TY - GEN
T1 - Clinical practice guidelines and comorbid diseases
T2 - 14th World Congress on Medical and Health Informatics, MEDINFO 2013
AU - Wilk, Szymon
AU - Michalowski, Martin
AU - Michalowski, Wojtek
AU - Farion, Ken
AU - Lin, Di
AU - Hing, Marisela Mainegra
AU - Mohapatra, Subhra
PY - 2013
Y1 - 2013
N2 - Managing a patient with comorbid diseases according to multiple clinical practice guidelines (CPGs) may result in adverse interactions that need to be mitigated (identified and addressed) so a safe therapy can be devised. However, mitigation poses both clinical and methodological challenges. It requires extensive domain knowledge and calls for advanced CPG models and efficient algorithms to process them. We respond to the above challenges by describing our algorithm that mitigates interactions between pairs of CPGs. The algorithm creates logical models of analyzed CPGs and uses constraint logic programming (CLP) together with domain knowledge, codified as interaction and revision operators, to process them. Logical CPG models are transformed into CLP-CPG models that are solved to find a safe therapy. We represent these CLP-CPG models using MiniZinc, a standard language for CLP models. As motivation and illustration of our mitigation algorithm we use a clinical case study describing a patient managed for hypertension and deep vein thrombosis according to two individual CPGs. We apply the algorithm to this scenario and present MiniZinc representations of the constructed CLP-CPG models.
AB - Managing a patient with comorbid diseases according to multiple clinical practice guidelines (CPGs) may result in adverse interactions that need to be mitigated (identified and addressed) so a safe therapy can be devised. However, mitigation poses both clinical and methodological challenges. It requires extensive domain knowledge and calls for advanced CPG models and efficient algorithms to process them. We respond to the above challenges by describing our algorithm that mitigates interactions between pairs of CPGs. The algorithm creates logical models of analyzed CPGs and uses constraint logic programming (CLP) together with domain knowledge, codified as interaction and revision operators, to process them. Logical CPG models are transformed into CLP-CPG models that are solved to find a safe therapy. We represent these CLP-CPG models using MiniZinc, a standard language for CLP models. As motivation and illustration of our mitigation algorithm we use a clinical case study describing a patient managed for hypertension and deep vein thrombosis according to two individual CPGs. We apply the algorithm to this scenario and present MiniZinc representations of the constructed CLP-CPG models.
KW - Adverse Drug Event
KW - Clinical Practice Guideline
KW - Comorbidity
KW - Constraint Logic Programming
KW - MiniZinc Language
UR - http://www.scopus.com/inward/record.url?scp=84894342774&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84894342774&partnerID=8YFLogxK
U2 - 10.3233/978-1-61499-289-9-352
DO - 10.3233/978-1-61499-289-9-352
M3 - Conference contribution
C2 - 23920575
AN - SCOPUS:84894342774
SN - 9781614992882
T3 - Studies in Health Technology and Informatics
SP - 352
EP - 356
BT - MEDINFO 2013 - Proceedings of the 14th World Congress on Medical and Health Informatics
PB - IOS Press
Y2 - 20 August 2013 through 23 August 2013
ER -