The electrocardiogram (ECG) is the most commonly used exam for the evaluation of cardiovascular diseases. Here we propose that the age predicted by artificial intelligence (AI) from the raw ECG (ECG-age) can be a measure of cardiovascular health. A deep neural network is trained to predict a patient’s age from the 12-lead ECG in the CODE study cohort (n = 1,558,415 patients). On a 15% hold-out split, patients with ECG-age more than 8 years greater than the chronological age have a higher mortality rate (hazard ratio (HR) 1.79, p < 0.001), whereas those with ECG-age more than 8 years smaller, have a lower mortality rate (HR 0.78, p < 0.001). Similar results are obtained in the external cohorts ELSA-Brasil (n = 14,236) and SaMi-Trop (n = 1,631). Moreover, even for apparent normal ECGs, the predicted ECG-age gap from the chronological age remains a statistically significant risk predictor. These results show that the AI-enabled analysis of the ECG can add prognostic information.
Background: The 2012 World Heart Federation Criteria are the current gold standard for the diagnosis of latent rheumatic heart disease (RHD). Because data and experience using these criteria have grown, there is opportunity to simplify and develop outcome prediction tools. We aimed to develop a simple echocardiographic score applicable for RHD screening with potential to predict disease progression. Methods: This study included 3 cohorts used for score derivation (n=9501), score validation (n=7312), and assessment of outcomes prediction (n=227). In the derivation cohort, variables independently associated with definite RHD were assigned point values proportional to their regression coefficients. The sum of these values was stratified into low (0–6), intermediate (7–9), and high (≥10) risk. Results: Five components were selected for score development, including mitral valve anterior leaflet thickening, excessive leaflet tip motion, and regurgitation jet length ≥2 cm, and aortic valve focal thickening and any regurgitation. The score showed optimal discrimination and calibration for RHD diagnosis in the derivation and validation cohorts (C statistic, 0.998 and 0.994, respectively), with good discrimination for predicting disease progression (C statistic, 0.811). Progression-free survival rate in the low-risk children at 1-, 2-, and 3-year follow-up was 100%, 100%, and 93%, respectively, compared with 90%, 60%, and 47% in high-risk group. The point-based score was strongly associated with disease progression (hazard ratio, 1.270; 95% CI, 1.188–1.358; P <0.001). Conclusions: This simplified score, based on components of the World Heart Federation criteria, is highly accurate to recognize definite RHD and provides the first tool for risk stratification, assigning children with latent RHD to low, intermediate, or high risk based on echocardiographic features at diagnosis.
Digital electrocardiographs are now widely available and a large number of digital electrocardiograms (ECGs) have been recorded and stored. The present study describes the development and clinical applications of a large database of such digital ECGs, namely the CODE (Clinical Outcomes in Digital Electrocardiology) study. ECGs obtained by the Telehealth Network of Minas Gerais, Brazil, from 2010-17, were organized in a structured database. A hierarchical free-text machine learning algorithm recognized specific ECG diagnoses from cardiologist reports. The Glasgow ECG Analysis Program provided Minnesota Codes and automatic diagnostic statements. The presence of a specific ECG abnormality was considered when both automatic and medical diagnosis were concordant; cases of discordance were decided using heuristisc rules and manual review. The ECG database was linked to the national mortality information system using probabilistic linkage methods. From 2,470,424 ECGs, 1,773,689 patients were identified. After excluding the ECGs with technical problems and patients <16 years-old, 1,558,415 patients were studied. High performance measures were obtained using an end-to-end deep neural network trained to detect 6 types of ECG abnormalities, with F1 scores >80% and specificity >99% in an independent test dataset. We also evaluated the risk of mortality associated with the presence of atrial fibrillation (AF), which showed that AF was a strong predictor of cardiovascular mortality and mortality for all causes, with increased risk in women. In conclusion, a large database that comprises all ECGs performed by a large telehealth network can be useful for further developments in the field of digital electrocardiography, clinical cardiology and cardiovascular epidemiology.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.