enabling advanced applications and research It is a structure of presenting information in chronological order. Large data analysis of medical treatment needs to map the corresponding medical events in the clinical records; the medical events with temporal information are very useful in medical era. These efforts will become the foundation of understanding disease, facilitating the analysis of large medical data as well. It is easier for understanding the events and corresponding time point. The actual events and their occurring consequence becomes clear at a glance

Results

Discussion

Conclusion