AUTOMATED PERSONALIZED ARRHYTHMIA MONITORING SYSTEM

Abstract

Background. The detection of arrhythmia is considered the basis for the diagnosis of cardiovascular diseases at the present time. Arrhythmia can be caused by various factors, such as heart disease, medication, stress, in some cases, arrhythmia can be life-threatening, so the task of its timely detection and treatment is extremely urgent. The nonstationary nature and variability of the electrocardiogram form in different patients leads to the lack of a universal approach for detecting arrhythmias at the time of their occurrence. The developed methods for identifying and classifying signs of arrhythmia, implemented in automated arrhythmia monitoring systems, optimize the work of doctors in diagnostic tasks by analyzing electrocardiograms and other data to identify signs of arrhythmia. The existing automated systems for the diagnosis of arrhythmia are based on the use of machine learning algorithms for the analysis of an electrocardiogram, and identify signs characteristic of electrocardiogram analysis, and identify signs characteristic of various types of arrhythmias. The aim of the work is to develop the structure of an automated arrhythmia monitoring system, analyze the main methods for analyzing heart rate variability and use adaptable threshold values using the example of an electrocardiogram in pathology. Materials and methods. The study materials were electrocardiograms with arrhythmia episodes from certified databases. The study was conducted using mathematical statistics methods. Results. The structure of an automated personalized arrhythmia monitoring system with the integration of personal medical information and the use of artificial intelligence is proposed. Conclusion. The structure of an automated arrhythmia monitoring system has been developed, the main methods of analyzing heart rate variability have been analyzed and an adaptable threshold for patient age has been used on the example of an electrocardiogram for arrhythmia.

Keywords

• arrhythmia
• personalization
• monitoring
• automated system
• arrhythmia classification
• telemedicine system
• personalized diagnostics
• electrocardiogram