Seventh International Conference on Advances in Computing, Electronics and Communication-ACEC2018
Author(s) : BASARAB M.A., KONNOVA N.S
The development of medical decision support systems, especially in the field of cardiology, is an important and urgent task. The report considers the main requirements for the recognition system used to assess the functional state of the cardiovascular system (CVS). The description of the general scheme of the developed decision support system based on the identification and classification of CVS states is given. As various types of neural networks and other classifiers based on machine learning are often used in problems of the cardiovascular states identification, here, the results obtained with the help of different architectures of such classifiers are examined. A proprietary numerical experiment with real clinical data (confirmed by cross-validation) is performed on the basis of the most efficient neural networks with refinements for generalization and data preprocessing.