Artificial intelligence-enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study.

BACKGROUND: Artificial intelligence (AI)-enabled electrocardiography (ECG) can be used to predict risk of future disease and mortality but has not yet been adopted into clinical practice. Existing model predictions do not have actionability at an individual patient level, explainability, or biological plausibi. We sought to address these limitations of previous AI-ECG approaches by developing the AI-ECG risk estimator (AIRE) platform. METHODS: The AIRE platform was developed in a secondary care dataset (Beth Israel Deaconess Medical Center [BIDMC]) of 1 163 401 ECGs from 189 539 patients with deep learning and a discrete-time survival model to create a patient-specific survival curve with a single ECG. Therefore, AIRE predicts not only risk of mortality, but also time-to-mortality. AIRE was validated in five diverse, transnational cohorts from the USA, Brazil, and the UK (UK Biobank [UKB]), including volunteers, primary care patients, and secondary care patients. FINDINGS: AIRE accurately predicts risk of all-cause mortality (BIDMC C-index 0·775, 95% CI 0·773-0·776; C-indices on external validation datasets 0·638-0·773), future ventricular arrhythmia (BIDMC C-index 0·760, 95% CI 0·756-0·763; UKB C-index 0·719, 95% CI 0·635-0·803), future atherosclerotic cardiovascular disease (0·696, 0·694-0·698; 0·643, 0·624-0·662), and future heart failure (0·787, 0·785-0·789; 0·768, 0·733-0·802). Through phenome-wide and genome-wide association studies, we identified candidate biological pathways for the prediction of increased risk, including changes in cardiac structure and function, and genes associated with cardiac structure, biological ageing, and metabolic syndrome. INTERPRETATION: AIRE is an actionable, explainable, and biologically plausible AI-ECG risk estimation platform that has the potential for use worldwide across a wide range of clinical contexts for short-term and long-term risk estimation. FUNDING: British Heart Foundation, National Institute for Health and Care Research, and Medical Research Council.

Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms.

Background and Aims: AI-enhanced 12-lead ECG can detect a range of structural heart diseases (SHDs) but has a limited role in community-based screening. We developed and externally validated a noise-resilient single-lead AI-ECG algorithm that can detect SHD and predict the risk of their development using wearable/portable devices. Methods: Using 266,740 ECGs from 99,205 patients with paired echocardiographic data at Yale New Haven Hospital, we developed ADAPT-HEART, a noise-resilient, deep-learning algorithm, to detect SHD using lead I ECG. SHD was defined as a composite of LVEF<40%, moderate or severe left-sided valvular disease, and severe LVH. ADAPT-HEART was validated in four community hospitals in the US, and the population-based cohort of ELSA-Brasil. We assessed the model's performance as a predictive biomarker among those without baseline SHD across hospital-based sites and the UK Biobank. Results: The development population had a median age of 66 [IQR, 54-77] years and included 49,947 (50.3%) women, with 18,896 (19.0%) having any SHD. ADAPT-HEART had an AUROC of 0.879 (95% CI, 0.870-0.888) with good calibration for detecting SHD in the test set, and consistent performance in hospital-based external sites (AUROC: 0.852-0.891) and ELSA-Brasil (AUROC: 0.859). Among those without baseline SHD, high vs. low ADAPT-HEART probability conferred a 2.8- to 5.7-fold increase in the risk of future SHD across data sources (all P<0.05). Conclusions: We propose a novel model that detects and predicts a range of SHDs from noisy single-lead ECGs obtainable on portable/wearable devices, providing a scalable strategy for community-based screening and risk stratification for SHD.

An Ensemble Deep Learning Algorithm for Structural Heart Disease Screening Using Electrocardiographic Images: PRESENT SHD.

