Kraus S, Prokosch HU (2019)
Publication Type: Book chapter / Article in edited volumes
Publication year: 2019
Publisher: IOS Press
Edited Volumes: ICT for Health Science Research - Proceedings of the EFMI 2019 Special Topic Conference
Series: Studies in Health Technology and Informatics
City/Town: Amsterdam
Book Volume: 258
Pages Range: 36-40
DOI: 10.3233/978-1-61499-959-1-36
The Arden Syntax is a standard for clinical decision support functions in the form of Medical Logic Modules (MLMs). While the data type system of the early versions was limited to flat lists, later versions introduced an object type, supporting complex data structures, even up to entire electronic medical records (EMRs). Such objects are static insofar as their structure cannot be modified at MLM runtime. University Hospital Erlangen uses an experimental Arden Syntax version termed PLAIN, which provides an integrated mapper for arbitrary data structures, including entire EMRs. To facilitate knowledge encoding and reduce MLM complexity, we searched for a way to complement patient records with precalculated data items. We modified the object data type in two ways. The first was to include a statement for the explicit creation of new attributes; the second was to implicitly create an attribute whenever a value is assigned to a previously non-existing attribute. As a proof of concept, we complemented the ventilation section of every accessed EMR with a patient-individual recommendation for the expiratory tidal volume. A means to extend the structure of an object at runtime provides several advantages. The precalculated data items need no longer be calculated by the MLMs themselves, which reduces complexity and facilitates code maintenance. This might be beneficial not only for clinical decision support, but also with respect to the use of Arden Syntax language constructs for phenotyping queries, as well as with respect to the frequently required preprocessing of EMR data.
APA:
Kraus, S., & Prokosch, H.-U. (2019). Complementing medical records with precalculated data items to facilitate decision support and phenotyping. In Amnon Shabo, Inge Madsen, Thomas M. Deserno, Matthias Lobe, Kristiina Hayrinen, Hans-Ulrich Prokosch, Fernando Martin-Sanchez, Klaus-Hendrik Wolf (Eds.), ICT for Health Science Research - Proceedings of the EFMI 2019 Special Topic Conference. (pp. 36-40). Amsterdam: IOS Press.
MLA:
Kraus, Stefan, and Hans-Ulrich Prokosch. "Complementing medical records with precalculated data items to facilitate decision support and phenotyping." ICT for Health Science Research - Proceedings of the EFMI 2019 Special Topic Conference. Ed. Amnon Shabo, Inge Madsen, Thomas M. Deserno, Matthias Lobe, Kristiina Hayrinen, Hans-Ulrich Prokosch, Fernando Martin-Sanchez, Klaus-Hendrik Wolf, Amsterdam: IOS Press, 2019. 36-40.
BibTeX: Download