Constructing Large Scale Cohort for Clinical Study on Heart Failure with Electronic Health Record in Regional Healthcare Platform:Challenges and Strategies in Data Reuse
|
摘要
Regional healthcare platforms collect clinical data from hospitals in specific areas for the purpose of healthcare management. It is a common requirement to reuse the data for clinical research. However, we have to face challenges like the inconsistence of terminology in electronic health records(EHR) and the complexities in data quality and data formats in regional healthcare platform. In this paper, we propose methodology and process on constructing large scale cohorts which forms the basis of causality and comparative effectiveness relationship in epidemiology. We firstly constructed a Chinese terminology knowledge graph to deal with the diversity of vocabularies on regional platform. Secondly, we built special disease case repositories(i.e., heart failure repository) that utilize the graph to search the related patients and to normalize the data. Based on the requirements of the clinical research which aimed to explore the effectiveness of taking statin on 180-days readmission in patients with heart failure, we built a large-scale retrospective cohort with 29647 cases of heart failure patients from the heart failure repository. After the propensity score matching, the study group(n=6346) and the control group(n=6346) with parallel clinical characteristics were acquired. Logistic regression analysis showed that taking statins had a negative correlation with 180-days readmission in heart failure patients. This paper presents the workflow and application example of big data mining based on regional EHR data.
Regional healthcare platforms collect clinical data from hospitals in specific areas for the purpose of healthcare management. It is a common requirement to reuse the data for clinical research. However, we have to face challenges like the inconsistence of terminology in electronic health records(EHR) and the complexities in data quality and data formats in regional healthcare platform. In this paper, we propose methodology and process on constructing large scale cohorts which forms the basis of causality and comparative effectiveness relationship in epidemiology. We firstly constructed a Chinese terminology knowledge graph to deal with the diversity of vocabularies on regional platform. Secondly, we built special disease case repositories(i.e., heart failure repository) that utilize the graph to search the related patients and to normalize the data. Based on the requirements of the clinical research which aimed to explore the effectiveness of taking statin on 180-days readmission in patients with heart failure, we built a large-scale retrospective cohort with 29647 cases of heart failure patients from the heart failure repository. After the propensity score matching, the study group(n=6346) and the control group(n=6346) with parallel clinical characteristics were acquired. Logistic regression analysis showed that taking statins had a negative correlation with 180-days readmission in heart failure patients. This paper presents the workflow and application example of big data mining based on regional EHR data.
Regional healthcare platforms collect clinical data from hospitals in specific areas for the purpose of healthcare management. It is a common requirement to reuse the data for clinical research. However, we have to face challenges like the inconsistence of terminology in electronic health records(EHR) and the complexities in data quality and data formats in regional healthcare platform. In this paper, we propose methodology and process on constructing large scale cohorts which forms the basis of causality and comparative effectiveness relationship in epidemiology. We firstly constructed a Chinese terminology knowledge graph to deal with the diversity of vocabularies on regional platform. Secondly, we built special disease case repositories(i.e., heart failure repository) that utilize the graph to search the related patients and to normalize the data. Based on the requirements of the clinical research which aimed to explore the effectiveness of taking statin on 180-days readmission in patients with heart failure, we built a large-scale retrospective cohort with 29647 cases of heart failure patients from the heart failure repository. After the propensity score matching, the study group(n=6346) and the control group(n=6346) with parallel clinical characteristics were acquired. Logistic regression analysis showed that taking statins had a negative correlation with 180-days readmission in heart failure patients. This paper presents the workflow and application example of big data mining based on regional EHR data.
引文
1.ShahAD,LangenbergC,RapsomanikiE,etal.Type 2 diabetesandincidenceofcardiovasculardiseases:a cohort study in 1.9 million people.Lancet Diabetes Endocrinol2015;3(2):105-13.doi:10.1016/S2213-8587(14)70219-0.
2.Denaxas SC,George J,Herrett E,et al.Data resource profile:cardiovasculardiseaseresearchusinglinked bespokestudiesandelectronichealthrecords(CALIBER).IntJEpidemiol2012;41(6):1625-38.doi:10.1093/ije/dys188.
