Identifying data set specific duplicate patient records

Update Item Information
Publication Type poster
School or College School of Medicine
Department Biomedical Informatics
Creator DuVall, Scott L.
Title Identifying data set specific duplicate patient records
Date 2009
Description Probabilistic models are commonly used in the identification of duplicate records. These methods are usually more accurate than deterministic methods, but are exponentially more computationally complex. Thus to make them computationally feasible, they rely on deterministic blocking strategies. This project investigates how machine learning methods can be used to automatically determine an optimal blocking strategy using duplicate records already identified.
Type Text; Image
Publisher University of Utah
Subject Probabilistic models; Duplicate records; Duplicate patient records; Trapeze Interactive Poster
Subject LCSH Medical informatics; Medical records -- Data processing
Language eng
Bibliographic Citation DuVall, S. (2009). Identifying data set specific duplicate patient records. University of Utah.
Rights Management (c)Scott DuVall
Format Medium application/pdf
Format Extent 180,197 bytes
Identifier ir-main,11054
ARK ark:/87278/s6zk61cp
Setname ir_uspace
ID 707874
Reference URL https://collections.lib.utah.edu/ark:/87278/s6zk61cp