Integration of NLP2FHIR Representation with Deep Learning Models for EHR Phenotyping: A Pilot Study on Obesity Datasets.
Journal
AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science
ISSN: 2153-4063
Titre abrégé: AMIA Jt Summits Transl Sci Proc
Pays: United States
ID NLM: 101539486
Informations de publication
Date de publication:
Historique:
entrez:
30
8
2021
pubmed:
31
8
2021
medline:
11
9
2021
Statut:
epublish
Résumé
HL7 Fast Healthcare Interoperability Resources (FHIR) is one of the current data standards for enabling electronic healthcare information exchange. Previous studies have shown that FHIR is capable of modeling both structured and unstructured data from electronic health records (EHRs). However, the capability of FHIR in enabling clinical data analytics has not been well investigated. The objective of the study is to demonstrate how FHIR-based representation of unstructured EHR data can be ported to deep learning models for text classification in clinical phenotyping. We leverage and extend the NLP2FHIR clinical data normalization pipeline and conduct a case study with two obesity datasets. We tested several deep learning-based text classifiers such as convolutional neural networks, gated recurrent unit, and text graph convolutional networks on both raw text and NLP2FHIR inputs. We found that the combination of NLP2FHIR input and text graph convolutional networks has the highest F1 score. Therefore, FHIR-based deep learning methods has the potential to be leveraged in supporting EHR phenotyping, making the phenotyping algorithms more portable across EHR systems and institutions.
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
410-419Subventions
Organisme : NIGMS NIH HHS
ID : R01 GM105688
Pays : United States
Organisme : NIBIB NIH HHS
ID : R56 EB028101
Pays : United States
Organisme : NHGRI NIH HHS
ID : U01 HG009450
Pays : United States
Informations de copyright
©2021 AMIA - All rights reserved.
Références
J Am Med Inform Assoc. 2014 Sep-Oct;21(5):824-32
pubmed: 24431333
J Am Med Inform Assoc. 2020 Dec 9;27(12):1921-1934
pubmed: 33040151
J Biomed Inform. 2014 Dec;52:28-35
pubmed: 24534443
Genet Med. 2013 Oct;15(10):761-71
pubmed: 23743551
J Am Med Inform Assoc. 2009 Jul-Aug;16(4):561-70
pubmed: 19390096
Yearb Med Inform. 2017 Aug;26(1):28-37
pubmed: 28480474
AMIA Jt Summits Transl Sci Proc. 2019 May 06;2019:809-818
pubmed: 31259038
Circ J. 2020 Jan 24;84(2):144-152
pubmed: 31866635
Nature. 2018 Oct;562(7726):203-209
pubmed: 30305743
ACM BCB. 2015 Sep;2015:258-267
pubmed: 28736769
BMC Med Inform Decis Mak. 2019 Apr 4;19(Suppl 3):78
pubmed: 30943974
NPJ Digit Med. 2018 May 8;1:18
pubmed: 31304302
J Am Med Inform Assoc. 2014 Sep-Oct;21(5):858-65
pubmed: 24637954
Stud Health Technol Inform. 2019 Aug 21;264:462-466
pubmed: 31437966
J Biomed Inform. 2019 Aug;96:103253
pubmed: 31325501
AMIA Jt Summits Transl Sci Proc. 2019 May 06;2019:145-152
pubmed: 31258966
J Biomed Inform. 2019 Nov;99:103310
pubmed: 31622801
BMC Med Inform Decis Mak. 2019 Apr 4;19(Suppl 3):71
pubmed: 30943960
J Biomed Inform. 2020 Feb;102:103361
pubmed: 31911172
J Am Med Inform Assoc. 2016 Sep;23(5):899-908
pubmed: 26911829
Neural Comput. 1997 Nov 15;9(8):1735-80
pubmed: 9377276
AMIA Jt Summits Transl Sci Proc. 2015 Mar 25;2015:147-51
pubmed: 26306258
J Am Med Inform Assoc. 2010 Sep-Oct;17(5):507-13
pubmed: 20819853
JAMIA Open. 2019 Oct 18;2(4):570-579
pubmed: 32025655
AMIA Annu Symp Proc. 2006;:1040
pubmed: 17238659
AMIA Annu Symp Proc. 2020 Mar 04;2019:755-764
pubmed: 32308871
Sci Data. 2016 May 24;3:160035
pubmed: 27219127
J Am Med Inform Assoc. 2011 Sep-Oct;18(5):580-7
pubmed: 21709161
J Am Med Inform Assoc. 2009 Jul-Aug;16(4):576-9
pubmed: 19390102
AMIA Jt Summits Transl Sci Proc. 2018 May 18;2017:74-83
pubmed: 29888045
J Am Med Inform Assoc. 2009 Jul-Aug;16(4):571-5
pubmed: 19390103
J Am Med Inform Assoc. 2009 Jul-Aug;16(4):596-600
pubmed: 19390098