Extracting clinical knowledge from electronic medical records
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/17591 |
Resumo: | As the adoption of Electronic Medical Records (EMRs) rises in the healthcare institutions, these resources’ importance increases due to all clinical information they contain about patients. However, the unstructured information in the form of clinical narratives present in these records makes it hard to extract and structure useful clinical knowledge. This unstructured information limits the potential of the EMRs because the clinical information these records contain can be used to perform essential tasks inside healthcare institutions such as searching, summarization, decision support and statistical analysis, as well as be used to support management decisions or serve for research. These tasks can only be done if the unstructured clinical information from the narratives is appropriately extracted, structured and processed in clinical knowledge. Usually, this information extraction and structuration in clinical knowledge is performed manually by healthcare practitioners, which is not efficient and is error-prone. This research aims to propose a solution to this problem, by using Machine Translation (MT) from the Portuguese language to the English language, Natural Language Processing (NLP) and Information Extraction (IE) techniques. With the help of these techniques, the goal is to develop a prototype pipeline modular system that can extract clinical knowledge from unstructured clinical information contained in Portuguese EMRs, in an automated way, in order to help EMRs to fulfil their potential and consequently help the Portuguese hospital involved in this research. This research also intends to show that this generic prototype system and approach can potentially be applied to other hospitals, even if they don’t use the Portuguese language. |
id |
RCAP_7c5da1995e5353d3bf347c160c6fd3d8 |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/17591 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Extracting clinical knowledge from electronic medical recordsInformation extractionKnowledge extractionMachine translationNatural language processingText miningEngenharia informáticaDados médicosProcessamento da linguagemProcessamento da informaçãoAs the adoption of Electronic Medical Records (EMRs) rises in the healthcare institutions, these resources’ importance increases due to all clinical information they contain about patients. However, the unstructured information in the form of clinical narratives present in these records makes it hard to extract and structure useful clinical knowledge. This unstructured information limits the potential of the EMRs because the clinical information these records contain can be used to perform essential tasks inside healthcare institutions such as searching, summarization, decision support and statistical analysis, as well as be used to support management decisions or serve for research. These tasks can only be done if the unstructured clinical information from the narratives is appropriately extracted, structured and processed in clinical knowledge. Usually, this information extraction and structuration in clinical knowledge is performed manually by healthcare practitioners, which is not efficient and is error-prone. This research aims to propose a solution to this problem, by using Machine Translation (MT) from the Portuguese language to the English language, Natural Language Processing (NLP) and Information Extraction (IE) techniques. With the help of these techniques, the goal is to develop a prototype pipeline modular system that can extract clinical knowledge from unstructured clinical information contained in Portuguese EMRs, in an automated way, in order to help EMRs to fulfil their potential and consequently help the Portuguese hospital involved in this research. This research also intends to show that this generic prototype system and approach can potentially be applied to other hospitals, even if they don’t use the Portuguese language.Com a adopção cada vez maior das instituições de saúde face aos Processos Clínicos Electrónicos (PCE), estes documentos ganham cada vez mais importância em contexto clínico, devido a toda a informação clínica que contêm relativamente aos pacientes. No entanto, a informação não estruturada na forma de narrativas clínicas presente nestes documentos electrónicos, faz com que seja difícil extrair e estruturar deles conhecimento clínico. Esta informação não estruturada limita o potencial dos PCE, uma vez que essa mesma informação, caso seja extraída e estruturada devidamente, pode servir para que as instituições de saúde possam efectuar actividades importantes com maior eficiência e sucesso, como por exemplo actividades de pesquisa, sumarização, apoio à decisão, análises estatísticas, suporte a decisões de gestão e de investigação. Este tipo de actividades apenas podem ser feitas com sucesso caso a informação clínica não estruturada presente nos PCE seja devidamente extraída, estruturada e processada em conhecimento clínico. Habitualmente, esta