Enhancing unsupervised medical entity linking with multi-instance learning

Abstract Background A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng Yan, Yuanzhe Zhang, Kang Liu, Jun Zhao, Yafei Shi, Shengping Liu
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Medical entity linking Unsupervised learning Multiple instance learning Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/3d709502866840f0bb9649983c16a49a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3d709502866840f0bb9649983c16a49a
record_format	dspace
spelling	oai:doaj.org-article:3d709502866840f0bb9649983c16a49a2021-11-21T12:28:56ZEnhancing unsupervised medical entity linking with multi-instance learning10.1186/s12911-021-01654-z1472-6947https://doaj.org/article/3d709502866840f0bb9649983c16a49a2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01654-zhttps://doaj.org/toc/1472-6947Abstract Background A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background. Methods We propose an unsupervised entity linking model using multi-instance learning (MIL). Our approach builds on a basic unsupervised entity linking method (named BEL), which is an embedding similarity-based EL model in this paper, and uses MIL training paradigm to boost the performance of BEL. First, we construct a dataset from an unlabeled large-scale Chinese medical consultation corpus with the help of BEL. Subsequently, we use a variety of encoders to obtain the representations of mention-context and the ICD10 entities. Then the representations are fed into a ranking network to score candidate entities. Results We evaluate the proposed model on the test dataset annotated by professional doctors. The evaluation results show that our method achieves 60.34% accuracy, exceeding the fundamental BEL by 1.72%. Conclusions We propose an unsupervised entity linking method to the entity linking in the medical domain, using MIL training manner. We annotate a test set for evaluation. The experimental results show that our model behaves better than the fundamental model BEL, and provides an insight for future research.Cheng YanYuanzhe ZhangKang LiuJun ZhaoYafei ShiShengping LiuBMCarticleMedical entity linkingUnsupervised learningMultiple instance learningComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss S9, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medical entity linking Unsupervised learning Multiple instance learning Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Medical entity linking Unsupervised learning Multiple instance learning Computer applications to medicine. Medical informatics R858-859.7 Cheng Yan Yuanzhe Zhang Kang Liu Jun Zhao Yafei Shi Shengping Liu Enhancing unsupervised medical entity linking with multi-instance learning
description	Abstract Background A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background. Methods We propose an unsupervised entity linking model using multi-instance learning (MIL). Our approach builds on a basic unsupervised entity linking method (named BEL), which is an embedding similarity-based EL model in this paper, and uses MIL training paradigm to boost the performance of BEL. First, we construct a dataset from an unlabeled large-scale Chinese medical consultation corpus with the help of BEL. Subsequently, we use a variety of encoders to obtain the representations of mention-context and the ICD10 entities. Then the representations are fed into a ranking network to score candidate entities. Results We evaluate the proposed model on the test dataset annotated by professional doctors. The evaluation results show that our method achieves 60.34% accuracy, exceeding the fundamental BEL by 1.72%. Conclusions We propose an unsupervised entity linking method to the entity linking in the medical domain, using MIL training manner. We annotate a test set for evaluation. The experimental results show that our model behaves better than the fundamental model BEL, and provides an insight for future research.
format	article
author	Cheng Yan Yuanzhe Zhang Kang Liu Jun Zhao Yafei Shi Shengping Liu
author_facet	Cheng Yan Yuanzhe Zhang Kang Liu Jun Zhao Yafei Shi Shengping Liu
author_sort	Cheng Yan
title	Enhancing unsupervised medical entity linking with multi-instance learning
title_short	Enhancing unsupervised medical entity linking with multi-instance learning
title_full	Enhancing unsupervised medical entity linking with multi-instance learning
title_fullStr	Enhancing unsupervised medical entity linking with multi-instance learning
title_full_unstemmed	Enhancing unsupervised medical entity linking with multi-instance learning
title_sort	enhancing unsupervised medical entity linking with multi-instance learning
publisher	BMC
publishDate	2021
url	https://doaj.org/article/3d709502866840f0bb9649983c16a49a
work_keys_str_mv	AT chengyan enhancingunsupervisedmedicalentitylinkingwithmultiinstancelearning AT yuanzhezhang enhancingunsupervisedmedicalentitylinkingwithmultiinstancelearning AT kangliu enhancingunsupervisedmedicalentitylinkingwithmultiinstancelearning AT junzhao enhancingunsupervisedmedicalentitylinkingwithmultiinstancelearning AT yafeishi enhancingunsupervisedmedicalentitylinkingwithmultiinstancelearning AT shengpingliu enhancingunsupervisedmedicalentitylinkingwithmultiinstancelearning
_version_	1718419000732418048

Enhancing unsupervised medical entity linking with multi-instance learning

Ejemplares similares