Background: Identifying structural heart diseases (SHDs) early can change the course of the disease, but their diagnosis requires cardiac imaging, which is limited in accessibility. Objective: To leverage 12-lead ECG images for automated detection and prediction of multiple SHDs using a novel deep learning model. Methods: We developed a series of convolutional neural network models for detecting a range of individual SHDs from images of ECGs with SHDs defined by transthoracic echocardiograms (TTEs) performed within 30 days of the ECG at the Yale New Haven Hospital (YNHH). SHDs were defined based on TTEs with LV ejection fraction <40%, moderate-to-severe left-sided valvular disease (aortic/mitral stenosis or regurgitation), or severe left ventricular hypertrophy (IVSd > 1.5cm and diastolic dysfunction). We developed an ensemble XGBoost model, PRESENT-SHD, as a composite screen across all SHDs. We validated PRESENT-SHD at 4 US hospitals and a prospective population-based cohort study, the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), with concurrent protocolized ECGs and TTEs. We also used PRESENT-SHD for risk stratification of new-onset SHD or heart failure (HF) in clinical cohorts and the population-based UK Biobank (UKB). Results: The models were developed using 261,228 ECGs from 93,693 YNHH patients and evaluated on a single ECG from 11,023 individuals at YNHH (19% with SHD), 44,591 across external hospitals (20-27% with SHD), and 3,014 in the ELSA-Brasil (3% with SHD). In the held-out test set, PRESENT-SHD demonstrated an AUROC of 0.886 (0.877-894), sensitivity of 89%, and specificity of 66%. At hospital-based sites, PRESENT-SHD had AUROCs ranging from 0.854-0.900, with sensitivities and specificities of 93-96% and 51-56%, respectively. The model generalized well to ELSA-Brasil (AUROC, 0.853 [0.811-0.897], sensitivity 88%, specificity 62%). PRESENT-SHD performance was consistent across demographic subgroups. A positive PRESENT-SHD screen portended a 2- to 4-fold higher risk of new-onset SHD/HF, independent of demographics, comorbidities, and the competing risk of death across clinical sites and UKB, with high predictive discrimination. Conclusion: We developed and validated PRESENT-SHD, an AI-ECG tool identifying a range of SHD using images of 12-lead ECGs, representing a robust, scalable, and accessible modality for automated SHD screening and risk stratification.

Association between leisure-time physical activity and arterial stiffness in adults of the ELSA-Brasil study: a mediation analysis.

OBJECTIVES: We aimed at defining the direct and the mediated pathways for the association between leisure-time physical activity (LTPA) and carotid-to-femoral pulse wave velocity (cf-PWV), and also to identify whether these effects are influenced by sex and age. METHODS: Cross-sectional data from 13 718 adults (35-74 years) were obtained at the baseline of the ELSA-Brasil study. The cf-PWV was obtained by measuring the pulse transit time and the distance traveled by the pulse between the carotid and the femoral, as well as clinical and anthropometric parameters were measured. The levels of LTPA were determined by applying the long form of the International Physical Activity Questionnaire (IPAQ). RESULTS: Classical cardiovascular risk factors were independently associated with cf-PWV. Path analysis showed that increased levels of LTPA were directly associated with lower cf-PWV in both men and women ( ß : -0.123 ±â€Š0.03 vs. 0.065 ±â€Š0.029, P for sex = 0.165), except for diabetes. Also, the mediated effect of LTPA on SBP and DBPs, heart rate, BMI, and fasting glucose, was associated with lower cf-PWV in men and women ( ß : -0.113 ±â€Š0.016 vs. -0.104 ±â€Š0.016, P for sex = 0.692), except for diabetes. When age was tested as a moderator, the direct effect did not change significantly according to participants' age, regardless of sex. However, the mediated effect increases in both men and women over 50 years. CONCLUSION: Our findings support that LTPA in adults reduces cf-PWV by acting in different ways according to age. Physical activity in older individuals improves cardiometabolic risk factors and thus mitigates the stiffening of large arteries.

Using Artificial Intelligence to Predict Heart Failure Risk from Single-lead Electrocardiographic Signals: A Multinational Assessment.

