Text-Based Identification of Herpes Zoster Ophthalmicus With Ocular Involvement in the Electronic Health Record: A Population-Based Study.
herpes zoster ophthalmicus
natural language processing
retrospective cohort study
shingles
Journal
Open forum infectious diseases
ISSN: 2328-8957
Titre abrégé: Open Forum Infect Dis
Pays: United States
ID NLM: 101637045
Informations de publication
Date de publication:
Feb 2021
Feb 2021
Historique:
received:
06
10
2020
accepted:
29
12
2020
entrez:
12
2
2021
pubmed:
13
2
2021
medline:
13
2
2021
Statut:
epublish
Résumé
Diagnosis codes are inadequate for accurately identifying herpes zoster ophthalmicus (HZO). Manual review of medical records is expensive and time-consuming, resulting in a lack of population-based data on HZO. We conducted a retrospective cohort study, including 87 673 patients aged ≥50 years who had a new HZ diagnosis and associated antiviral prescription between 2010 and 2018. We developed and validated an automated natural language processing (NLP) algorithm to identify HZO with ocular involvement (ocular HZO). We compared the characteristics of NLP-identified ocular HZO, nonocular HZO, and non-HZO cases among HZ patients and identified the factors associated with ocular HZO among HZ patients. The NLP algorithm achieved 94.9% sensitivity and 94.2% specificity in identifying ocular HZO cases. Among 87 673 incident HZ cases, the proportion identified as ocular HZO was 9.0% (n = 7853) by NLP and 2.3% (n = 1988) by The NLP algorithm achieved high accuracy and can be used in large population-based studies to identify ocular HZO, avoiding labor-intensive chart review. Age, sex, and race were strongly associated with ocular HZO among HZ patients. We should consider these risk factors when planning for zoster vaccination.
Sections du résumé
BACKGROUND
BACKGROUND
Diagnosis codes are inadequate for accurately identifying herpes zoster ophthalmicus (HZO). Manual review of medical records is expensive and time-consuming, resulting in a lack of population-based data on HZO.
METHODS
METHODS
We conducted a retrospective cohort study, including 87 673 patients aged ≥50 years who had a new HZ diagnosis and associated antiviral prescription between 2010 and 2018. We developed and validated an automated natural language processing (NLP) algorithm to identify HZO with ocular involvement (ocular HZO). We compared the characteristics of NLP-identified ocular HZO, nonocular HZO, and non-HZO cases among HZ patients and identified the factors associated with ocular HZO among HZ patients.
RESULTS
RESULTS
The NLP algorithm achieved 94.9% sensitivity and 94.2% specificity in identifying ocular HZO cases. Among 87 673 incident HZ cases, the proportion identified as ocular HZO was 9.0% (n = 7853) by NLP and 2.3% (n = 1988) by
CONCLUSIONS
CONCLUSIONS
The NLP algorithm achieved high accuracy and can be used in large population-based studies to identify ocular HZO, avoiding labor-intensive chart review. Age, sex, and race were strongly associated with ocular HZO among HZ patients. We should consider these risk factors when planning for zoster vaccination.
Identifiants
pubmed: 33575426
doi: 10.1093/ofid/ofaa652
pii: ofaa652
pmc: PMC7863871
doi:
Types de publication
Journal Article
Langues
eng
Pagination
ofaa652Informations de copyright
© The Author(s) 2021. Published by Oxford University Press on behalf of Infectious Diseases Society of America.
Références
N Engl J Med. 2013 Jul 18;369(3):255-63
pubmed: 23863052
Arch Ophthalmol. 1983 Jan;101(1):42-5
pubmed: 6600391
Ophthalmology. 2016 Jul;123(7):1469-75
pubmed: 27067924
J Infect Dis. 2020 Aug 4;222(5):798-806
pubmed: 31830250
Med Clin North Am. 2013 Jul;97(4):503-22, ix
pubmed: 23809711
BMJ. 2014 May 13;348:g2911
pubmed: 25134101
Ophthalmology. 2020 Mar;127(3):324-330
pubmed: 31668889
Ophthalmology. 2013 Mar;120(3):451-456
pubmed: 23207173
JAMA Ophthalmol. 2014 Mar;132(3):326-31
pubmed: 24370901
Am Fam Physician. 2002 Nov 1;66(9):1723-30
pubmed: 12449270
Mayo Clin Proc. 2017 Dec;92(12):1806-1821
pubmed: 29202939
JAMA Ophthalmol. 2016 Sep 1;134(9):1001-6
pubmed: 27387135
Lancet Infect Dis. 2004 Jan;4(1):26-33
pubmed: 14720565
Fam Pract. 2002 Oct;19(5):471-5
pubmed: 12356697
J Am Acad Dermatol. 2007 Dec;57(6 Suppl):S130-5
pubmed: 18021864
Clin Exp Ophthalmol. 2019 Jan;47(1):7-14
pubmed: 29920898
Open Forum Infect Dis. 2020 Jan 09;7(1):ofaa005
pubmed: 32010734
BMJ Open. 2014 Jun 10;4(6):e004833
pubmed: 24916088
Arthritis Care Res (Hoboken). 2014 Nov;66(11):1740-8
pubmed: 24664671
Mayo Clin Proc. 2013 Jun;88(6):562-70
pubmed: 23664666
Am J Epidemiol. 2011 Nov 1;174(9):1054-61
pubmed: 21920944
Perm J. 2012 Summer;16(3):37-41
pubmed: 23012597
Cornea. 2017 Jun;36(6):740-742
pubmed: 28410358
Am J Med. 2017 Jan;130(1):21-26
pubmed: 27644149
Neurology. 2010 Mar 9;74(10):792-7
pubmed: 20200348
Br J Ophthalmol. 2016 Mar;100(3):312-4
pubmed: 26178905
Ophthalmology. 2008 Feb;115(2 Suppl):S3-12
pubmed: 18243930
BMJ. 2019 Jan 17;364:k5234
pubmed: 30655269