Natural Language Processing for Rapid Response to Emergent Diseases: Case Study of Calcium Channel Blockers and Hypertension in the COVID-19 Pandemic.
COVID-19
electronic health records
emergent disease
informatics
medication information
natural language processing
public health
response
Journal
Journal of medical Internet research
ISSN: 1438-8871
Titre abrégé: J Med Internet Res
Pays: Canada
ID NLM: 100959882
Informations de publication
Date de publication:
14 Aug 2020
14 Aug 2020
Historique:
received:
02
06
2020
accepted:
26
07
2020
revised:
02
07
2020
pubmed:
8
8
2020
medline:
22
8
2020
entrez:
8
8
2020
Statut:
epublish
Résumé
A novel disease poses special challenges for informatics solutions. Biomedical informatics relies for the most part on structured data, which require a preexisting data or knowledge model; however, novel diseases do not have preexisting knowledge models. In an emergent epidemic, language processing can enable rapid conversion of unstructured text to a novel knowledge model. However, although this idea has often been suggested, no opportunity has arisen to actually test it in real time. The current coronavirus disease (COVID-19) pandemic presents such an opportunity. The aim of this study was to evaluate the added value of information from clinical text in response to emergent diseases using natural language processing (NLP). We explored the effects of long-term treatment by calcium channel blockers on the outcomes of COVID-19 infection in patients with high blood pressure during in-patient hospital stays using two sources of information: data available strictly from structured electronic health records (EHRs) and data available through structured EHRs and text mining. In this multicenter study involving 39 hospitals, text mining increased the statistical power sufficiently to change a negative result for an adjusted hazard ratio to a positive one. Compared to the baseline structured data, the number of patients available for inclusion in the study increased by 2.95 times, the amount of available information on medications increased by 7.2 times, and the amount of additional phenotypic information increased by 11.9 times. In our study, use of calcium channel blockers was associated with decreased in-hospital mortality in patients with COVID-19 infection. This finding was obtained by quickly adapting an NLP pipeline to the domain of the novel disease; the adapted pipeline still performed sufficiently to extract useful information. When that information was used to supplement existing structured data, the sample size could be increased sufficiently to see treatment effects that were not previously statistically detectable.
Sections du résumé
BACKGROUND
A novel disease poses special challenges for informatics solutions. Biomedical informatics relies for the most part on structured data, which require a preexisting data or knowledge model; however, novel diseases do not have preexisting knowledge models. In an emergent epidemic, language processing can enable rapid conversion of unstructured text to a novel knowledge model. However, although this idea has often been suggested, no opportunity has arisen to actually test it in real time. The current coronavirus disease (COVID-19) pandemic presents such an opportunity.
OBJECTIVE
The aim of this study was to evaluate the added value of information from clinical text in response to emergent diseases using natural language processing (NLP).
METHODS
We explored the effects of long-term treatment by calcium channel blockers on the outcomes of COVID-19 infection in patients with high blood pressure during in-patient hospital stays using two sources of information: data available strictly from structured electronic health records (EHRs) and data available through structured EHRs and text mining.
RESULTS
In this multicenter study involving 39 hospitals, text mining increased the statistical power sufficiently to change a negative result for an adjusted hazard ratio to a positive one. Compared to the baseline structured data, the number of patients available for inclusion in the study increased by 2.95 times, the amount of available information on medications increased by 7.2 times, and the amount of additional phenotypic information increased by 11.9 times.
CONCLUSIONS
In our study, use of calcium channel blockers was associated with decreased in-hospital mortality in patients with COVID-19 infection. This finding was obtained by quickly adapting an NLP pipeline to the domain of the novel disease; the adapted pipeline still performed sufficiently to extract useful information. When that information was used to supplement existing structured data, the sample size could be increased sufficiently to see treatment effects that were not previously statistically detectable.
Identifiants
pubmed: 32759101
pii: v22i8e20773
doi: 10.2196/20773
pmc: PMC7431235
doi:
Substances chimiques
Calcium Channel Blockers
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e20773Investigateurs
Pierre-Yves Ancel
(PY)
Alain Bauchet
(A)
Nathanaël Beeker
(N)
Vincent Benoit
(V)
Mélodie Bernaux
(M)
Ali Bellamine
(A)
Romain Bey
(R)
Aurélie Bourmaud
(A)
Stéphane Breant
(S)
Anita Burgun
(A)
Fabrice Carrat
(F)
Charlotte Caucheteux
(C)
Julien Champ
(J)
Sylvie Cormont
(S)
Christel Daniel
(C)
Julien Dubiel
(J)
Catherine Duclos
(C)
Loic Esteve
(L)
Marie Frank
(M)
Nicolas Garcelon
(N)
Alexandre Gramfort
(A)
Nicolas Griffon
(N)
Olivier Grisel
(O)
Martin Guilbaud
(M)
Claire Hassen-Khodja
(C)
François Hemery
(F)
Martin Hilka
(M)
Anne Sophie Jannot
(AS)
Jerome Lambert
(J)
Richard Layese
(R)
Judith Leblanc
(J)
Léo Lebouter
(L)
Guillaume Lemaitre
(G)
Damien Leprovost
(D)
Ivan Lerner
(I)
Kankoe Levi Sallah
(KL)
Aurélien Maire
(A)
Marie-France Mamzer
Patricia Martel
(P)
Arthur Mensch
(A)
Thomas Moreau
(T)
Antoine Neuraz
(A)
Nina Orlova
(N)
Nicolas Paris
(N)
Bastien Rance
(B)
Hélène Ravera
(H)
Antoine Rozes
(A)
Elisa Salamanca
(E)
Arnaud Sandrin
(A)
Patricia Serre
(P)
Xavier Tannier
(X)
Jean-Marc Treluyer
(JM)
Damien van Gysel
(D)
Gaël Varoquaux
(G)
Jill Jen Vie
(J)
Maxime Wack
(M)
Perceval Wajsburt
(P)
Demian Wassermann
(D)
Eric Zapletal
(E)
Informations de copyright
©Antoine Neuraz, Ivan Lerner, William Digan, Nicolas Paris, Rosy Tsopra, Alice Rogier, David Baudoin, Kevin Bretonnel Cohen, Anita Burgun, Nicolas Garcelon, Bastien Rance, AP-HP/Universities/INSERM COVID-19 Research Collaboration; AP-HP COVID CDR Initiative. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 14.08.2020.
Références
Stud Health Technol Inform. 2015;216:574-8
pubmed: 26262116
Methods Inf Med. 1993 Aug;32(4):281-91
pubmed: 8412823
Ann Intern Med. 2012 Jan 3;156(1 Pt 1):11-8
pubmed: 22213490
J Am Med Inform Assoc. 2017 May 1;24(3):607-613
pubmed: 28339516
Health Serv Res. 2016 Apr;51(2):790-811
pubmed: 26293167