Acta Univ. Agric. Silvic. Mendelianae Brun. 2014, 62(4), 769-776 | DOI: 10.11118/actaun201462040769

Neural Network for Determining Risk Rate of Post-Heart Stroke Patients

Oldřich Trenz¹, Milan Sepši², Vladimír Konečný¹

¹ Department of Informatics, Faculty of Business and Economics, Mendel University in Brno, 613 00 Brno, Czech Republic

² Department of Internal Cardiology Medicine - Institutions Shared with the Faculty Hospital in Brno - Institutions of Adult Age Medicine - Faculty of Medicine, Masaryk University in Brno, Jihlavská 20, 625 00 Brno, Czech Republic

The ischemic heart disease presents an important health problem that affects a great part of the population and is the cause of one third of all deaths in the Czech Republic. The availability of data describing the patients' prognosis enables their further analysis, with the aim of lowering the patients' risk, by proposing optimum treatment. The main reason for creating the neural network model is not only to automate the process of establishing the risk rate of patients suffering from ischemic heart disease, but also to adapt it for practical use in clinical conditions. Our aim is to identify especially the specific group of risk-rate patients whose well-timed preventive care can improve the quality and prolong the length of their lives.
The aim of the paper is to propose a patient-parameter structure, using which we could create a suitable model based on a self-taught neural network. The emphasis is placed on identifying key descriptive parameters (in the form of a reduction of the available descriptive parameters) that are crucial for identifying the required patients, and simultaneously to achieve a portability of the model among individual clinical workplaces (availability of parameters).

Keywords: self-learning neural network, risk stratification, myocardial infarction

Published: October 4, 2014  Show citation