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.
The electrocardiogram is a simple and useful clinical tool; nevertheless, few studies have evaluated the prevalence of electrocardiographic abnormalities in the Latin American population. This study aims to evaluate the major electrocardiographic abnormalities according to the Minnesota coding system in Brazilian adults, stratified by gender, age, race, and cardiovascular risk factors. Data from 14,424 adults (45.8% men, age 35 to 74 years) were obtained at baseline of the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), according to standardized protocol. The electrocardiogram were obtained with the Burdick Atria 6100 machine, stored on Pyramis System, automatically coded according to the Minnesota coding system by the Glasgow University software and then manually revised. Major abnormalities were more prevalent in men than women (11.3% and 7.9%, p <0.001). These differences were consistent through the different age groups, race, and number of cardiovascular risk factors. Electrocardiographic major abnormalities were more prevalent in black participants for both men (black: 15.1%, mixed: 10.4%, white: 11.1%, p = 0.001) and women (black: 10%, mixed: 7.6%, white: 7.2%, p = 0.004). In conclusion, in this large sample of Brazilian adults, the prevalence of major electrocardiographic abnormalities was higher among men, the elderly, black, and among people with more cardiovascular risk factors.
Anos de vida perdidos ajustados por incapacidade (do inglês, Disability-Adjusted Life-Year)
Background Coronavirus disease 2019 (COVID‐19) primarily causes lung infection, but recent studies have shown that cardiac involvement is associated with a worse prognosis. Objectives We conducted a systematic review and meta‐analysis to examine the prevalence of cardiac arrhythmias detected by the electrocardiogram and their relationships with adverse outcomes in patients with COVID‐19. Methods PubMed and Google were searched for studies that reported on cardiac arrhythmias and/or examined the relationship between arrhythmias and adverse outcomes. Results Thirty studies with 12,713 participants were included in the systematic review, and 28 studies (n = 12,499) in the meta‐analysis. The mean age was 61.3 ± 16.8 years; 39.3% were female. In 25 studies with 7578 patients, the overall prevalence of cardiac arrhythmias was 10.3% (95% confidence interval [CI]: 8.4%–12.3%). The most common arrhythmias documented during hospitalization were supraventricular arrhythmias (6.2%, 95% CI: 4.4%–8.1%) followed by ventricular arrhythmias (2.5%, 95% CI: 1.8%–3.1%). The incidence of cardiac arrhythmias was higher among critically ill patients (relative risk [RR]: 12.1, 95% CI: 8.5–17.3) and among non‐survivors (RR: 3.8, 95%, CI: 1.7–8.7). Eight studies reported changes in the QT interval. The prevalence of QTc > 500 ms was 12.3% (95% CI: 6.9%–17.8%). ST‐segment deviation was reported in eight studies, with a pooled estimate of 8.7% (95% CI: 7.3% to 10.0%). Conclusion Our meta‐analysis showed that QTc prolongation, ST‐segment deviation, and various other cardiac arrhythmias were observed in patients hospitalized with COVID‐19. The presence of cardiac arrhythmias was associated with a worse prognosis.
Background Although infection with Trypanosoma cruzi is thought to be lifelong, less than half of those infected develop cardiomyopathy, suggesting greater parasite control or even clearance. Antibody levels appear to correlate with T. cruzi (antigen) load. We test the association between a downwards antibody trajectory, PCR positivity and ECG alterations in untreated individuals with Chagas disease. Methodology/Principal findings This is a retrospective cohort of T. cruzi seropositive blood donors. Paired blood samples (index donation and follow-up) were tested using the VITROS Immunodiagnostic Products Anti-T.cruzi (Chagas) assay (Ortho Clinical Diagnostics, Raritan NJ) and PCR performed on the follow-up sample. A 12-lead resting ECG was performed. Significant antibody decline was defined as a reduction of > 1 signal-to-cutoff (S/CO) unit on the VITROS assay. Follow-up S/CO of < 4 was defined as borderline/low. 276 untreated seropositive blood donors were included. The median (IQR) follow-up was 12.7 years (8.5–16.9). 56 (22.1%) subjects had a significant antibody decline and 35 (12.7%) had a low/borderline follow-up result. PCR positivity was lower in the falling (26.8% vs 52.8%, p = 0.001) and low/borderline (17.1% vs 51.9%, p < 0.001) antibody groups, as was the rate of ECG abnormalities. Falling and low/borderline antibody groups were predominantly composed of individuals with negative PCR and normal ECG findings: 64% and 71%, respectively. Conclusions/Significance Low and falling antibody levels define a phenotype of possible spontaneous parasite clearance.
Chagas cardiomyopathy is the most harmful complication of Chagas disease. The electrocardiogram is a well-studied exam and has been considered an important tool for detection and evaluation of Chagas cardiomyopathy since the first years of its description. Many of its abnormalities have been described as associated with a worse prognosis. Serum BNP levels were described as inversely related to the left ventricular ejection fraction and as an independent predictor of death. It was not reported how electrocardiographic alterations correlate to NT-proBNP and its analog. The present study aims to describe the baseline electrocardiograms of a large cohort of patients with Chagas disease from endemic area and to establish an association between the number of electrocardiogram alterations and high levels of NT-ProBNP in Chagas disease patients. This study selected 1,959 Chagas disease patients in 21 municipalities within a limited region in the northern part of the State of Minas Gerais (Brazil), 1,084 of them had Chagas cardiomyopathy. NT-proBNP levels were suggestive of heart failure in 11.7% of this population. One or more electrocardiographic alterations have an Odds Ratio of 9.12 (CI 95% 5.62-14.80) to have NT-proBNP elevation. Considering the association between the number of 1, 2, and 3 or more alterations in electrocardiogram and NT-proBNP elevation, the ORs were 7.11 (CI 95% 4.33-11.67); 16.04 (CI 95% 9.27-27.77) and 47.82 (CI 95% 17.98-127.20), respectively. The presence and the number of typical electrocardiographic alterations of Chagas disease are independently associated with the severity of the cardiomyopathy.
ObjectiveCardiovascular diseases (CVDs) are highly preventable non-communicable diseases. ECG is a potential tool for risk stratification with respect to CVD. Our aim was to evaluate ECG’s role in all-cause and cardiovascular mortality prediction.MethodsParticipants from the Brazilian Longitudinal Study of Adult Health, free of known CVD at baseline were included. A 12-lead ECG was obtained at baseline (2008–2010). Participants were followed up to 2018 by annual interviews. Deaths were independently reviewed. Cox as well as Fine and Grey multivariable regression models were applied to evaluate if the presence of any major electrocardiographic abnormality (MEA), defined according to the Minnesota Code system, would predict total and cardiovascular deaths. We also evaluated the Net Reclassification Index of adding MEA to the Systematic Coronary Risk Evaluation (SCORE).ResultsThe 13 428 participants (median age 51 years, 45% men) were followed up for 8±1 years. All-cause and cardiovascular mortality occurred in 2.8% and 1.2% of the population, respectively. Prevalent MEA was an independent predictor of overall (HR=2.3, 95% CI 1.7 to 2.9) and cardiovascular mortality (HR=4.6, 95% CI 3.0 to 7.0) after adjustments for age, race, education and traditional cardiovascular risk factors. Adding MEA to the SCORE resulted in 9% mis-reclassification in the non-event subgroup and 33% correct reclassification in those with a fatal cardiovascular event.ConclusionPresence of MEA was an independent predictor of overall and cardiovascular mortality. ECG may have a role in risk prediction of cardiovascular mortality in primary care.
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
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.