MODELING THE PROCESS OF RECOGNITION OF PACEMAKER DYSFUNCTION

Abstract

The article presents a comprehensive study aimed at solving a pressing scientific and practical problem - modeling and designing information technology for recognizing pacemaker dysfunctions to increase the efficiency of diagnostics and reliability of life support systems. The relevance of the work is due to the rapid growth of the number of cardiovascular diseases in the world and in Ukraine in particular, which leads to an increase in the number of operations for implanting pacemakers, the functioning of which requires continuous and high-precision monitoring. The authors analyzed the world experience in using modern diagnostic tools, including neural networks for analyzing radiographs, mobile applications for remote monitoring, and machine learning algorithms for ECG analysis, which revealed the lack of integrated solutions that would combine different methods for detecting technical and clinical failures. The proposed approach is based on the use of multimodal input data, such as information about the patient's symptoms (dizziness, arrhythmia, weakness), device hardware reports (pacing rate, battery status, intracardiac signals), ECG and Holter monitoring results, as well as data from physical activity and intracardiac pressure sensors. The scientific novelty of the study lies in the development of a mathematical model of the process of recognizing pacemaker dysfunction, presented as a sequence of tuples and transformations that provide data preparation, selection of the most informative signs of cardiac activity and direct recognition of the system state. Special attention is paid to the stages of signal normalization and artifact filtering, which guarantees high accuracy of classification of disorders even under difficult operating conditions or during physical exertion of the patient. The practical significance of the work is confirmed by the creation of a structure of output results, which include not only automated fixation of anomalies, but also the formation of specific recommendations for changing pacemaker settings and instant notification of medical personnel, relatives and the patient himself. The proposed technology allows to ensure a continuous monitoring cycle, minimize the risk of human error when interpreting complex diagnostic data and significantly improve the prognosis for patients with high dependence on an artificial pacemaker. Thus, the results obtained create a reliable foundation for building modern information technologies for cardiac care.