Reconciliation of concurrently applied clinical practice guidelines using constraint logic programming

Szymon Wilk, Martin Michalowski, Marisela Mainegra Hing, Wojtek Michalowski, Ken Farion

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

This paper describes a novel methodological approach to reconciling points of contention (inconsistencies related to adverse and contradicting actions) when concurrently using multiple clinical practice guidelines (CPGs). The need to address these inconsistencies arises when a patient with comorbidity (the presence of one or more diseases in addition to a primary one) has to be managed according to different treatment regimens. We explain how to construct a formal guideline model using Constraint Logic Programming (CLP) and illustrate it with an example. We also present a procedure for mitigating points of contention that may arise when solving a constructed model given available patient information. The proposed procedure is conducted automatically and it employs mitigation operators that encapsulate clinical knowledge and define possible modifications to the model. The use of the mitigation procedure is demonstrated in a clinical scenario.

Original languageEnglish (US)
Title of host publicationProceedings of the 6th International Symposium on Health Informatics and Bioinformatics, HIBIT 2011
Pages33-40
Number of pages8
DOIs
StatePublished - 2011
Event6th International Symposium on Health Informatics and Bioinformatics, HIBIT 2011 - Izmir, Turkey
Duration: May 2 2011May 5 2011

Publication series

NameProceedings of the 6th International Symposium on Health Informatics and Bioinformatics, HIBIT 2011

Other

Other6th International Symposium on Health Informatics and Bioinformatics, HIBIT 2011
Country/TerritoryTurkey
CityIzmir
Period5/2/115/5/11

Fingerprint

Dive into the research topics of 'Reconciliation of concurrently applied clinical practice guidelines using constraint logic programming'. Together they form a unique fingerprint.

Cite this