Risk factors

‘Heart Age’ revealed in 10-second ECG


Heart Age estimates that can explain a patient’s cardiovascular risk can be determined based on a 10-second, 12-lead ECG, paving the way for increased use in clinical practice, Australian researchers say.

In findings published in Nature Scientific Reports they show that a cardiovascular-health estimate derived from a short ECG and computed statistical analysis achieved similar accuracy to a five-minute resting ECG trace.

In a study involving 2,771 participants (1682 healthy volunteers,  305 with cardiovascular risk factors and 784 with cardiovascular disease) they found that the 10-second ECG Heart Age estimate showed strong agreement with the 5-minute Heart Age (R2 = 0.94, p < 0.001, mean ± SD bias 0.0 ± 5.1 years).

“We show that Heart Age can be estimated from standard-fidelity, conventional 10-second ECG recordings without requiring more specialised, higher-fidelity, five-minute long recording,” the paper said.

“Consequently, ECG-based Heart Age as estimated using Bayesian techniques can now be more readily implemented in clinical practice.”

The authors said ‘Heart Age‘ was a simple way of communicating an individual’s cardiovascular disease risk, by contrasting it to the patient’s chronological age as a ‘Heart Age Gap’. Previous research has shown that Heart Age Gap is an easy-to-understand and effective measure to prompt patients to improve their modifiable lifestyle risk factors, such as by quitting smoking, dietary changes and increased activity.

Professor of Cardiac Imaging and Director of Clinical Imaging at the University of Sydney, Martin Ugander, said the team, involving US and Swedish researchers, was currently undertaking further clinical testing of a cloud-based solution that would compute Heart Age from the ECG recording.

“Standard clinical ECG machines are configured to routinely automatically transfer the digital file of an ECG recording to our Advanced ECG cloud system, where the clinician can log in and see the results of ECG Heart Age, and a number of other advanced ECG measures,” he told the limbic.

“Our anecdotal clinical experience using a 5-minute ECG Heart Age in New Zealand has shown that presenting cardiovascular risk as a Heart Age can profoundly increase the ability for a patient to understand and digest their cardiovascular risk, and heart age can be a very strong motivator for lifestyle changes (diet, exercise, tobacco use) and adherence to medication.”

“Medicine and the information we as doctors provide to patients can be technical, complicated, and often times challenging to comprehend. People have a universal understanding of age. When it comes to the heart, Heart Age is able to convey cardiovascular risk and the presence of subclinical disease in a surprisingly simple, intuitive, and powerful way.”

He said the ideal application of the technology would be making it available to general practitioners to assess and motivate people with few or no heart disease symptoms to make changes to mitigate progression.

The team is also working on a separate trial to determine if using Heart Age for people with hypertension would improve outcomes. Further, they have received funding to conduct heart disease screening using an Apple Watch app and ECG recording, to detect silent heart disease in the general public.

The Heart Age research was based on a pre-existing database of de-identified subjects with five-minute and 10-second ECG recordings.

It used Bayesian statistical analyses, machine learning and linear regression, incorporating the patient’s actual age with ECG characteristics, notably the P-wave duration and the spatial QT duration.

According to their paper, the ECG inputs used in the calculating  Heart Age may include “the T-wave axis in the frontal plane, P-wave duration, frontal plane vectorcardiographic QRS axis, spatial JT interval, spatial mean QRS-T angle, high-frequency QRS root mean squared voltages across signal-averaged leads after band-pass filtering, beat-to-beat QT- and RR-interval variability, and measures of T-wave complexity based on singular value decomposition and signal averaging of the T wave.”

Within the study, the analysis showed that the Heart Age Gap “increases markedly with cardiovascular risk and disease”.

It found healthy individuals had no Heart Age Gap (with a range of plus or minus 5.7 years), but the variance increased with cardiovascular risk. Those with cardiovascular risk factors had a gap of 7.4 years (with a range of plus or minus 7.3 years).

Patients with known cardiovascular disease, however, had an average Heart Age Gap of 14.3 years (plus or minus 9.2 years).

Already a member?

Login to keep reading.

OR
Email me a login link
logo

© 2022 the limbic