دورية أكاديمية
أعرض في EDS

Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching.

التفاصيل البيبلوغرافية
العنوان: Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching.
المؤلفون: Siegersma KR; Laboratory of Experimental Cardiology, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands.; Department of Cardiology, Amsterdam University Medical Centers, VU University Medical Center, Amsterdam, Netherlands., Evers M; Laboratory of Experimental Cardiology, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands., Bots SH; Laboratory of Experimental Cardiology, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands., Groepenhoff F; Laboratory of Experimental Cardiology, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands.; Central Diagnostic Laboratory, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands., Appelman Y; Department of Cardiology, Amsterdam University Medical Centers, VU University Medical Center, Amsterdam, Netherlands., Hofstra L; Department of Cardiology, Amsterdam University Medical Centers, VU University Medical Center, Amsterdam, Netherlands.; Cardiology Centers of the Netherlands, Utrecht, Netherlands., Tulevski II; Cardiology Centers of the Netherlands, Utrecht, Netherlands., Somsen GA; Cardiology Centers of the Netherlands, Utrecht, Netherlands., den Ruijter HM; Laboratory of Experimental Cardiology, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands., Spruit M; Department of Public Health and Primary Care, Leiden University Medical Center, Leiden University, Leiden, Netherlands.; Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands., Onland-Moret NC; Department of Epidemiology, Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands.
المصدر: JMIR medical informatics [JMIR Med Inform] 2022 Jan 25; Vol. 10 (1), pp. e31063. Date of Electronic Publication: 2022 Jan 25.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101645109 Publication Model: Electronic Cited Medium: Print ISSN: 2291-9694 (Print) NLM ISO Abbreviation: JMIR Med Inform Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: Toronto : JMIR Publications, [2013]-
مستخلص: Background: Knowledge about adverse drug reactions (ADRs) in the population is limited because of underreporting, which hampers surveillance and assessment of drug safety. Therefore, gathering accurate information that can be retrieved from clinical notes about the incidence of ADRs is of great relevance. However, manual labeling of these notes is time-consuming, and automatization can improve the use of free-text clinical notes for the identification of ADRs. Furthermore, tools for language processing in languages other than English are not widely available.
Objective: The aim of this study is to design and evaluate a method for automatic extraction of medication and Adverse Drug Reaction Identification in Clinical Notes (ADRIN).
Methods: Dutch free-text clinical notes (N=277,398) and medication registrations (N=499,435) from the Cardiology Centers of the Netherlands database were used. All clinical notes were used to develop word embedding models. Vector representations of word embedding models and string matching with a medical dictionary (Medical Dictionary for Regulatory Activities [MedDRA]) were used for identification of ADRs and medication in a test set of clinical notes that were manually labeled. Several settings, including search area and punctuation, could be adjusted in the prototype to evaluate the optimal version of the prototype.
Results: The ADRIN method was evaluated using a test set of 988 clinical notes written on the stop date of a drug. Multiple versions of the prototype were evaluated for a variety of tasks. Binary classification of ADR presence achieved the highest accuracy of 0.84. Reduced search area and inclusion of punctuation improved performance, whereas incorporation of the MedDRA did not improve the performance of the pipeline.
Conclusions: The ADRIN method and prototype are effective in recognizing ADRs in Dutch clinical notes from cardiac diagnostic screening centers. Surprisingly, incorporation of the MedDRA did not result in improved identification on top of word embedding models. The implementation of the ADRIN tool may help increase the identification of ADRs, resulting in better care and saving substantial health care costs.
(©Klaske R Siegersma, Maxime Evers, Sophie H Bots, Floor Groepenhoff, Yolande Appelman, Leonard Hofstra, Igor I Tulevski, G Aernout Somsen, Hester M den Ruijter, Marco Spruit, N Charlotte Onland-Moret. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 25.01.2022.)
References: Br J Clin Pharmacol. 2019 Jul;85(7):1507-1515. (PMID: 30941789)
J Am Med Inform Assoc. 2003 Jul-Aug;10(4):339-50. (PMID: 12668691)
AMIA Annu Symp Proc. 2018 Apr 16;2017:411-420. (PMID: 29854105)
Int J Med Inform. 2019 Aug;128:62-70. (PMID: 31160013)
J Am Med Inform Assoc. 2001 May-Jun;8(3):254-66. (PMID: 11320070)
Ann Pharmacother. 2008 Jul;42(7):1017-25. (PMID: 18594048)
J Am Med Inform Assoc. 2020 Jun 1;27(6):901-907. (PMID: 32388549)
Drug Saf. 2006;29(5):385-96. (PMID: 16689555)
NPJ Digit Med. 2021 Feb 26;4(1):37. (PMID: 33637859)
J Am Med Inform Assoc. 2013 Sep-Oct;20(5):947-53. (PMID: 23703825)
J Biomed Semantics. 2018 Mar 30;9(1):12. (PMID: 29602312)
J Am Med Inform Assoc. 2020 Jan 1;27(1):47-55. (PMID: 31334805)
PLoS One. 2015 Aug 14;10(8):e0134208. (PMID: 26273830)
Qual Saf Health Care. 2007 Apr;16(2):132-4. (PMID: 17403760)
Epidemiology. 2014 May;25(3):470-1. (PMID: 24713887)
Lancet Oncol. 2016 May;17(5):e209-19. (PMID: 27301048)
Drug Saf. 2018 Jul;41(7):665-675. (PMID: 29520645)
JAMA. 2013 Apr 3;309(13):1351-2. (PMID: 23549579)
J Biomed Inform. 2018 Nov;87:12-20. (PMID: 30217670)
JMIR Med Inform. 2019 Apr 27;7(2):e12239. (PMID: 31066697)
Drug Saf. 1999 Feb;20(2):109-17. (PMID: 10082069)
J Biomed Inform. 2019;100S:100057. (PMID: 34384583)
J Pharmacol Pharmacother. 2013 Dec;4(Suppl 1):S73-7. (PMID: 24347988)
BMC Cardiovasc Disord. 2021 Jun 10;21(1):287. (PMID: 34112101)
J Allergy Clin Immunol. 2020 Feb;145(2):463-469. (PMID: 31883846)
فهرسة مساهمة: Keywords: adverse drug reactions; clinical notes; word embeddings
تواريخ الأحداث: Date Created: 20220125 Latest Revision: 20220329
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC8826143
DOI: 10.2196/31063
PMID: 35076407
قاعدة البيانات: MEDLINE
الوصف
تدمد:2291-9694
DOI:10.2196/31063