Importance: Despite the availability of disease-modifying therapies, scalable strategies for heart failure (HF) risk stratification remain elusive. Portable devices capable of recording single-lead electrocardiograms (ECGs) can enable large-scale community-based risk assessment. Objective: To evaluate an artificial intelligence (AI) algorithm to predict HF risk from noisy single-lead ECGs. Design: Multicohort study. Setting: Retrospective cohort of individuals with outpatient ECGs in the integrated Yale New Haven Health System (YNHHS) and prospective population-based cohorts of UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Participants: Individuals without HF at baseline. Exposures: AI-ECG-defined risk of left ventricular systolic dysfunction (LVSD). Main Outcomes and Measures: Among individuals with ECGs, we isolated lead I ECGs and deployed a noise-adapted AI-ECG model trained to identify LVSD. We evaluated the association of the model probability with new-onset HF, defined as the first HF hospitalization. We compared the discrimination of AI-ECG against the pooled cohort equations to prevent HF (PCP-HF) score for new-onset HF using Harrel's C-statistic, integrated discrimination improvement (IDI), and net reclassification improvement (NRI). Results: There were 194,340 YNHHS patients (age 56 years [IQR, 41-69], 112,082 women [58%]), 42,741 UKB participants (65 years [59-71], 21,795 women [52%]), and 13,454 ELSA-Brasil participants (56 years [41-69], 7,348 women [55%]) with baseline ECGs. A total of 3,929 developed HF in YNHHS over 4.5 years (2.6-6.6), 46 in UKB over 3.1 years (2.1-4.5), and 31 in ELSA-Brasil over 4.2 years (3.7-4.5). A positive AI-ECG screen was associated with a 3- to 7-fold higher risk for HF, and each 0.1 increment in the model probability portended a 27-65% higher hazard across cohorts, independent of age, sex, comorbidities, and competing risk of death. AI-ECG's discrimination for new-onset HF was 0.725 in YNHHS, 0.792 in UKB, and 0.833 in ELSA-Brasil. Across cohorts, incorporating AI-ECG predictions in addition to PCP-HF resulted in improved Harrel's C-statistic (Δ=0.112-0.114), with an IDI of 0.078-0.238 and an NRI of 20.1%-48.8% for AI-ECG vs. PCP-HF. Conclusions and Relevance: Across multinational cohorts, a noise-adapted AI model with lead I ECGs as the sole input defined HF risk, representing a scalable portable and wearable device-based HF risk-stratification strategy.

Salt Intake in Adults with Diabetes and Hypertension: The Longitudinal Study of Adult Health-Brasil Study.

Background and Objective: Hypertension and type-2 diabetes are strong risk factors for cardiovascular diseases, and their management requires lifestyle changes, including a shift in dietary habits. The consumption of salt has increased in the last decades in some countries, but its association with type-2 diabetes remains unknown. Thus, we aimed to estimate the amount of salt intake among adults with and without diabetes and to assess whether concomitant hypertension and diabetes are associated with higher salt intake. Methods: Data from 11,982 adults 35-74 years of age enrolled in the baseline of the Longitudinal Study of Adult Health-Brasil study (2008-2010) were studied. A clinical and anthropometric evaluation was performed, and their daily salt intake was estimated by the overnight 12-hr urine sodium excretion. Results: Salt intake (gram per day) was higher in participants with diabetes as compared with those without diabetes, regardless of sex (men: 14.2 ± 6.4 vs. 12.4 ± 5.6, P < 0.05; women: 10.5 ± 4.8 vs. 9.1 ± 4.1, P < 0.05). However, salt intake is high in participants with fasting glucose ≥126 mg/dL or HbA1c ≥6.5%, but not in participants with blood glucose 2 hr after the glucose tolerance test ≥200 mg/dL. When hypertension and diabetes coexisted, salt consumption was higher than among people without these conditions. The prevalence of hypertension increased with increasing salt intake in women with diabetes, but not in men with this condition. Conclusions: Our findings highlight the high consumption of salt in individuals with diabetes and/or hypertension, and the need for effective strategies to reduce salt consumption in these groups of increased risk for major cardiovascular events, especially in women.

Scalable Risk Stratification for Heart Failure Using Artificial Intelligence applied to 12-lead Electrocardiographic Images: A Multinational Study.

