Learning a Health Knowledge Graph from Electronic Medical Records

Abstract Demand for clinical decision support systems in medicine and self-diagnostic symptom checkers has substantially increased in recent years. Existing platforms rely on knowledge bases manually compiled through a labor-intensive process or automatically derived using simple pairwise statistics...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Maya Rotmensch, Yoni Halpern, Abdulhakim Tlimat, Steven Horng, David Sontag
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/5f64696401c341ff9c0a0acb8861ec01
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5f64696401c341ff9c0a0acb8861ec01
record_format	dspace
spelling	oai:doaj.org-article:5f64696401c341ff9c0a0acb8861ec012021-12-02T11:52:42ZLearning a Health Knowledge Graph from Electronic Medical Records10.1038/s41598-017-05778-z2045-2322https://doaj.org/article/5f64696401c341ff9c0a0acb8861ec012017-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-05778-zhttps://doaj.org/toc/2045-2322Abstract Demand for clinical decision support systems in medicine and self-diagnostic symptom checkers has substantially increased in recent years. Existing platforms rely on knowledge bases manually compiled through a labor-intensive process or automatically derived using simple pairwise statistics. This study explored an automated process to learn high quality knowledge bases linking diseases and symptoms directly from electronic medical records. Medical concepts were extracted from 273,174 de-identified patient records and maximum likelihood estimation of three probabilistic models was used to automatically construct knowledge graphs: logistic regression, naive Bayes classifier and a Bayesian network using noisy OR gates. A graph of disease-symptom relationships was elicited from the learned parameters and the constructed knowledge graphs were evaluated and validated, with permission, against Google’s manually-constructed knowledge graph and against expert physician opinions. Our study shows that direct and automated construction of high quality health knowledge graphs from medical records using rudimentary concept extraction is feasible. The noisy OR model produces a high quality knowledge graph reaching precision of 0.85 for a recall of 0.6 in the clinical evaluation. Noisy OR significantly outperforms all tested models across evaluation frameworks (p < 0.01).Maya RotmenschYoni HalpernAbdulhakim TlimatSteven HorngDavid SontagNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-11 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Maya Rotmensch Yoni Halpern Abdulhakim Tlimat Steven Horng David Sontag Learning a Health Knowledge Graph from Electronic Medical Records
description	Abstract Demand for clinical decision support systems in medicine and self-diagnostic symptom checkers has substantially increased in recent years. Existing platforms rely on knowledge bases manually compiled through a labor-intensive process or automatically derived using simple pairwise statistics. This study explored an automated process to learn high quality knowledge bases linking diseases and symptoms directly from electronic medical records. Medical concepts were extracted from 273,174 de-identified patient records and maximum likelihood estimation of three probabilistic models was used to automatically construct knowledge graphs: logistic regression, naive Bayes classifier and a Bayesian network using noisy OR gates. A graph of disease-symptom relationships was elicited from the learned parameters and the constructed knowledge graphs were evaluated and validated, with permission, against Google’s manually-constructed knowledge graph and against expert physician opinions. Our study shows that direct and automated construction of high quality health knowledge graphs from medical records using rudimentary concept extraction is feasible. The noisy OR model produces a high quality knowledge graph reaching precision of 0.85 for a recall of 0.6 in the clinical evaluation. Noisy OR significantly outperforms all tested models across evaluation frameworks (p < 0.01).
format	article
author	Maya Rotmensch Yoni Halpern Abdulhakim Tlimat Steven Horng David Sontag
author_facet	Maya Rotmensch Yoni Halpern Abdulhakim Tlimat Steven Horng David Sontag
author_sort	Maya Rotmensch
title	Learning a Health Knowledge Graph from Electronic Medical Records
title_short	Learning a Health Knowledge Graph from Electronic Medical Records
title_full	Learning a Health Knowledge Graph from Electronic Medical Records
title_fullStr	Learning a Health Knowledge Graph from Electronic Medical Records
title_full_unstemmed	Learning a Health Knowledge Graph from Electronic Medical Records
title_sort	learning a health knowledge graph from electronic medical records
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/5f64696401c341ff9c0a0acb8861ec01
work_keys_str_mv	AT mayarotmensch learningahealthknowledgegraphfromelectronicmedicalrecords AT yonihalpern learningahealthknowledgegraphfromelectronicmedicalrecords AT abdulhakimtlimat learningahealthknowledgegraphfromelectronicmedicalrecords AT stevenhorng learningahealthknowledgegraphfromelectronicmedicalrecords AT davidsontag learningahealthknowledgegraphfromelectronicmedicalrecords
_version_	1718394925996834816

Learning a Health Knowledge Graph from Electronic Medical Records

Ejemplares similares