Long-term epilepsy outcome dynamics revealed by natural language processing of clinic notes.
clinical informatics
electronic health record
seizure freedom
seizure frequency
Journal
Epilepsia
ISSN: 1528-1167
Titre abrégé: Epilepsia
Pays: United States
ID NLM: 2983306R
Informations de publication
Date de publication:
07 2023
07 2023
Historique:
revised:
26
04
2023
received:
16
12
2022
accepted:
26
04
2023
pmc-release:
01
07
2024
medline:
13
7
2023
pubmed:
28
4
2023
entrez:
28
4
2023
Statut:
ppublish
Résumé
Electronic medical records allow for retrospective clinical research with large patient cohorts. However, epilepsy outcomes are often contained in free text notes that are difficult to mine. We recently developed and validated novel natural language processing (NLP) algorithms to automatically extract key epilepsy outcome measures from clinic notes. In this study, we assessed the feasibility of extracting these measures to study the natural history of epilepsy at our center. We applied our previously validated NLP algorithms to extract seizure freedom, seizure frequency, and date of most recent seizure from outpatient visits at our epilepsy center from 2010 to 2022. We examined the dynamics of seizure outcomes over time using Markov model-based probability and Kaplan-Meier analyses. Performance of our algorithms on classifying seizure freedom was comparable to that of human reviewers (algorithm F Our findings demonstrate that epilepsy outcome measures can be extracted accurately from unstructured clinical note text using NLP. At our tertiary center, the disease course often followed a remitting and relapsing pattern. This method represents a powerful new tool for clinical research with many potential uses and extensions to other clinical questions.
Identifiants
pubmed: 37114472
doi: 10.1111/epi.17633
pmc: PMC10523917
mid: NIHMS1896516
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1900-1909Subventions
Organisme : NINDS NIH HHS
ID : DP1 NS122038
Pays : United States
Organisme : NINDS NIH HHS
ID : K23NS121520
Pays : United States
Organisme : NIH HHS
ID : 1DP1 OD029758
Pays : United States
Organisme : NINDS NIH HHS
ID : K23 NS126495
Pays : United States
Organisme : NINDS NIH HHS
ID : K23 NS121520
Pays : United States
Organisme : NINDS NIH HHS
ID : R56 NS099348
Pays : United States
Informations de copyright
© 2023 International League Against Epilepsy.
Références
J Am Med Inform Assoc. 2022 Apr 13;29(5):873-881
pubmed: 35190834
PLoS One. 2019 Jul 22;14(7):e0219854
pubmed: 31329615
Epilepsia. 2017 May;58(5):901-906
pubmed: 28374950
Brain. 2006 Mar;129(Pt 3):617-24
pubmed: 16401617
Epilepsia. 2011 Mar;52(3):619-26
pubmed: 21269287
BMJ Open. 2019 Apr 1;9(4):e023232
pubmed: 30940752
Seizure. 2021 Feb;85:138-144
pubmed: 33461032
BMJ Open. 2013 Jan 03;3(1):
pubmed: 23293244
J Neurol Neurosurg Psychiatry. 2019 Nov;90(11):1276-1285
pubmed: 31248935
Seizure. 2022 Oct;101:48-51
pubmed: 35882104
Neurology. 2022 Apr 5;98(14):583-590
pubmed: 35379694
N Engl J Med. 2001 Aug 2;345(5):311-8
pubmed: 11484687
Neurology. 2018 Oct 30;91(18):829-836
pubmed: 30282773
Epilepsy Res. 2004 Jun;60(1):31-40
pubmed: 15279868
Epilepsia. 2015 Jan;56(1):40-8
pubmed: 25431231
Epilepsia. 1979 Dec;20(6):729-37
pubmed: 499118
Brain. 2014 Dec;137(Pt 12):3213-22
pubmed: 25338950
PLoS One. 2017 Dec 21;12(12):e0190035
pubmed: 29267375
Circ Cardiovasc Qual Outcomes. 2010 Mar;3(2):188-95
pubmed: 20179265
Arch Neurol. 2009 Oct;66(10):1233-9
pubmed: 19822778
Epilepsy Behav. 2021 Oct 11;124:108330
pubmed: 34649159
Lancet. 1995 Jul 15;346(8968):140-4
pubmed: 7603228
Epilepsia. 2023 Feb;64(2):292-305
pubmed: 36462150
Med Care. 1983 Aug;21(8):821-9
pubmed: 6888031
N Engl J Med. 2000 Feb 3;342(5):314-9
pubmed: 10660394