Background: Current risk stratification strategies for heart failure (HF) risk require either specific blood-based biomarkers or comprehensive clinical evaluation. In this study, we evaluated the use of artificial intelligence (AI) applied to images of electrocardiograms (ECGs) to predict HF risk. Methods: Across multinational longitudinal cohorts in the integrated Yale New Haven Health System (YNHHS) and in population-based UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), we identified individuals without HF at baseline. Incident HF was defined based on the first occurrence of an HF hospitalization. We evaluated an AI-ECG model that defines the cross-sectional probability of left ventricular dysfunction from a single image of a 12-lead ECG and its association with incident HF. We accounted for the competing risk of death using the Fine-Gray subdistribution model and evaluated the discrimination using Harrel's c-statistic. The pooled cohort equations to prevent HF (PCP-HF) were used as a comparator for estimating incident HF risk. Results: Among 231,285 individuals at YNHHS, 4472 had a primary HF hospitalization over 4.5 years (IQR 2.5-6.6) of follow-up. In UKB and ELSA-Brasil, among 42,741 and 13,454 people, 46 and 31 developed HF over a follow-up of 3.1 (2.1-4.5) and 4.2 (3.7-4.5) years, respectively. A positive AI-ECG screen portended a 4-fold higher risk of incident HF among YNHHS patients (age-, sex-adjusted HR [aHR] 3.88 [95% CI, 3.63-4.14]). In UKB and ELSA-Brasil, a positive-screen ECG portended 13- and 24-fold higher hazard of incident HF, respectively (aHR: UKBB, 12.85 [6.87-24.02]; ELSA-Brasil, 23.50 [11.09-49.81]). The association was consistent after accounting for comorbidities and the competing risk of death. Higher model output probabilities were progressively associated with a higher risk for HF. The model's discrimination for incident HF was 0.718 in YNHHS, 0.769 in UKB, and 0.810 in ELSA-Brasil. Across cohorts, incorporating model probability with PCP-HF yielded a significant improvement in discrimination over PCP-HF alone. Conclusions: An AI model applied to images of 12-lead ECGs can identify those at elevated risk of HF across multinational cohorts. As a digital biomarker of HF risk that requires just an ECG image, this AI-ECG approach can enable scalable and efficient screening for HF risk.

Life satisfaction and ideal cardiovascular health score: A cross-sectional study from ELSA-Brasil.

OBJECTIVES: To investigate whether higher levels of life satisfaction are associated with a higher ideal cardiovascular health (CVH) score in middle-aged and older populations in the Brazilian context. METHOD: Cross-sectional analysis of 12,936 participants of the Brazilian Longitudinal Study of Adult Health, Visit 2 (2012-2014), aged 38-79 years. The response variables were the global, lifestyle, and biological ideal CVH scores, as defined by the American Heart Association Life's Simple 7. The scores were categorized as low, intermediate, and optimal. Life satisfaction was measured by the Satisfaction with the Life Scale. Multinomial logistic regression was used to estimate the magnitude with adjustment for potential confounding factors. Low scores were the categories of reference for the analyses. RESULTS: Only 10.5% of the participants had an optimal (≥5) global ideal CVH score. After total adjustment, 1 SD increment in the life satisfaction score was associated with an odds ratio (OR) of 1.05 (95% confidence interval [CI: 1.01-1.09]) and 1.15 (95% CI [1.07-1.23]) for intermediate and optimal global ideal CVH scores, respectively. Regarding the lifestyle ideal CVH score, the increment of 1 SD in the life satisfaction scale determined an OR of 1.11 (95% CI [1.06-1.15]) and 1.22 (95% CI [1.14-1.31]) for intermediate and optimal lifestyle ideal CVH score, respectively. Life satisfaction was not associated with the biological ideal CVH score. CONCLUSION: The results suggested that the higher the life satisfaction, the higher the CVH. The findings add to the knowledge of assets to promote CVH. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Racial Inequities in the Control of Hypertension and the Explanatory Role of Residential Segregation: a Decomposition Analysis in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil).

The mechanisms underlying racial inequities in uncontrolled hypertension have been limited to individual factors. We investigated racial inequities in uncontrolled hypertension and the explanatory role of economic segregation in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). All 3897 baseline participants with hypertension (2008-2010) were included. Uncontrolled hypertension (SBP ≥ 140 mmHg or DBP ≥ 90 mmHg), self-reported race (White/Brown/Black people), and neighborhood economic segregation (low/medium/high) were analyzed cross-sectionally. We used decomposition analysis, which describes how much a disparity would change (disparity reduction; explained portion) and remain (disparity residual; unexplained portion) upon removing racial differences in economic segregation (i.e., if Black people had the distribution of segregation of White people, how much we would expect uncontrolled hypertension to decrease among Black people). Age- and gender-adjusted prevalence of uncontrolled hypertension (39.0%, 52.6%, and 54.2% for White, Brown, and Black participants, respectively) remained higher for Black and Brown vs White participants, regardless of economic segregation. Uncontrolled hypertension showed a dose-response pattern with increasing segregation levels for White but not for Black and Brown participants. After adjusting for age, gender, education, and study center, unexplained portion (disparity residual) of race on uncontrolled hypertension was 18.2% (95% CI 13.4%; 22.9%) for Black vs White participants and 12.6% (8.2%; 17.1%) for Brown vs White participants. However, explained portion (disparity reduction) through economic segregation was - 2.1% (- 5.1%; 1.3%) for Black vs White and 0.5% (- 1.7%; 2.8%) for Brown vs White participants. Although uncontrolled hypertension was greater for Black and Brown vs White people, racial inequities in uncontrolled hypertension were not explained by economic segregation.