extração é realizada manualmente pelos profissionais médicos, o que não é eficiente e é susceptível a erros. Esta dissertação pretende então propôr uma solução para este problema, ao utilizar técnicas de Tradução Automática (TA) da língua portuguesa para a língua inglesa, Processamento de Linguagem Natural (PLN) e Extração de Informação (EI). O objectivo é desenvolver um sistema protótipo de módulos em série que utilize estas técnicas, possibilitando a extração de conhecimento clínico, de uma forma automática, de informação clínica não estruturada presente nos PCE de um hospital português. O principal objetivo é ajudar os PCE a atingirem todo o seu potencial em termos de conhecimento clínico que contêm e consequentemente ajudar o hospital português em questão envolvido nesta dissertação, demonstrando também que este sistema protótipo e esta abordagem podem potencialmente ser aplicados a outros hospitais, mesmo que não sejam de língua portuguesa.2019-03-13T14:31:30Z2021-03-13T00:00:00Z2018-11-13T00:00:00Z2018-11-132018-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfapplication/octet-streamhttp://hdl.handle.net/10071/17591TID:202099873engLamy, Manuel Maria Vilela Pestana de Mourainfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:44:52Zoai:repositorio.iscte-iul.pt:10071/17591Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:21:21.041560Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Extracting clinical knowledge from electronic medical records |
title |
Extracting clinical knowledge from electronic medical records |
spellingShingle |
Extracting clinical knowledge from electronic medical records Lamy, Manuel Maria Vilela Pestana de Moura Information extraction Knowledge extraction Machine translation Natural language processing Text mining Engenharia informática Dados médicos Processamento da linguagem Processamento da informação |
title_short |
Extracting clinical knowledge from electronic medical records |
title_full |
Extracting clinical knowledge from electronic medical records |
title_fullStr |
Extracting clinical knowledge from electronic medical records |
title_full_unstemmed |
Extracting clinical knowledge from electronic medical records |
title_sort |
Extracting clinical knowledge from electronic medical records |
author |
Lamy, Manuel Maria Vilela Pestana de Moura |
author_facet |
Lamy, Manuel Maria Vilela Pestana de Moura |
author_role |
author |
dc.contributor.author.fl_str_mv |
Lamy, Manuel Maria Vilela Pestana de Moura |
dc.subject.por.fl_str_mv |
Information extraction Knowledge extraction Machine translation Natural language processing Text mining Engenharia informática Dados médicos Processamento da linguagem Processamento da informação |
topic |
Information extraction Knowledge extraction Machine translation Natural language processing Text mining Engenharia informática Dados médicos Processamento da linguagem Processamento da informação |
description |
As the adoption of Electronic Medical Records (EMRs) rises in the healthcare institutions, these resources’ importance increases due to all clinical information they contain about patients. However, the unstructured information in the form of clinical narratives present in these records makes it hard to extract and structure useful clinical knowledge. This unstructured information limits the potential of the EMRs because the clinical information these records contain can be used to perform essential tasks inside healthcare institutions such as searching, summarization, decision support and statistical analysis, as well as be used to support management decisions or serve for research. These tasks can only be done if the unstructured clinical information from the narratives is appropriately extracted, structured and processed in clinical knowledge. Usually, this information extraction and structuration in clinical knowledge is performed manually by healthcare practitioners, which is not efficient and is error-prone. This research aims to propose a solution to this problem, by using Machine Translation (MT) from the Portuguese language to the English language, Natural Language Processing (NLP) and Information Extraction (IE) techniques. With the help of these techniques, the goal is to develop a prototype pipeline modular system that can extract clinical knowledge from unstructured clinical information contained in Portuguese EMRs, in an automated way, in order to help EMRs to fulfil their potential and consequently help the Portuguese hospital involved in this research. This research also intends to show that this generic prototype system and approach can potentially be applied to other hospitals, even if they don’t use the Portuguese language. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-11-13T00:00:00Z 2018-11-13 2018-09 2019-03-13T14:31:30Z 2021-03-13T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10071/17591 TID:202099873 |
url |
http://hdl.handle.net/10071/17591 |
identifier_str_mv |
TID:202099873 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf application/octet-stream |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134774696083456 |