Show simple item record  

dc.contributor.authorPeng, Mingkaien_NZ
dc.contributor.authorSundararajan, Vijayaen_NZ
dc.contributor.authorWilliamson, Tyleren_NZ
dc.contributor.authorMinty, Evan P.en_NZ
dc.contributor.authorSmith, Tony C.en_NZ
dc.contributor.authorDoktorchik, Chelsea T.A.en_NZ
dc.contributor.authorQuan, Hudeen_NZ
dc.coverage.spatialUnited Statesen_NZ
dc.date.accessioned2019-07-05T03:20:51Z
dc.date.available2018-03en_NZ
dc.date.available2019-07-05T03:20:51Z
dc.date.issued2018en_NZ
dc.identifier.citationPeng, M., Sundararajan, V., Williamson, T., Minty, E. P., Smith, T. C., Doktorchik, C. T. A., & Quan, H. (2018). Exploration of association rule mining for coding consistency and completeness assessment in inpatient administrative health data. Journal of Biomedical Informatics, 79, 41–47. https://doi.org/10.1016/j.jbi.2018.02.001en
dc.identifier.urihttps://hdl.handle.net/10289/12688
dc.description.abstractOBJECTIVE: Data quality assessment is a challenging facet for research using coded administrative health data. Current assessment approaches are time and resource intensive. We explored whether association rule mining (ARM) can be used to develop rules for assessing data quality. MATERIALS AND METHODS: We extracted 2013 and 2014 records from the hospital discharge abstract database (DAD) for patients between the ages of 55 and 65 from five acute care hospitals in Alberta, Canada. The ARM was conducted using the 2013 DAD to extract rules with support ≥0.0019 and confidence ≥0.5 using the bootstrap technique, and tested in the 2014 DAD. The rules were compared against the method of coding frequency and assessed for their ability to detect error introduced by two kinds of data manipulation: random permutation and random deletion. RESULTS: The association rules generally had clear clinical meanings. Comparing 2014 data to 2013 data (both original), there were 3 rules with a confidence difference >0.1, while coding frequency difference of codes in the right hand of rules was less than 0.004. After random permutation of 50% of codes in the 2014 data, average rule confidence dropped from 0.72 to 0.27 while coding frequency remained unchanged. Rule confidence decreased with the increase of coding deletion, as expected. Rule confidence was more sensitive to code deletion compared to coding frequency, with slope of change ranging from 1.7 to 184.9 with a median of 9.1. CONCLUSION: The ARM is a promising technique to assess data quality. It offers a systematic way to derive coding association rules hidden in data, and potentially provides a sensitive and efficient method of assessing data quality compared to standard methods.en_NZ
dc.format.mimetypeapplication/pdf
dc.language.isoenen_NZ
dc.rightsThis is an author’s accepted version of an article published in the journal: Journal of Biomedical Informatics. ©2018 Elsevier.
dc.subjectAssociation rule miningen_NZ
dc.subjectCoding completenessen_NZ
dc.subjectCoding inconsistencyen_NZ
dc.subjectDiagnosis codeen_NZ
dc.subjectInpatient administrative health dataen_NZ
dc.subjectInternational classification of diseaseen_NZ
dc.subjectAgeden_NZ
dc.subjectAlbertaen_NZ
dc.subjectAlgorithmsen_NZ
dc.subjectClinical Codingen_NZ
dc.subjectComputer Simulationen_NZ
dc.subjectData Miningen_NZ
dc.subjectDatabases, Factualen_NZ
dc.subjectFemaleen_NZ
dc.subjectHospitalizationen_NZ
dc.subjectHospitalsen_NZ
dc.subjectHumansen_NZ
dc.subjectInpatientsen_NZ
dc.subjectInternational Classification of Diseasesen_NZ
dc.subjectMaleen_NZ
dc.subjectMedical Informaticsen_NZ
dc.subjectMiddle Ageden_NZ
dc.subjectPatient Dischargeen_NZ
dc.subjectReproducibility of Resultsen_NZ
dc.titleExploration of association rule mining for coding consistency and completeness assessment in inpatient administrative health data.en_NZ
dc.typeJournal Article
dc.identifier.doi10.1016/j.jbi.2018.02.001en_NZ
dc.relation.isPartOfJournal of Biomedical Informaticsen_NZ
pubs.begin-page41
pubs.elements-id220738
pubs.end-page47
pubs.publication-statusPublisheden_NZ
pubs.volume79en_NZ
dc.identifier.eissn1532-0480en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record