3.Abrah?oMTF,NobreMRC,GutierrezMA.Amethod forcohortselectionofcardiovasculardiseaserecords fromanelectronichealthrecordsystem.IntJMed Inform2017;102:138-49.doi:10.1016/j.ijmedinf.2017.03.015.
4.JinB,CheC,LiuZ,etal.Predictingtheriskof heartfailurewithEHRsequentialdatamodeling.IEEEAccess2018;6:9256-61.doi:10.1109/access.2017.2789324.
5.LeiL,ZhouY,ZhaiJ,etal.Aneffectivepatientrepresentationlearningfortime-seriespredictiontasks basedonEHRs.2018IEEEInternationalConference onBioinformaticsandBiomedicine(BIBM).2018Dec 3-6;Madric,Spain.IEEE;2018.p885-92.doi:10.1109/bibm.2018.8621542.
6.RajkomarA,OrenE,ChenK,etal.Scalableandaccuratedeeplearningwithelectronichealthrecords.Digital Med 2018;1(1):18.doi:10.1038/s41746-018-0029-1.
7.DonnellyK.SNOMED-CT:theadvancedterminology andcodingsystemforeHealth.StudHealthTechnol Inform 2006;121:279-90.
8.Mcdonald CJ,Huff SM,Suico JG,et al.LOINC,a universalstandardforidentifyinglaboratoryobservations:a 5-year update.Clin Chem 2003;49(4):624-33.doi:10.1373/49.4.624.
9.De Franco E,Flanagan SE,Houghton JA,et al.The effect of early,comprehensive genomic testing on clinical care in neonatal diabetes:an international cohort study.Lancet 2015;386(9997):957-63.doi:10.1016/s0140-6736(15)60098-8.
10.Bashi N,Karunanithi M,Fatehi F,et al.Remote monitoringofpatientswithheartfailure:anoverviewof systematic reviews.J Med Internet Res 2017;19(1):e18.doi:10.2196/jmir.6571.
11.Kudyba SP.Healthcare informatics:improving efficiencythroughtechnology,analytics,andmanagement.Boca Raton,FL,USA:CRC Press;2016.doi:10.1201/b21424-6.
12.Nakamura M,Wakabayashi G,Miyasaka Y,et al.Multicentercomparativestudyoflaparoscopicandopen distalpancreatectomyusingpropensityscore‐matching.J Hepatobiliary Pancreat Sci 2015;22(10):731-6.doi:10.1002/jhbp.268.
13.Ruan T,Wang M,Sun J,et al.An automatic approach forconstructingaknowledgebaseofsymptomsin Chinese.JBiomedSemantics2017;8(1):33.doi:10.1186/s13326-017-0145-x.
14.Qiu J,Wang Q,Zhou Y,et al.Fast and accurate recognition of Chinese clinical named entities with residual dilated convolutions.2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).2018Dec 3-6;Madrid,Spain.IEEE;2018.p935-42.doi:10.1109/bibm.2018.8621360.
15.XuJ,GanL,ChengM,etal.UnsupervisedmedicalentityrecognitionandlinkinginChineseonline medicaltext.JHealthcEng2018;2548537.doi:10.1155/2018/2548537.
16.LiZ,YangZ,ShenC,etal.Integratingshortestdependencypathandsentencesequenceintoadeep learningframeworkforrelationextractioninclinical text.BMC Med Inform Decis Mak 2019;19(Suppl 1):22.doi:10.1186/s12911-019-0736-9.
17.Bodenreider O.The unified medical language system(UMLS):integratingbiomedicalterminology.Nucleic Acids Res 2004;32(suppl 1):D267-70.doi:10.1093/nar/gkh061.
18.LoweHJ,BarnettGO.Understandingandusingthe medicalsubjectheadings(MeSH)vocabularytoperform literature searches.JAMA 1994;271(14):1103-8.
19.Sherman RE,Anderson SA,Dal Pan GJ,et al.Real-worldevidence—whatisitandwhatcanittellus.N Engl J Med 2016;375(23):2293-7.doi:10.1056/NEJMsb1609216.
