Electrocardiogram-Based Heart Age Estimation by a Deep Learning Model Provides More Information on the Incidence of Cardiovascular Disorders

Abstract

ObjectiveThe biological age progression of the heart varies from person to person. We developed a deep learning model (DLM) to predict the biological age via ECG to explore its contribution to future cardiovascular diseases (CVDs).MethodsThere were 71,741 cases ranging from 20 to 80 years old recruited from the health examination center. The development set used 32,707 cases to train the DLM for estimating the ECG-age, and 8,295 cases were used as the tuning set. The validation set included 30,469 ECGs to follow the outcomes, including all-cause mortality, cardiovascular-cause mortality, heart failure (HF), diabetes mellitus (DM), chronic kidney disease (CKD), acute myocardial infarction (AMI), stroke (STK), coronary artery disease (CAD), atrial fibrillation (AF), and hypertension (HTN). Two independent external validation sets (SaMi-Trop and CODE15) were also used to validate our DLM.ResultsThe mean absolute errors of chronologic age and ECG-age was 6.899 years (r = 0.822). The higher difference between ECG-age and chronological age was related to more comorbidities and abnormal ECG rhythm. The cases with the difference of more than 7 years had higher risk on the all-cause mortality [hazard ratio (HR): 1.61, 95% CI: 1.23–2.12], CV-cause mortality (HR: 3.49, 95% CI: 1.74–7.01), HF (HR: 2.79, 95% CI: 2.25–3.45), DM (HR: 1.70, 95% CI: 1.53–1.89), CKD (HR: 1.67, 95% CI: 1.41–1.97), AMI (HR: 1.76, 95% CI: 1.20–2.57), STK (HR: 1.65, 95% CI: 1.42–1.92), CAD (HR: 1.24, 95% CI: 1.12–1.37), AF (HR: 2.38, 95% CI: 1.86–3.04), and HTN (HR: 1.67, 95% CI: 1.51–1.85). The external validation sets also validated that an ECG-age >7 years compare to chronologic age had 3.16-fold risk (95% CI: 1.72–5.78) and 1.59-fold risk (95% CI: 1.45–1.74) on all-cause mortality in SaMi-Trop and CODE15 cohorts. The ECG-age significantly contributed additional information on heart failure, stroke, coronary artery disease, and atrial fibrillation predictions after considering all the known risk factors.ConclusionsThe ECG-age estimated via DLM provides additional information for CVD incidence. Older ECG-age is correlated with not only on mortality but also on other CVDs compared with chronological age.

Artificial Intelligence-Enabled Electrocardiography Predicts Left Ventricular Dysfunction and Future Cardiovascular Outcomes: A Retrospective Analysis

“…The first strategy was the standard oversampling process without any revision in each batch (no-match), and the initial parameters were generated at random. The second strategy was to use the first strategy with transfer learning via age estimation DLM (no match with transfer), which was based on a previous study [ 46 ]. The third strategy was to additionally match both sex and age (sex-/age-matched).…”

Heart age estimated using explainable advanced electrocardiography

“…Such results at least superficially correspond to the findings in our study that the Heart Age Gap increased with increasing burden of cardiovascular risk. Other DNN-based AI methods, similar to that of Attia et al also more recently reported similarly encouraging results 10 , 13 , 14 .…”

“…Or the extent to which unanticipated results might merely relate to excess dependency on the particular characteristics of a given DNN AI model’s training set 50 . In addition, a major flaw in all DNN-based AI ECG age models that we are aware of is that their age predictions were made using training datasets that also included individuals with both cardiovascular risk factors and established disease 8 , 10 , 13 , 14 . For ECG Heart Age to be used as a marker of potentially reversible cardiovascular disease and risk, it is imperative that ECG Heart Age agrees with chronological age in healthy populations, since it is the deviation from the line of identity in this relationship that forms the basis for measurement-related accuracy and precision, and subsequent disease-related assessment and risk.…”

Artificial Intelligence-Enabled Electrocardiogram Predicted Left Ventricle Diameter as an Independent Risk Factor of Long-Term Cardiovascular Outcome in Patients With Normal Ejection Fraction

“…As the AI-ECG could predict the disease development in healthy individuals without abnormal imaging findings or symptoms, the concept of previvors was proposed recently. With apparent false positive AI-ECG findings, patients with a higher risk of many diseases, such as LV dysfunction ( 20 ), future atrial fibrillation ( 63 ), hyperkalemia ( 64 ), and elder heart age ( 44 ), could receive preventive interventions or medical surveillance early.…”

“…The demographic characteristics were obtained in our EMRs and disease history before the index date of ECG was collected using the corresponding code of International Classification of Disease, Ninth Revision and Tenth Revision (ICD-9 and ICD-10, respectively), as described previously ( 24 , 26 , 32 , 44 ). The remaining echocardiographic parameters, such as interventricular septum (IVS) diameter, left ventricular posterior wall (LVPW) diameter, left atrium (LA) size, aortic root (AO) diameter, right ventricular (RV) diameter, pulmonary artery systolic pressure (PASP), and pericardial effusion (PE), were also collected in this study.…”