Search academic texts

Registration Number

0223U001882, 0122U002660 , R & D reports

Title

Create information technology for the analysis of a big array of ECG data to predict the risk of cardiovascular disease. Stage 2. Analysis of a big array of ECG and demographic data based on the results of large-scale screening of the population in China.

popup.stage_title

Head

Chaikovskyi Illia A., Кандидат медичних наук

Registration Date

04-02-2023

Organization

V.M. Glushkov Institute of Cybernetics of the National Academy of Sciences of Ukraine

popup.description2

During the execution of the stage, the array of electrocardiographic indicators was supplemented with all possible combined indices of hypertrophy of the left and right ventricles. A control sample was also added, in the elements of which all ECG indicators are within the normal range. As a result of a statistical analysis of an array of about 400 ECG parameters based on mass screening of the population in the Khmelnytskyi region (about 22,000 people) and the People's Republic of China (about 25,000 people, data provided by the Department of Population Research at the University of Oxford), previously unknown connections between individual and generalized ECG parameters and such an endpoint as death from all causes (all-case-mortality). Statistical data on the survival of the participants of the 2015 study in the Shepetivskyi district for 5 years, as well as the participants of the population study of Kadoori Biobank and the University of Oxford for 10 years, were obtained. On this basis, a technique for predicting the risk of mortality from all causes based on the data of an in-depth ECG/VRS analysis was created. To create such a technique, machine learning methods were used, in particular Isolation Forest anomaly detection.

Product Description

popup.authors

Budnyk Mykola Mykolaiovych
Ponomariov Vadym D.
Ryzhenko Tetiana M.
Syropiatov Illya
Chaykovsky Illya A

popup.nrat_date

2023-02-04