<p style="text-align:justify;">
<b>Objective</b> We address the problem of mapping local laboratory terminologies to the Logical Observation Identifiers Names and Codes (LOINC). We study different ontology matching algorithms and investigate how the probability of term combinations in LOINC helps to increase match quality and reduce manual effort.
<b>Materials and Methods</b> We propose two matching strategies namely full name and multi-part matching. The multi-part approach also considers the occurrence probability of combined concept parts. It can further recommend possible combinations of concept parts to allow more local terms to be mapped. Three real-world laboratory databases from Taiwanese hospitals are used to validate the proposed strategies with respect to different quality measures and execution runtime. A comparison to the commonly used tool RELMA Lab Auto Mapper (LAM) is also provided.
<b>Results</b> The new multi-part strategy yields the best match quality with F-measure values between 89% and 96%. It can automatically match 70-85% of the laboratory terminologies to LOINC. The recommendation step can further propose a mapping to (proposed) LOINC concepts for 9-20% of the local terminology concepts. On average, 91% of the local terminology concepts can be correctly mapped to existing or newly proposed LOINC concepts.
<b>Conclusion</b> The mapping quality of the multi-part strategy is significantly better than LAM. It enables domain experts to perform LOINC matching with little manual work. The probability of term combinations proved to be a valuable strategy to increase the quality of match results, to provide recommendations for proposed LOINC concepts, but also to decrease the run time for match processing.
</p>
<h2>Keywords</h2>
<ul>
<li>LOINC</li>
<li>Pre-coordination</li>
<li>Probability</li>
<li>Ontology Matching</li>
<li>Translation</li>
</ul>
<h2 id="bibtex_heading">BibTex</h2>
<pre id="bibtex_listing">
@article{lee2013multi,
title={A multi-part matching strategy for mapping LOINC with laboratory terminologies},
author={Lee, Li-Hui and Gro{\\ss}, Anika and Hartung, Michael and Liou, Der-Ming and Rahm, Erhard},
journal={Journal of the American Medical Informatics Association},
volume = {21},
pages={792–800},
year={2014},
publisher={BMJ Publishing Group Ltd}
}
</pre>
