Linkage of Hospital Records and Death Certificates by a Search Engine and Machine Learning.

death certificates information storage and retrieval medical record linkage search engine supervised machine learning

Journal

JAMIA open
ISSN: 2574-2531
Titre abrégé: JAMIA Open
Pays: United States
ID NLM: 101730643

Informations de publication

Date de publication:
Jan 2021
Historique:
received: 15 12 2020
revised: 22 01 2021
accepted: 02 02 2021
entrez: 12 3 2021
pubmed: 13 3 2021
medline: 13 3 2021
Statut: epublish

Résumé

Vital status is of central importance to hospital clinical research. However, hospital information systems record only in-hospital death information. Recently, the French government released a publicly available dataset containing death-certificate data for over 25 million individuals. The objective of this study was to link French death certificates to the Bordeaux University Hospital records to complete the vital status information. Our linkage strategy was composed of a search engine to reduce the number of comparisons and machine-learning algorithms. The overall pipeline was evaluated by assembling a file containing 3,565 in-hospital deaths and 15,000 alive persons. The recall and precision of our linkage strategy were 97.5% and 99.97% for the upper threshold and 99.4% and 98.9% for the lower threshold, respectively. In this study, we demonstrated the feasibility of accurately linking hospital records with death certificates using a search engine and machine learning.

Identifiants

pubmed: 33709061
doi: 10.1093/jamiaopen/ooab005
pii: ooab005
pmc: PMC7935495
doi:

Banques de données

Dryad
['10.5061/dryad.1ns1rn8sj']

Types de publication

Journal Article

Langues

eng

Pagination

ooab005

Informations de copyright

© The Author(s) 2021. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Références

Am J Epidemiol. 1985 May;121(5):754-66
pubmed: 4014167
AMIA Annu Symp Proc. 2003;:259-63
pubmed: 14728174
Stat Med. 2017 Jul 20;36(16):2514-2521
pubmed: 28303597
AMIA Jt Summits Transl Sci Proc. 2015 Mar 25;2015:450-5
pubmed: 26306284
J Am Med Inform Assoc. 1997 May-Jun;4(3):233-7
pubmed: 9147342
BMC Med Inform Decis Mak. 2016 Oct 6;16(1):129
pubmed: 27716178
Int J Popul Data Sci. 2018 Jan 10;3(1):410
pubmed: 30533534
Cad Saude Publica. 2014 Aug;30(8):1623-32
pubmed: 25210903
Sci Data. 2019 Jan 08;6:180298
pubmed: 30620344
BMC Med Inform Decis Mak. 2020 Nov 9;20(1):289
pubmed: 33167998
Big Data Soc. 2017 Dec 5;4(2):2053951717745678
pubmed: 30381794

Auteurs

Sebastien Cossin (S)

CHU de Bordeaux, Pôle de Santé Publique, Service d'information Médicale, Informatique et Archivistique Médicales (IAM), Bordeaux F-33000, France.
Inserm, Bordeaux Population Health Research Center, Team ERIAS, University of Bordeaux, UMR 1219, Bordeaux F-33000, France.

Serigne Diouf (S)

CHU de Bordeaux, Pôle de Santé Publique, Service d'information Médicale, Informatique et Archivistique Médicales (IAM), Bordeaux F-33000, France.
Inserm, Bordeaux Population Health Research Center, Team ERIAS, University of Bordeaux, UMR 1219, Bordeaux F-33000, France.

Romain Griffier (R)

CHU de Bordeaux, Pôle de Santé Publique, Service d'information Médicale, Informatique et Archivistique Médicales (IAM), Bordeaux F-33000, France.
Inserm, Bordeaux Population Health Research Center, Team ERIAS, University of Bordeaux, UMR 1219, Bordeaux F-33000, France.

Philippine Le Barrois d'Orgeval (P)

CHU de Bordeaux, Pôle de Santé Publique, Service d'information Médicale, Informatique et Archivistique Médicales (IAM), Bordeaux F-33000, France.
Inserm, Bordeaux Population Health Research Center, Team ERIAS, University of Bordeaux, UMR 1219, Bordeaux F-33000, France.

Gayo Diallo (G)

Inserm, Bordeaux Population Health Research Center, Team ERIAS, University of Bordeaux, UMR 1219, Bordeaux F-33000, France.

Vianney Jouhet (V)

CHU de Bordeaux, Pôle de Santé Publique, Service d'information Médicale, Informatique et Archivistique Médicales (IAM), Bordeaux F-33000, France.
Inserm, Bordeaux Population Health Research Center, Team ERIAS, University of Bordeaux, UMR 1219, Bordeaux F-33000, France.

Classifications MeSH