Decision Support for Medication Change of Parkinson's Disease Patients.

摘要: Background and Objective Parkinson's disease (PD) is a degenerative disorder of the central nervous system for which currently there no cure. Its treatment requires long-term, interdisciplinary management, usage typical medications, including levodopa, dopamine agonists, enzymes, such as MAO-B inhibitors. The key goal management to prolong patients' independence keep their quality life. Due different combinations motor non-motor symptoms from PD patients suffer, in addition existing comorbidities, change medications difficult patient-specific. To help physicians, we developed two decision support models suggest how medication treatment. Methods were using DEX methodology, integrates qualitative multi-criteria modelling with rule-based expert systems. differ way rules defined. In first model, are based on interviews neurologists (DEX model), second they formed database past decisions data model). We assessed both Progression Markers Initiative (PPMI) questionnaire answered by 17 4 European countries accuracy measure Jaccard index. Results Both include 15 sub-models that address possible changes given current state. particular, incorporate state (dyskinesia intensity, dyskinesia duration, OFF duration), mental problems (impulsivity, cognition, hallucinations paranoia), epidemiologic (patient's age, activity level) comorbidities (cardiovascular problems, hypertension low blood pressure). highest ranges 69.31 99.06 %. Conclusions show model superior model. results indicate constructed sufficiently adequate thus fit purpose making “second-opinion” suggestions users.