Abstract : The COVID-19 pandemic has increased the relevance of remote and preventive diagnosis. In an age of social distancing and self-isolation, developing personalized COVID-19 self-testing and monitoring systems is an important area of healthcare. The aim of the study was to develop and apply methods for the automated study of the acoustic characteristics of COVID-19 cough to optimize early diagnosis and assessment of disease dynamics. The study was conducted by Acoustery project team (Russian Federation) and Astana Medical University (Republic of Kazakhstan). For training and validation of the algorithm, data from 70 people (35 without COVID-19 and 35 with confirmed COVID-19) were used. 2-3 cough episodes were recorded for each study participant. In total of 196 cough episodes were recorded. Moreover, cough acoustic patterns were analyzed by a pulmonologist. Acoustic criteria that are signs of COVID-19 were identified. The results of this study may contribute to the development of effective remote screening to COVID-19 and increase the effectiveness of government control of the spread of the SARS-COV2.