AP25796273 – Algorithm for detecting hemodynamically significant cardiac arrhythmia during free physical activity
Objective of the project – The main goal of the project is to develop an algorithm for timely and effective diagnosis of hemodynamically important arrhythmias of the heart during free movement activity. This algorithm aims to ensure the safety of patients, prevent complications of heart diseases and improve the efficiency of medical services.
Relevance: Medical diagnosis is one of the key areas of healthcare, especially for the early detection of cardiovascular diseases and monitoring life-threatening arrhythmias during patient screening. Currently, in the Republic of Kazakhstan, effective scientific and technical recommendations for detecting arrhythmias during free movement activity are lacking or are in the early stages of development. Studying heart rate, rhythm, and sequence of contractions, as well as developing medical service methodologies based on medical and economic groups, are urgent tasks. The use of modern medical and information technologies allows improving diagnostic effectiveness. Therefore, the development and enhancement of a non-invasive cardiodiagnostic system for timely detection of life-threatening conditions remain an important scientific and practical challenge.
Scientific supervisor: PhD, Ainur Toktargalykzy Bekbai
Expected and achieved results: The results of the work are highly useful for medical specialists. The algorithm allows effective real-time detection of hemodynamically significant arrhythmias with high reliability compared to traditional methods. Continuous monitoring of patients’ heart condition during free movement helps prevent unexpected complications. Early detection of arrhythmias enables more effective treatment and the development of individualized patient care plans. The results are published in scientific articles and presented at conferences. Experimental data confirmed the accuracy of the method and its applicability for clinical practice.
List of publications with links to them
- Bekbay, Ainur, et al. "an interpretable ecgbased approach for detecting hemodynamically significant arrhythmias using lightweight machine learning models." Eastern-European Journal of Enterprise Technologies 5 (2025). https://doi.org/10.15587/1729-4061.2025.340493