2019
DOI: 10.1109/access.2019.2919121
|View full text |Cite
|
Sign up to set email alerts
|

A Hybrid Method to Extract Clinical Information From Chinese Electronic Medical Records

Abstract: Narrative reports in medical records contain abundant clinical information that may be converted into structured data for managing patient information and predicting trends in diseases. Though various rule-based and machine-learning methods are available in electronic medical records (EMRs), a few works have explored the hybrid methods in extracting information from the Chinese EMRs. In this paper, we developed a novel hybrid approach which integrates the rules and bidirectional long short-term memory with a c… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
9

Relationship

2
7

Authors

Journals

citations
Cited by 15 publications
(8 citation statements)
references
References 26 publications
0
8
0
Order By: Relevance
“…Feature extraction is generally implemented by a coding layer in the NER framework. BiLSTM 33 and BiGRU 34 models are commonly used for feature extraction. BiLSTM uses two-layer LSTM to obtain the forward and backward information of text sequences and splicing them to obtain the final hidden layer feature representation, which can solve the problem of capturing contextual semantic information and effectively improve the effect of named entity recognition 35 .…”
Section: Introductionmentioning
confidence: 99%
“…Feature extraction is generally implemented by a coding layer in the NER framework. BiLSTM 33 and BiGRU 34 models are commonly used for feature extraction. BiLSTM uses two-layer LSTM to obtain the forward and backward information of text sequences and splicing them to obtain the final hidden layer feature representation, which can solve the problem of capturing contextual semantic information and effectively improve the effect of named entity recognition 35 .…”
Section: Introductionmentioning
confidence: 99%
“…Xia et al (10) used the long short-term memory (LSTM) model to identify medical entities in EMR text and achieved 89.44% of the F1-score, which confirmed the effectiveness of deep learning algorithms in EMRs named entity recognition tasks. Cheng et al (11) extracted clinical entities and attributes from various types of clinical narrative texts, such as operative records, discharge summaries, clinical data requests, etc., using a novel hybrid approach called clinical entity and attributes extractor (CEAER), which combines the rules and bidirectional LSTM networks with a conditional random field layer model. Finally, this bidirectional long short-term memory conditional random fields (BiLSTM-CRF) model achieved an F1-score of 87.00%.…”
Section: Related Workmentioning
confidence: 99%
“…In the training process, we maximized the logarithmic probability of correct tag sequences y*. [11] y* represents the result of the true tag, and Y X represents all possible tags. After decoding, the output sequence with the maximum score is obtained:…”
Section: + + + + + + + + + + + + + + + + + + + + E [Cls] E 给 E 予 E 云 E 克 E 抗 E 炎 E 镇 E 痛 E [Sep] E 关 E 节 E 肿 E 痛 E 好 E 转 E 后 E 出 E 院 E [Smentioning
confidence: 99%
“…With the rapid development of computing technologies, more and more medical monitoring equipments and software systems are used in clinical practice, generating a large amount of data. This provides opportunities and challenges to accelerate clinical science using large scale of practical clinical data in less expense [ 1 , 2 ]. For this reason, machine learning has been increasing impact for medical information research.…”
Section: Introductionmentioning
confidence: 99%