Untangle the relationship of muscle mass and bone mineral content on handgrip strength: Results of ELSA-Brasil.

The study aims to investigate the independent association of muscle mass (MM) and bone mineral content (BMC) in the performance of the handgrip strength (HGS) test and whether there is effect modification by sex and age. In 12,491 participants from the ELSA-Brasil we estimated the associations between MM, BMC and HGS using linear regression models. All the analyses were performed for total population, also stratified for sex and age. For total population an interaction term was included between each explanatory variable of interest with sex and age to verify the presence of effect modification. We observed that the higher quintiles of MM and BMC were associated to an increasing in the mean of HGS compared to the first quintile, with greater magnitudes in men compared to women, also adults compared to elderly. When we estimated the independent effect of each exposure of interest, MM showed stronger effect in HGS in women, men and adults then BMC. In conclusion, we observed that higher amounts of MM and BMC are associated with higher HGS, regardless of sociodemographic characteristics, health conditions and lifestyle, with this effect being greater in men and adults.

Untangle the relationship of muscle mass and bone mineral content on handgrip strength: Results of ELSA-Brasil / Desvendando a relação entre massa muscular e conteúdo mineral ósseo na força de preensão palmar: Resultados do ELSA-Brasil

Abstract The study aims to investigate the independent association of muscle mass (MM) and bone mineral content (BMC) in the performance of the handgrip strength (HGS) test and whether there is effect modification by sex and age. In 12,491 participants from the ELSA-Brasil we estimated the associations between MM, BMC and HGS using linear regression models. All the analyses were performed for total population, also stratified for sex and age. For total population an interaction term was included between each explanatory variable of interest with sex and age to verify the presence of effect modification. We observed that the higher quintiles of MM and BMC were associated to an increasing in the mean of HGS compared to the first quintile, with greater magnitudes in men compared to women, also adults compared to elderly. When we estimated the independent effect of each exposure of interest, MM showed stronger effect in HGS in women, men and adults then BMC. In conclusion, we observed that higher amounts of MM and BMC are associated with higher HGS, regardless of sociodemographic characteristics, health conditions and lifestyle, with this effect being greater in men and adults.

Resumo O estudo tem como objetivo investigar a associação independente da massa muscular (MM) e conteúdo mineral ósseo (CMO) na realização do teste de força de preensão manual (FPM) e se há modificação do efeito por sexo e idade. Em 12.491 participantes do ELSA-Brasil estimamos as associações entre MM, CMO e FPM usando modelos de regressão linear. Todas as análises foram realizadas para a população total, também estratificada por sexo e idade. Para a população total foi incluído um termo de interação entre cada variável explicativa de interesse com sexo e idade para verificar a presença de modificação de efeito. Observamos que os maiores quintis de MM e BMC estiveram associados a um aumento na média da FPM em relação ao primeiro quintil, com maiores magnitudes em homens em relação a mulheres, também em adultos em relação a idosos. Quando estimamos o efeito independente de cada exposição de interesse, MM mostrou efeito mais forte na FPM em mulheres, homens e adultos do que BMC. Em conclusão, observamos que maiores quantidades de MM e BMC estão associadas a maior FPM, independentemente das características sociodemográficas, condições de saúde e estilo de vida, sendo esse efeito maior em homens e adultos.

The high salt intake in adults with metabolic syndrome is related to increased waist circumference and blood pressure: the Brazilian Longitudinal Study of Adult Health study (ELSA-Brasil).

