Noselli, M, Mason, D, Mohammed, MA et al. (1 more author) (2017) MonAT: a VisualWeb-based Tool to Profile Health Data Quality. In: Fred, A, Van den Broek, EL, Gamboa, H and Vaz, M, (eds.) Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2017). 10th International Conference on Health Informatics (HEALTHINF 2017), 21-23 Feb 2017, Porto, Portugal. SCITEPRESS , pp. 26-34. ISBN 978-989-758-213-4
Abstract
Electronic Health Records (EHRs) are an important asset for clinical research and decision making, but the utility of EHR data depends on its quality. In health, quality is typically investigated by using statistical methods to profile data. To complement established methods, we developed a web-based visualisation tool called MonAT Web Application (MonAT) for profiling the completeness and correctness of EHR. The tool was evaluated by four researchers using anthropometric data from the Born in Bradford Project (BiB Project), and this highlighted three advantages. The first was to understand how missingness varied across variables, and especially to do this for subsets of records. The second was to investigate whether certain variables for groups of records were sufficiently complete to be used in subsequent analysis. The third was to portray longitudinally the records for a given person, to improve outlier identification.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Keywords: | Data Quality, Visualization, Health Data, Longitudinal Data |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 18 Jan 2017 15:08 |
Last Modified: | 03 Aug 2017 10:43 |
Status: | Published |
Publisher: | SCITEPRESS |
Identification Number: | 10.5220/0006114200260034 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:110718 |