20.SamwaldM,JentzschA,BoutonC,etal.Linked opendrugdataforpharmaceuticalresearchand development.JCheminform2011;3(1):19.doi:10.1186/1758-2946-3-19.
21.HearstMA.Automaticacquisitionofhyponymsfrom largetextcorpora.Proceedingsofthe14thconference on Computational linguistics.1992 Aug.23-28;Nantes,France.Stroudsburg,PA,USA:Association for computational linguistics;1992.2:p539-45.doi:10.3115/992133.992154.
22.BelleauF,NolinMA,TourignyN,etal.Bio2RDF:towardsamashuptobuildbioinformaticsknowledge systems.JBiomedInform2008;41(5):706-16.doi:10.1016/j.jbi.2008.03.004.
23.ZhangJ,WangQ,ZhangZ,etal.Aneffectivestandardizationmethodforthelabindicatorsinregional medicalhealthplatformusingN-gramsandstacking.2018IEEEInternationalConferenceonBioinformaticsandBiomedicine(BIBM).2018Dec3-6;Madrid,Spain.IEEE,2018.p.1602-9.doi:10.1109/bibm.2018.8621274.
24.Wang Q,Wang T,Xu C.Using a knowledge graph for hypernymydetectionbetweenChinesesymptoms.2018TenthInternationalConferenceonAdvanced Computational Intelligence(ICACI).2018 Mar 29-31;Xiamen China.IEEE,2018.p.601-6.doi:10.1109/icaci.2018.8377528.
25.WangQ,XuC,ZhouY,etal.Anattention-basedBiGRU-CapsNetmodelforhypernymydetectionbetweencompoundentities.2018IEEEInternational Conference on Bioinformatics and Biomedicine(BIBM).2018Dec3-6;Madrid,Spain.IEEE,2018.p.1031-5.doi:10.1109/bibm.2018.8621408.
26.RichessonRL,AndrewsJE,KrischerJP.Useof SNOMED CT to represent clinical research data:a semanticcharacterizationofdataitemsoncasereport formsinvasculitisresearch.JAmMedInformAssoc2006;13(5):536-46.doi:10.1197/jamia.M2093.
27.WeiskopfNG,WengC.Methodsanddimensionsof electronichealthrecorddataqualityassessment:enablingreuseforclinicalresearch.JAmMedInformAssoc2013;20(1):144-51.doi:10.1136/amiajnl-2011-000681.
28.YeQ,ZhaoL,RuanT,etal.Usabilityresearchof regionalhealthdataforclinicalefficacyanalysis.BigDataRes2018;4(3):2018026.Chinese.doi:10.11959/j.issn.2096-0271.2018026.
29.ElwynG,O’connorA,StaceyD,etal.Developing aqualitycriteriaframeworkforpatientdecision aids:onlineinternationalDelphiconsensusprocess.BMJ2006;333(7565):417.doi:10.1136/bmj.38926.629329.ae.
30.Brown BB.Delphi process:a methodology used for the elicitationofopinionsofexperts.SantaMonica,CA,USA:RAND Corporation;1968.https://www.rand.org/pubs/papers/P3925.html.Accessed May 16,2019.
31.Bauersachs J,Galuppo P,Fraccarollo D,et al.Improvementofleftventricularremodelingandfunctionby hydroxymethylglutaryl coenzyme a reductase inhibition with cerivastatin in rats with heart failure after myocardial infarction.Circulation 2001;104(9):982-5.
32.CaliendoM,KopeinigS.Somepracticalguidancefor theimplementationofpropensityscorematching.J EcoSurvey2008;22(1):31-72.doi:10.1007/3-540-28708-6_4.
33.Lunt M.Selecting an appropriate caliper can be essentialforachievinggoodbalancewithpropensityscore matching.Am J Epidemiol 2013;179(2):226-35.doi:10.1093/aje/kwt212.
