A proposal for a LOINC automatic mapping support tool
Parole chiave:
Natural Language Processing, LOINC, Mapping support tool, text similarity, Clinical coding systemsAbstract
Clinical coding and classification systems are the lingua franca to overcome idiosyncrasies of the local informative systems. Among those required into the Italian EHR, LOINC aims to uniquely identify both clinical document types indexed into EHR registries and tests into laboratory reports. Its use requires that local test codes are mapped to the codes of the standard so that equivalent concepts are aligned and can be easily understood and reused by other systems. This mapping process is cost and time-consuming as involves for many hours domain experts to find the right association. Therefore, this paper aims to make a proposal for an automatic mapping tool to support domain experts in finding the correct LOINC code to map to, specifically customized on the Italian language, combining textual similarity techniques with new NLP models and taking advantage of the so-called "wisdom of the crowd".
Riferimenti bibliografici
Agenzia per l’Italia Digitale. 2022. “Fascicolo Sanitario Elettronico 2.0: pubblicate le Linee Guida per l’attuazione.” https://www.agid.gov.it/it/agenzia/stampa-e-comunicazione/notizie/2022/07/19/fascicolo-sanitario-elettronico-20-pubblicate-linee-guida-lattuazione.
Chiaravalloti, Maria Teresa, Mario Ciampi, Erika Pasceri, Mario Sicuranza, Giuseppe De Pietro, and Roberto Guarasci. 2015. “A model for realizing interoperable EHR systems in Italy.” In 15th International HL7 Interoperability Conference (IHIC 2015) Proceedings, 13−22, http://ihic2015.hl7cr.eu/Proceedings-web.pdf.
Dixon, Brian E., John Hook, and Daniel J. Vreeman. 2015. “Learning from the crowd in terminology mapping: the LOINC experience.” Lab Medicine 46 (2): 168–74.
Fidahussein, Mustafa, and Daniel J. Vreeman. 2014. “A corpus-based approach for automated LOINC mapping.” Journal of the American Medical Informatics Association 21 (1): 64–72.
Frassica, Joseph J. 2003. “Frequency of laboratory test utilization in the intensive care unit and its implications for large scale data collection efforts.” In AMIA Annual Symposium Proceedings, 844.
Lau, Lee Min, Kate Johnson, Kent Monson, Siew H. Lam, and Stanley M. Huff. 2000. “A method for the automated mapping of laboratory results to LOINC.” In AMIA Annual Symposium Proceedings, 472–76.
Parisi, Francesca, and Maria Teresa Chiaravalloti. 2018. “A set of NooJ Grammars to verify laboratory data correctness.” In Formalizing Natural Languages with NooJ 2018 and Its Natural Language Processing Applications, edited by Ignazio Mauro Mirto, Mario Monteleone, Max Silberztein, 155−66. Cham: Springer. DOI: https://doi.org/10.1007/978-3-030-10868-7_14.
Parr, Sharidan K., Matthew S. Shotwell, Alvin D. Jeffery, Thomas A. Lasko, and Michael E. Matheny. 2018. “Automated mapping of laboratory tests to LOINC codes using noisy labels in a national electronic health record system database.” Journal of the American Medical Informatics Association 25 (10): 1292−300. DOI: 10.1093/jamia/ocy110.
Regenstrief Institute, Inc. n.d. “LOINC Code Rankings.” Accessed November 25, 2022. http://loinc.org/usage/obs.
Silberztein, Max. 2015. La formalisation des langues, l’approche de NooJ. London : ISTE.
Vreeman, Daniel J., and Clement J. McDonald. 2005. “Automated mapping of local radiology terms to LOINC.” In AMIA Annual Symposium Proceedings, 769–73.
Vreeman, Daniel J., and Clement J. McDonald. 2006. “A comparison of Intelligent Mapper and document similarity scores for mapping local radiology terms to LOINC.” In AMIA Annual Symposium Proceedings, 809–13.
Wikipedia. 2022. “NooJ.” Last modified January 6, 2022. https://en.wikipedia.org/wiki/NooJ.
Zollo, Kenneth A., and Stanley M. Huff. 2000. “Automated mapping of observation codes using extensional definitions.” Journal of the American Medical Informatics Association 7 (6): 586–92.
Zunner, Christian, Thomas Bürkle, Hans-Ulrich Prokosch, and Thomas Ganslandt. 2013. “Mapping local laboratory interface terms to LOINC at a German university hospital using RELMA V.5: a semi-automated approach.” Journal of the American Medical Informatics Association 20 (2): 293–97.
##submission.downloads##
Pubblicato
Fascicolo
Sezione
Licenza
Copyright (c) 2022 Cacucci Editore
Questo lavoro è fornito con la licenza Creative Commons Attribuzione - Non commerciale - Condividi allo stesso modo 4.0 Internazionale.
