Comparison of Supervised Machine Learning and Probabilistic Approaches for Record Linkage
If you need an accessible version of this item, please submit a remediation request.
Date
2020-03-25
Language
American English
Embargo Lift Date
Department
Committee Members
Degree
Degree Year
Department
Grantor
Journal Title
Journal ISSN
Volume Title
Found At
AMIA Informatics summit 2019 Conference Proceedings.
Abstract
Record linkage is vital to prevent fragmentation of patient data. Machine learning approaches present considerable potential for record linkage. We compared the performance of three machine learning algorithms to an established probabilistic record linkage technique. Machine learning approaches exhibited results that were comparable, or statistically superior to the established probabilistic approach. It is unclear if the cost of manually reviewing datasets for supervised learning is justified by the performance improvements they yield.
Description
item.page.description.tableofcontents
item.page.relation.haspart
Cite As
McNutt, A.T., Grannis, S.J., Bo, N., Xu, H., Kasthurirathne, S. N.(2020, March). Comparison of Supervised Machine Learning and Probabilistic Approaches for Record Linkage. AMIA Informatics summit 2020 Conference Proceedings.
ISSN
Publisher
Series/Report
Sponsorship
Major
Extent
Identifier
Relation
Journal
Source
Alternative Title
Type
Presentation