2.Denaxas SC,George J,Herrett E,et al.Data resource profile:cardiovasculardiseaseresearchusinglinked bespokestudiesandelectronichealthrecords(CALIBER).IntJEpidemiol2012;41(6):1625-38.doi:10.1093/ije/dys188.
3.Abrah?oMTF,NobreMRC,GutierrezMA.Amethod forcohortselectionofcardiovasculardiseaserecords fromanelectronichealthrecordsystem.IntJMed Inform2017;102:138-49.doi:10.1016/j.ijmedinf.2017.03.015.
4.JinB,CheC,LiuZ,etal.Predictingtheriskof heartfailurewithEHRsequentialdatamodeling.IEEEAccess2018;6:9256-61.doi:10.1109/access.2017.2789324.
5.LeiL,ZhouY,ZhaiJ,etal.Aneffectivepatientrepresentationlearningfortime-seriespredictiontasks basedonEHRs.2018IEEEInternationalConference onBioinformaticsandBiomedicine(BIBM).2018Dec 3-6;Madric,Spain.IEEE;2018.p885-92.doi:10.1109/bibm.2018.8621542.
6.RajkomarA,OrenE,ChenK,etal.Scalableandaccuratedeeplearningwithelectronichealthrecords.Digital Med 2018;1(1):18.doi:10.1038/s41746-018-0029-1.
7.DonnellyK.SNOMED-CT:theadvancedterminology andcodingsystemforeHealth.StudHealthTechnol Inform 2006;121:279-90.
8.Mcdonald CJ,Huff SM,Suico JG,et al.LOINC,a universalstandardforidentifyinglaboratoryobservations:a 5-year update.Clin Chem 2003;49(4):624-33.doi:10.1373/49.4.624.
9.De Franco E,Flanagan SE,Houghton JA,et al.The effect of early,comprehensive genomic testing on clinical care in neonatal diabetes:an international cohort study.Lancet 2015;386(9997):957-63.doi:10.1016/s0140-6736(15)60098-8.
10.Bashi N,Karunanithi M,Fatehi F,et al.Remote monitoringofpatientswithheartfailure:anoverviewof systematic reviews.J Med Internet Res 2017;19(1):e18.doi:10.2196/jmir.6571.
11.Kudyba SP.Healthcare informatics:improving efficiencythroughtechnology,analytics,andmanagement.Boca Raton,FL,USA:CRC Press;2016.doi:10.1201/b21424-6.
12.Nakamura M,Wakabayashi G,Miyasaka Y,et al.Multicentercomparativestudyoflaparoscopicandopen distalpancreatectomyusingpropensityscore‐matching.J Hepatobiliary Pancreat Sci 2015;22(10):731-6.doi:10.1002/jhbp.268.
13.Ruan T,Wang M,Sun J,et al.An automatic approach forconstructingaknowledgebaseofsymptomsin Chinese.JBiomedSemantics2017;8(1):33.doi:10.1186/s13326-017-0145-x.
14.Qiu J,Wang Q,Zhou Y,et al.Fast and accurate recognition of Chinese clinical named entities with residual dilated convolutions.2018 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).2018Dec 3-6;Madrid,Spain.IEEE;2018.p935-42.doi:10.1109/bibm.2018.8621360.
15.XuJ,GanL,ChengM,etal.UnsupervisedmedicalentityrecognitionandlinkinginChineseonline medicaltext.JHealthcEng2018;2548537.doi:10.1155/2018/2548537.
16.LiZ,YangZ,ShenC,etal.Integratingshortestdependencypathandsentencesequenceintoadeep learningframeworkforrelationextractioninclinical text.BMC Med Inform Decis Mak 2019;19(Suppl 1):22.doi:10.1186/s12911-019-0736-9.
17.Bodenreider O.The unified medical language system(UMLS):integratingbiomedicalterminology.Nucleic Acids Res 2004;32(suppl 1):D267-70.doi:10.1093/nar/gkh061.
18.LoweHJ,BarnettGO.Understandingandusingthe medicalsubjectheadings(MeSH)vocabularytoperform literature searches.JAMA 1994;271(14):1103-8.
