Steven G Johnson1, Stuart Speedie1, Gyorgy Simon1, Vipin Kumar2, Bonnie L Westra3. 1. University of Minnesota, Institute for Health Informatics. 2. University of Minnesota , Department of Computer Science. 3. University of Minnesota, Institute for Health Informatics; University of Minnesota, School of Nursing.
Abstract
OBJECTIVE: The goal of this study is to apply an ontology based assessment process to electronic health record (EHR) data and determine its usefulness in characterizing data quality for calculating an example eMeasure (CMS178). METHODS: The process uses a data quality ontology that references separate data quality, domain and task ontologies to compute measures based on proportions of constraints that are satisfied. These quantities indicate how well the data conforms to the domain and how well it fits the task. RESULTS: The process was performed on a de-identified 200,000 encounter sample from a hospital EHR. CodingConsistency was poor (44%) but DomainConsistency (97%) and TaskRelevance (95%) were very good. Improvements in the data quality Measures correlated with improvements in the eMeasure. CONCLUSION: This approach can encourage the development of new detailed Domain ontologies that can be reused for data quality purposes across different organizations' EHR data. Automating the data quality assessment process using this method can enable sharing of data quality metrics that may aid in making research results that use EHR data more transparent and reproducible.
OBJECTIVE: The goal of this study is to apply an ontology based assessment process to electronic health record (EHR) data and determine its usefulness in characterizing data quality for calculating an example eMeasure (CMS178). METHODS: The process uses a data quality ontology that references separate data quality, domain and task ontologies to compute measures based on proportions of constraints that are satisfied. These quantities indicate how well the data conforms to the domain and how well it fits the task. RESULTS: The process was performed on a de-identified 200,000 encounter sample from a hospital EHR. CodingConsistency was poor (44%) but DomainConsistency (97%) and TaskRelevance (95%) were very good. Improvements in the data quality Measures correlated with improvements in the eMeasure. CONCLUSION: This approach can encourage the development of new detailed Domain ontologies that can be reused for data quality purposes across different organizations' EHR data. Automating the data quality assessment process using this method can enable sharing of data quality metrics that may aid in making research results that use EHR data more transparent and reproducible.
Entities:
Keywords:
Data quality; data validation and verification; electronic health record; ontology
Authors: J Marc Overhage; Patrick B Ryan; Christian G Reich; Abraham G Hartzema; Paul E Stang Journal: J Am Med Inform Assoc Date: 2011-10-28 Impact factor: 4.497
Authors: Richard Platt; Ryan M Carnahan; Jeffrey S Brown; Elizabeth Chrischilles; Lesley H Curtis; Sean Hennessy; Jennifer C Nelson; Judith A Racoosin; Melissa Robb; Sebastian Schneeweiss; Sengwee Toh; Mark G Weiner Journal: Pharmacoepidemiol Drug Saf Date: 2012-01 Impact factor: 2.890
Authors: Charles Safran; Meryl Bloomrosen; W Edward Hammond; Steven Labkoff; Suzanne Markel-Fox; Paul C Tang; Don E Detmer Journal: J Am Med Inform Assoc Date: 2006-10-31 Impact factor: 4.497
Authors: William R Hersh; Mark G Weiner; Peter J Embi; Judith R Logan; Philip R O Payne; Elmer V Bernstam; Harold P Lehmann; George Hripcsak; Timothy H Hartzog; James J Cimino; Joel H Saltz Journal: Med Care Date: 2013-08 Impact factor: 2.983
Authors: Timothy S Chang; Ashwin Buchipudi; Gregg C Fonarow; Michael A Pfeffer; Jennifer S Singer; Eric M Cheng Journal: Appl Clin Inform Date: 2019-06-19 Impact factor: 2.342
Authors: Franck Diaz-Garelli; Andrew Long; Michael P Bancks; Alain G Bertoni; Adhithya Narayanan; Brian J Wells Journal: AMIA Annu Symp Proc Date: 2022-02-21
Authors: Franck Diaz-Garelli; Roy Strowd; Virginia L Lawson; Maria E Mayorga; Brian J Wells; Thomas W Lycan; Umit Topaloglu Journal: JCO Clin Cancer Inform Date: 2020-06