Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas

Background: A significant proportion of the clinical record is in free text format, making it difficult to extract key information and make secondary use of patient data. Automatic detection of information within narratives initially requires humans, following specific protocols and rules, to ident...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Báez,Pablo, Villena,Fabián, Zúñiga,Karen, Jones,Natalia, Fernández,Gustavo, Durán,Manuel, Dunstan,Jocelyn
Lenguaje:	Spanish / Castilian
Publicado:	Sociedad Médica de Santiago 2021
Materias:	Data Curation Data Mining Medical Informatics Natural Language Processing Supervised Machine Learning
Acceso en línea:	http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0034-98872021000701014
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:scielo:S0034-98872021000701014
record_format	dspace
spelling	oai:scielo:S0034-988720210007010142021-11-04Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradasBáez,PabloVillena,FabiánZúñiga,KarenJones,NataliaFernández,GustavoDurán,ManuelDunstan,Jocelyn Data Curation Data Mining Medical Informatics Natural Language Processing Supervised Machine Learning Background: A significant proportion of the clinical record is in free text format, making it difficult to extract key information and make secondary use of patient data. Automatic detection of information within narratives initially requires humans, following specific protocols and rules, to identify medical entities of interest. Aim: To build a linguistic resource of annotated medical entities on texts produced in Chilean hospitals. Material and Methods: A clinical corpus was constructed using 150 referrals in public hospitals. Three annotators identified six medical entities: clinical findings, diagnoses, body parts, medications, abbreviations, and family members. An annotation scheme was designed, and an iterative approach to train the annotators was applied. The F1-Score metric was used to assess the progress of the annotator's agreement during their training. Results: An average F1-Score of 0.73 was observed at the beginning of the project. After the training period, it increased to 0.87. Annotation of clinical findings and body parts showed significant discrepancy, while abbreviations, medications, and family members showed high agreement. Conclusions: A linguistic resource with annotated medical entities on texts produced in Chilean hospitals was built and made available, working with annotators related to medicine. The iterative annotation approach allowed us to improve performance metrics. The corpus and annotation protocols will be released to the research community.info:eu-repo/semantics/openAccessSociedad Médica de SantiagoRevista médica de Chile v.149 n.7 20212021-07-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0034-98872021000701014es10.4067/s0034-98872021000701014
institution	Scielo Chile
collection	Scielo Chile
language	Spanish / Castilian
topic	Data Curation Data Mining Medical Informatics Natural Language Processing Supervised Machine Learning
spellingShingle	Data Curation Data Mining Medical Informatics Natural Language Processing Supervised Machine Learning Báez,Pablo Villena,Fabián Zúñiga,Karen Jones,Natalia Fernández,Gustavo Durán,Manuel Dunstan,Jocelyn Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
description	Background: A significant proportion of the clinical record is in free text format, making it difficult to extract key information and make secondary use of patient data. Automatic detection of information within narratives initially requires humans, following specific protocols and rules, to identify medical entities of interest. Aim: To build a linguistic resource of annotated medical entities on texts produced in Chilean hospitals. Material and Methods: A clinical corpus was constructed using 150 referrals in public hospitals. Three annotators identified six medical entities: clinical findings, diagnoses, body parts, medications, abbreviations, and family members. An annotation scheme was designed, and an iterative approach to train the annotators was applied. The F1-Score metric was used to assess the progress of the annotator's agreement during their training. Results: An average F1-Score of 0.73 was observed at the beginning of the project. After the training period, it increased to 0.87. Annotation of clinical findings and body parts showed significant discrepancy, while abbreviations, medications, and family members showed high agreement. Conclusions: A linguistic resource with annotated medical entities on texts produced in Chilean hospitals was built and made available, working with annotators related to medicine. The iterative annotation approach allowed us to improve performance metrics. The corpus and annotation protocols will be released to the research community.
author	Báez,Pablo Villena,Fabián Zúñiga,Karen Jones,Natalia Fernández,Gustavo Durán,Manuel Dunstan,Jocelyn
author_facet	Báez,Pablo Villena,Fabián Zúñiga,Karen Jones,Natalia Fernández,Gustavo Durán,Manuel Dunstan,Jocelyn
author_sort	Báez,Pablo
title	Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
title_short	Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
title_full	Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
title_fullStr	Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
title_full_unstemmed	Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
title_sort	construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas
publisher	Sociedad Médica de Santiago
publishDate	2021
url	http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0034-98872021000701014
work_keys_str_mv	AT baezpablo construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas AT villenafabian construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas AT zunigakaren construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas AT jonesnatalia construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas AT fernandezgustavo construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas AT duranmanuel construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas AT dunstanjocelyn construccionderecursosdetextoparalaidentificacionautomaticadeinformacionclinicaennarrativasnoestructuradas
_version_	1718437214346543104

Construcción de recursos de texto para la identificación automática de información clínica en narrativas no estructuradas

Ejemplares similares