Deep neural network estimated electrocardiographic-age as a mortality predictor

Abstract

The electrocardiogram (ECG) is the most commonly used exam for the screening and evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG tracing (ECG-age) can be a measure of cardiovascular health and provide prognostic information. A deep convolutional neural network was trained to predict a patient's age from the 12-lead ECG using data from patients that underwent an ECG from 2010 to 2017 - the CODE study cohort (n=1,558,415 patients). On the 15% hold-out CODE test split, patients with ECG-age more than 8 years greater than chronological age had a higher mortality rate (hazard ratio (HR) 1.79, p<0.001) in a mean follow-up of 3.67 years, whereas those with ECG-age more than 8 years less than chronological age had a lower mortality rate (HR 0.78, p<0.001). Similar results were obtained in the external cohorts ELSA-Brasil (n=14,236) and SaMi-Trop (n=1,631). The ability to predict mortality from the ECG predicted age remains even when we adjust the model for cardiovascular risk factors. Moreover, even for apparent normal ECGs, having a predicted ECG-age 8 or more years greater than chronological age remained a statistically significant predictor of risk (HR 1.53, p<0.001 in CODE 15% test split). These results show that AI-enabled analysis of the ECG can add prognostic information to the interpretation of the 12-lead ECGs.

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

“…Cox proportional hazard model and C-index are used as the performance assessment for a series of models in Figure 9 shows the DLM validation in two external cohorts, the SaMi-Trop and CODE-15% (24). During median follow-up years of 2.08 (IQR: 1.98-2.23) and 3.46 (IQR: 2.12-5.22), the initial at-risk patients in SaMi-Trop and CODE-15% were 1,556, and 218,070, respectively.…”

“…mortality and cardiovascular mortality (23). Currently, many research teams had pointed out the strength of mortality risk stratification using ECG-age (24)(25)(26). However, the application potential of ECG-age was not extensively explored.…”

Heart age estimated using explainable advanced electrocardiography

“…However, the prognostic value of the ECG Heart Age presented in the current study requires additional validation. Furthermore, another AI method similar to that of Attia et al reported similarly encouraging results 10 . However, although the results of such AI studies are promising, DNN-based AI techniques are inherently problematic in several respects, especially in relation to their lack of transparency and explainability, i.e., the ‘black box’ of AI 18,19 .Without the ability to know the exact features of the 12-lead ECG that are most important in a given DNN model’s output, both interpretability and ethical accountability are compromised 45 .…”

“…If standard 10-second ECG recordings could be used instead, the clinical impact might be enhanced. Moreover, artificial intelligence has been used to estimate ECG Heart Age using the 10-second resting 12-lead ECG 7,8,10 . However, artificial intelligence techniques are limited by their “black box” approach, whereby the clinician does not have transparency as to the exact source(s) of the changes in the ECG that can affect an ECG Heart Age or other output 18,19 .Therefore, the aim of the study was to predict 5-minute ECG Heart Age from measures available by 10-second 12-lead ECG, and to compare the 10-second ECG Heart Age to chronological age in healthy subjects, subjects with cardiovascular risk factors, and patients with established cardiovascular disease.…”

Electrocardiographic Predictors of Mortality: Data from a Primary Care Tele-Electrocardiography Cohort of Brazilian Patients

“…We found good performance of a deep neural network in the recognition of six ECG abnormalities [36]. In the field of prognosis and health promotion, the concept of an electrocardiographic age via AI, compared with the patient's biological age, is promising [40]. This new promising cardiac biomarker can summarize the individual electrocardiographic characteristics simply and intuitively.…”