As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Leveraging deep learning and vast clinical datasets can reveal crucial, previously indiscernible patterns in electrocardiogram (ECG) records, enhancing the diagnosis and assessment of cardiovascular diseases. In this study, we first construct a large-scale clinical 12-lead ECG dataset, then exploit the potential of deep learning models to analyze ECG data and identify a significant link between a patient’s cardiovascular health and the discrepancy between their chronological (CHR) age and the age as predicted from ECG data. Through analyzing ECG records, the research determines correlations between predicted ECG age and CHR age in different populations. The results demonstrate ECG age is strongly correlated with CHR age only in the normal population, while the correlation is weaker in the cardiovascular disease population. Further analysis showed that when the ECG age is higher than the CHR age, the individual has a higher risk (the average is 1.64 times higher) of developing various types of cardiovascular disease. Conversely, if the ECG age is lower, they tend to have a lower risk (the average is 0.72 times lower). This evidence suggests that the difference between the ECG age and the CHR age can be viewed as a marker for cardiovascular health.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.