Electrocardiogram (RCG) tests could be use in the future in combination with an AI model to detect premature aging and cognitive decline, according to a new study.
An electrocardiogram (ECG) measures the electrical activity of the heartbeat. With each beat, an electrical impulse travels through the heart.
Researchers have now designed an AI model, termed deep neural network (DNN), to predict people’s biological age (age of body cells and tissues) from ECG data.
“Unlike chronological age, which is based on years lived, ECG-age reflects the functional status of the heart and potentially the entire organism at the tissue level, providing insights into aging and health status,” said Bernard Ofosuhene, lead author of the study and clinical research co-ordinator in the department of medicine at the UMass Chan Medical School in Massachusetts.
Previous research has found that ECG-age can help predict heart disease and death. Before this new study, little was known about ECG-age’s relationship to cognitive impairment.
Researchers analysed data from more than 63,000 participants in the UK Biobank, a large and ongoing study of more than 500,000 volunteers from the United Kingdom who enrolled when they were between 40 and 69 years old.
Participants underwent a battery of cognitive tests. Cognitive performance was analysed during assessment visits to align with the timing of ECG testing and the artificial intelligence model was used to determine their ECG-age.
This approach ensured that the cognitive data accurately captured the participants’ cognitive status at the same time their ECG age was estimated.
Based on the ECG-age results in comparison to their actual ages, participants were divided into three groups: normal aging, accelerated ECG-aging (older than their chronological age), and decelerated ECG-aging (younger than their chronological age).
The analysis found that compared with the normal aging group, based on ECG-age, those younger than their chronological age group performed better on 6 of 8 cognitive tests, and older than their chronological age group performed worse on six of eight cognitive tests.
“There is a lot of ECG-data available for stroke treatment and I encourage health care professionals to use this data to look for signs of cognitive decline. Doing so may help with early diagnosis and timely intervention,” Ofosuhene said.
The study has several limitations. Because the analysis was conducted on people between the ages of 43 and 85, it is unclear whether the findings apply to other ages. This cross-sectional study, with all measures taken at the same time, does not provide information about changes in cognitive function over time.
“In future research, we aim to investigate whether gender differences affect the relationship between ECG-age and cognitive performance. Additionally, considering that most of UK Biobank participants are of European ancestry, we are interested in determining if our findings can be replicated in more diverse populations,” Ofosuhene said.
“Researchers increasingly recognise the strong connection between heart and brain health. This study shows that when AI analyses ECG data, a higher biological age is linked to poorer cognitive performance,” said Fernando Testai, professor of neurology and rehabilitation at the University of Illinois College of Medicine in Chicago, who was not involved in the study.
“Using ECG data to assess cognitive ability seems like a futuristic idea. If this study is validated, it could have several important outcomes. For instance, ECG data collected in a doctor’s office or remotely with wearables could help assess cognition at home or in rural areas lacking neuropsychiatric specialists.
“Additionally, using ECG data and AI might be quicker and more objective than traditional neuropsychological assessments. However, one important question remains: can ECG data predict future cognitive decline? Answering this could lead to valuable treatments since some ECG issues can be fixed.”