19.Sherman RE,Anderson SA,Dal Pan GJ,et al.Real-worldevidence—whatisitandwhatcanittellus.N Engl J Med 2016;375(23):2293-7.doi:10.1056/NEJMsb1609216.
20.SamwaldM,JentzschA,BoutonC,etal.Linked opendrugdataforpharmaceuticalresearchand development.JCheminform2011;3(1):19.doi:10.1186/1758-2946-3-19.
21.HearstMA.Automaticacquisitionofhyponymsfrom largetextcorpora.Proceedingsofthe14thconference on Computational linguistics.1992 Aug.23-28;Nantes,France.Stroudsburg,PA,USA:Association for computational linguistics;1992.2:p539-45.doi:10.3115/992133.992154.
22.BelleauF,NolinMA,TourignyN,etal.Bio2RDF:towardsamashuptobuildbioinformaticsknowledge systems.JBiomedInform2008;41(5):706-16.doi:10.1016/j.jbi.2008.03.004.
23.ZhangJ,WangQ,ZhangZ,etal.Aneffectivestandardizationmethodforthelabindicatorsinregional medicalhealthplatformusingN-gramsandstacking.2018IEEEInternationalConferenceonBioinformaticsandBiomedicine(BIBM).2018Dec3-6;Madrid,Spain.IEEE,2018.p.1602-9.doi:10.1109/bibm.2018.8621274.
24.Wang Q,Wang T,Xu C.Using a knowledge graph for hypernymydetectionbetweenChinesesymptoms.2018TenthInternationalConferenceonAdvanced Computational Intelligence(ICACI).2018 Mar 29-31;Xiamen China.IEEE,2018.p.601-6.doi:10.1109/icaci.2018.8377528.
25.WangQ,XuC,ZhouY,etal.Anattention-basedBiGRU-CapsNetmodelforhypernymydetectionbetweencompoundentities.2018IEEEInternational Conference on Bioinformatics and Biomedicine(BIBM).2018Dec3-6;Madrid,Spain.IEEE,2018.p.1031-5.doi:10.1109/bibm.2018.8621408.
26.RichessonRL,AndrewsJE,KrischerJP.Useof SNOMED CT to represent clinical research data:a semanticcharacterizationofdataitemsoncasereport formsinvasculitisresearch.JAmMedInformAssoc2006;13(5):536-46.doi:10.1197/jamia.M2093.
27.WeiskopfNG,WengC.Methodsanddimensionsof electronichealthrecorddataqualityassessment:enablingreuseforclinicalresearch.JAmMedInformAssoc2013;20(1):144-51.doi:10.1136/amiajnl-2011-000681.
28.YeQ,ZhaoL,RuanT,etal.Usabilityresearchof regionalhealthdataforclinicalefficacyanalysis.BigDataRes2018;4(3):2018026.Chinese.doi:10.11959/j.issn.2096-0271.2018026.
29.ElwynG,O’connorA,StaceyD,etal.Developing aqualitycriteriaframeworkforpatientdecision aids:onlineinternationalDelphiconsensusprocess.BMJ2006;333(7565):417.doi:10.1136/bmj.38926.629329.ae.
30.Brown BB.Delphi process:a methodology used for the elicitationofopinionsofexperts.SantaMonica,CA,USA:RAND Corporation;1968.https://www.rand.org/pubs/papers/P3925.html.Accessed May 16,2019.
31.Bauersachs J,Galuppo P,Fraccarollo D,et al.Improvementofleftventricularremodelingandfunctionby hydroxymethylglutaryl coenzyme a reductase inhibition with cerivastatin in rats with heart failure after myocardial infarction.Circulation 2001;104(9):982-5.
32.CaliendoM,KopeinigS.Somepracticalguidancefor theimplementationofpropensityscorematching.J EcoSurvey2008;22(1):31-72.doi:10.1007/3-540-28708-6_4.
33.Lunt M.Selecting an appropriate caliper can be essentialforachievinggoodbalancewithpropensityscore matching.Am J Epidemiol 2013;179(2):226-35.doi:10.1093/aje/kwt212.