A decision support system for Parkinson disease management: expert models for suggesting medication change. (15th May 2018)

• Record Type: Journal Article
• Authors: Bohanec, Marko; Miljković, Dragana; Valmarska, Anita; Mileva Boshkoska, Biljana; Gasparoli, Elisabetta; Gentile, Giovanni; Koutsikos, Konstantinos; Marcante, Andrea; Antonini, Angelo; Gatsios, Dimitrios; Rigas, George; Fotiadis, Dimitrios I.; Tsiouris, Kostas M.; Konitsiotis, Spiros
• Is Part Of: Journal of decision systems. Volume 27(2018)Supplement 1
• Page Start: 164
• Page End: 172
• Publication Date: 2018-05-15
• Subjects: Parkinson' disease -- disease management -- medication change -- decision support system -- expert modelling -- multi-criteria model -- method DEX; Decision support systems -- Periodicals; Management information systems -- Periodicals; Information resources management -- Periodicals; Information storage and retrieval systems -- Periodicals; Management -- Communication systems -- Periodicals; Decision support systems; Information resources management; Information storage and retrieval systems; Management -- Communication systems; Management information systems; Periodicals; 658.40305
• DOI: 10.1080/12460125.2018.1469320
• Languages: English
• ISSNs: 1246-0125

Abstract

Abstract: Parkinson's disease (PD) is a degenerative disorder of the central nervous system, which requires a long-term, interdisciplinary disease management. The EU Horizon 2020 project PD_manager (http://www.parkinson-manager.eu/ ) is aimed at developing a decision support system for PD management. As part of this task, we have developed decision-support models that identify situations in which the disease has progressed to the point which requires a change of medical therapy. The input data includes motor symptoms, non-motor symptoms and epidemiologic data. The models were developed in collaboration with medical experts, using a qualitative multi-criteria method DEX. In this paper, we describe the process and results of model development, and assess the quality of models in terms of classification accuracy, transparency, correctness and completeness.