OBJECTIVES: The association between metabolic syndrome (MetS), a cluster of cardiometabolic risk factors, and salt consumption has fed intense debate in recent years, although it is yet to be fully elucidated. We aimed to evaluate whether individuals with MetS have a high salt consumption and to identify which components of the MetS diagnosis could be independently related to high salt consumption. METHODS: We analyzed data from 11 982 adults, ages 35 to 74 y, from the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) cohort study, from which clinical and anthropometric data were assessed, and a validated 12-h overnight urine collection was used to estimate salt intake. MetS was defined according to the Adult Treatment Panel III criteria. RESULTS: Salt intake was increased in individuals with MetS compared with individuals without MetS, regardless of sex (men: 14.3 ± 6.4 g/d versus 12.2 ± 5.5 g/d, P < 0.001; women: 10.6 ± 4.9 g/d versus 8.9 ± 4.0 g/d, P < 0.001) and increased progressively as the MetS criteria accumulated. The high salt intake in MetS participants, however, was observed only in the presence of elevated waist circumference and/or blood pressure and not with the other MetS criteria (reduced high-density lipoprotein, increased triglycerides, and impaired fasting blood glucose), regardless of the presence of MetS. When diabetes was incorporated as a MetS criterion, increased salt intake was observed in men but not in women. CONCLUSIONS: Salt intake should be reduced worldwide, but strategies must be more intense in people with elevated blood pressure and waist circumference, regardless of MetS diagnosis, to avoid the associated morbidity and mortality.

Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images.

BACKGROUND: Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning-based approach that can use ECG images for the screening of LV systolic dysfunction. METHODS: Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction <40%. The model was validated within clinical settings at Yale New Haven Hospital and externally on ECG images from Cedars Sinai Medical Center in Los Angeles, CA; Lake Regional Hospital in Osage Beach, MO; Memorial Hermann Southeast Hospital in Houston, TX; and Methodist Cardiology Clinic of San Antonio, TX. In addition, it was validated in the prospective Brazilian Longitudinal Study of Adult Health. Gradient-weighted class activation mapping was used to localize class-discriminating signals on ECG images. RESULTS: Overall, 385 601 ECGs with paired echocardiograms were used for model development. The model demonstrated high discrimination across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROCs], 0.91; area under precision-recall curve [AUPRC], 0.55); and external sets of ECG images from Cedars Sinai (AUROC, 0.90 and AUPRC, 0.53), outpatient Yale New Haven Hospital clinics (AUROC, 0.94 and AUPRC, 0.77), Lake Regional Hospital (AUROC, 0.90 and AUPRC, 0.88), Memorial Hermann Southeast Hospital (AUROC, 0.91 and AUPRC 0.88), Methodist Cardiology Clinic (AUROC, 0.90 and AUPRC, 0.74), and Brazilian Longitudinal Study of Adult Health cohort (AUROC, 0.95 and AUPRC, 0.45). An ECG suggestive of LV systolic dysfunction portended >27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3-33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V2 and V3), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3-4.7]; median follow-up, 3.2 years). CONCLUSIONS: We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings.

Fasting Glucose, Glycated Hemoglobin, and 2h Post-load Blood Glucose Are Independently Associated With Arterial Stiffness in Diabetes: The ELSA-Brasil Study.

The association of diabetes with increased large artery stiffness is not definitively established. We aimed to describe the carotid-femoral pulse wave velocity (cf-PWV) in participants with and without diabetes and whether the cf-PWV could vary among the different laboratory-based criteria used. A cross-sectional analysis using baseline data from 13,912 adults was used. cf-PWV as well as anthropometric, biochemical, and clinical data were measured. Diabetes was defined by previous medical diagnosis, medication use, fasting glucose, an oral glucose tolerance test (GTT), or glycated hemoglobin (HbA1c). The prevalence of diabetes was 18.7%, higher in men than in women. After adjustment, participants with diabetes showed higher cf-PWV (men: 9.7 ± 1.7 vs 9.4 ± 1.7 m/s, P < .05; women: 9.4 ± 1.6 vs 9.1 ± 1.7 m/s, P < .05). We observed a progressive increase in cf-PWV as >1 laboratory-based criterion for diabetes diagnosis was reached. Also, participants with diabetes with alterations in any laboratory-based criteria had higher cf-PWV than participants without diabetes, regardless of sex. In summary, diabetes is associated with higher cf-PWV as is each laboratory-based parameter used for its diagnosis. These results support the strong consequences of glucose dysregulation on the vascular system and provide evidence to screen all parameters involved in glycemic metabolism to improve vascular health.

Birth weight is related with bone mineral content in adulthood: results of ELSA-Brasil.

