In determining the symptoms and predicting disease in medicine, health outcomes of patients are used, which are obtained from different clinical tests. Among the initial symptoms of people suffering from Parkinson's disease we can include muscle rigidity, problems with speech (dysphonia), movement or writing (dysgraphia). In this article, we focus just on the data obtained from the primary symp- toms of patients and their further use for early diagnosis and detection of Parkinson's disease using machine learning methods. We first describe basic characteristics of this disease and its typical features and then we analyze the current state and methods of collecting data used for creating decision models. Next, we also summarize the results of our previous research in this area and describe the future directions of our work.

Department of Cybernetics and Artificial Intelligence Faculty of Electrical Engineering and Informatics Technical University of Košice Slovakia

Literatura