OBJECTIVE: To investigate the association between birth weight and bone mineral content (BMC), and whether this relationship differs between men and women. METHODS: A total of 10,159 participants from the ELSA-Brasil cohort were eligible for this analysis. The outcome was the z-score of the ratio BMC (kg)/height (m). The exposure was the low birth weight (< 2.5kg). The magnitude of the associations was estimated by mean differences and their respective 95% confidence intervals (95%CI) using linear regression. All analyses were presented for the total population and stratified by sex. RESULTS: Most were women (54.98%), and the mean age was 52.72 years (SD ± 6.6). In the crude model, we observed that low birth weight was associated with a lower mean BMC/height z-score, compared to adequate birth weight (mean difference: -0.30; 95%CI: -0.39 to -0.21), and this effect was stronger in men (mean difference: -0.43; 95%CI: -0.56 to -0.30) than in women (mean difference: -0.31; 95%CI: -0.44 to -0.19). After adjusting for age, sex per total population, race/skin color, maternal education, individual education, and current weight, there was a considerable reduction in the magnitude of the association (total population: -0.10; 95%CI: -0.14 to -0.06; men: -0.13; 95%CI: -0.21 to -0.06; women: -0.13; 95%CI: -0.21 to -0.05). CONCLUSION: Low birth weight is related to BMC/height z-score in both sexes with no indication of differences by sex. The magnitude of the associations was attenuated after adjustment for the current weight.

Volume de Gordura Epicárdica está Associada com Disfunção Endotelial, mas Não com Calcificação Coronariana: Do ELSA-Brasil / Epicardial Fat Volume Is Associated with Endothelial Dysfunction, but not with Coronary Calcification: From the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil)

Resumo Fundamento O aumento no volume de gordura epicárdica (VGE) está relacionado com doença arterial coronariana (DAC), independentemente de gordura visceral ou subcutânea. O mecanismo dessa associação não é claro. O escore de cálcio coronariano (CC) e a disfunção endotelial estão relacionados com eventos coronarianos, mas não está bem esclarecido se o VGE está relacionado com esses marcadores. Objetivos Avaliar a associação entre VGE medido por método automatizado, fatores de risco cardiovasculares, escore de CC, e função endotelial. Métodos: Em 470 participantes do Estudo Longitudinal de Saúde do Adulto LSA-Brasil com medidas de VGE, escore de CC e função endotelial, realizamos modelos multivariados para avaliar a relação entre fatore de risco cardiovascular e VGE (variável resposta), e entre VGE (variável explicativa), e função endotelial ou escore de CC. Valor de p<0,05 bilateral foi considerado estatisticamente significativo. Resultados A idade média foi 55 ± 8 anos, e 52,3% dos pacientes eram homens. O VGE médio foi 111mL (86-144), e a prevalência de escore de CC igual a zero foi 55%. Nas análises multivariadas, um VGE mais alto relacionou-se com sexo feminino, idade mais avançada, circunferência da cintura, e triglicerídeos (p<0,001 para todos). Um VGE mais alto foi associado com pior função endotelial: em comparação ao primeiro quartil, os valores de odds ratio para a amplitude de pulso basal foram (q2=1,22; IC95% 1,07-1,40; q3=1,50, IC95% 1,30-1,74; q4=1,50, IC95% 1,28-1,79) e para a razão de tonometria arterial periférica foram (q2=0,87; IC95% 0,81-0,95; q3=0,86, IC95% 0,79-0,94; q4=0,80, IC95% 0,73-0,89), mas não com escore de CC maior que zero. Conclusão Um VGE mais alto associou-se com comprometimento da função endotelial, mas não com escore de CC. Os resultados sugerem que o VGE esteja relacionado ao desenvolvimento de DAC por uma via diferente da via do CC, possivelmente pela piora da disfunção endotelial e doença microvascular.

Abstract Background The increase in epicardial fat volume (EFV) is related to coronary artery disease (CAD), independent of visceral or subcutaneous fat. The mechanism underlying this association is unclear. Coronary artery calcium (CAC) score and endothelial dysfunction are related to coronary events, but whether EFV is related to these markers needs further clarification. Objectives To evaluate the association between automatically measured EFV, cardiovascular risk factors, CAC, and endothelial function. Methods In 470 participants from the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) with measures of EFV, CAC score and endothelial function, we performed multivariable models to evaluate the relation between cardiovascular risk factors and EFV (response variable), and between EFV (explanatory variable) and endothelial function variables or CAC score. Two-sided p <0.05 was considered statistically significant. Results Mean age was 55 ± 8 years, 52.3% of patients were men. Mean EFV was 111mL (IQ 86-144), and the prevalence of CAC score=0 was 55%. In the multivariable analyses, increased EFV was related to female sex, older age, waist circumference, and triglycerides (p<0.001 for all). Higher EFV was associated with worse endothelial function: as compared with the first quartile, the odds ratio for basal pulse amplitude were (q2=1.22, 95%CI 1.07-1.40; q3=1.50, 95%CI 1.30-1.74; q4=1.50, 95%CI 1.28-1.79) and for peripheral arterial tonometry ratio were (q2=0.87, 95%CI 0.81-0.95; q3=0.86, 95%CI 0.79-0.94; q4=0.80, 95%CI 0.73-0.89), but not with CAC score>0. Conclusion Higher EFV was associated with impaired endothelial function, but not with CAC. The results suggest that EFV is related to the development of CAD through a pathway different from the CAC pathway, possibly through aggravation of endothelial dysfunction and microvascular disease.

Saúde Cardiovascular e Fibrilação ou Flutter Atrial: Um Estudo Transversal do ELSA-Brasil / Cardiovascular Health and Atrial Fibrillation or Flutter: A Cross-Sectional Study from ELSA-Brasil

Resumo Fundamento A associação entre o status de saúde cardiovascular ideal ( ideal cardiovascular health ( ICVH) e diagnóstico de fibrilação ou flutter atrial (FFA) foi menos estudado em comparação a outras doenças cardiovasculares. Objetivos Analisar a associação entre o diagnóstico de FFA e métricas e escores de ICVH no Estudo Longitudinal de Saúde do Adulto (ELSA-Brasil). Métodos Este estudo analisou dados de 13141 participantes com dados completos. Os traçados eletrocardiográficos foram codificados de acordo com o Sistema de Minnesota, em um centro de leitura centralizado. As métricas do ICVH (dieta, atividade física, índice de massa corporal, tabagismo, glicemia de jeju, e colesterol total) e escores do ICVH foram calculados conforme proposto pela American Heart Association . Modelos de regressão logística bruta e ajustada foram construídos para analisar associações de métricas e escores do ICVH com diagnóstico de FFA. O nível de significância foi estabelecido em 0,05. Resultados A idade mediana da amostra foi de 55 anos, e 54,4% eram mulheres. Nos modelos ajustados, os escores de ICVH não apresentaram associação significativa com diagnóstico de FFA prevalente [odds ratio (OR):0,96; intervalo de confiança de 95% (IC95%):0,80-1,16; p=0,70). Perfis de pressão arterial ideal (OR:0,33; IC95%:0,1-0,74; p=0,007) e colesterol total ideal (OR:1,88; IC95%:1,19-2,98; p=0,007) foram significativamente associados com o diagnóstico de FFA. Conclusões Não foram identificadas associações significativas entre escores de ICVH global e diagnóstico de FFA após ajuste multivariado em nossas análises, devido, ao menos em parte, às associações antagônicas da FFA com métricas de pressão arterial e de colesterol total do ICVH. Nossos resultados sugerem que estimar a prevenção da FFA por meio de escore de ICVH global pode não ser adequado, e as métricas do ICVH devem ser consideradas separadamente.

Abstract Background The association between ideal cardiovascular health (ICVH) status and atrial fibrillation or flutter (AFF) diagnosis has been less studied compared to other cardiovascular diseases. Objective To analyze the association between AFF diagnosis and ICVH metrics and scores in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Methods This study analyzed data from 13,141 participants with complete data. Electrocardiographic tracings were coded according to the Minnesota Coding System, in a centralized reading center. ICVH metrics (diet, physical activity, body mass index, smoking, blood pressure, fasting plasma glucose, and total cholesterol) and scores were calculated as proposed by the American Heart Association. Crude and adjusted binary logistic regression models were built to analyze the association of ICVH metrics and scores with AFF diagnosis. Significance level was set at 0.05. Results The sample had a median age of 55 years and 54.4% were women. In adjusted models, ICVH scores were not significantly associated with prevalent AFF diagnosis (odds ratio [OR]:0.96; 95% confidence interval [95% CI]:0.80-1.16; p=0.70). Ideal blood pressure (OR:0.33; 95% CI:0.15-0.74; p=0.007) and total cholesterol (OR:1.88; 95% CI:1.19-2.98; p=0.007) profiles were significantly associated with AFF diagnosis. Conclusions No significant associations were identified between global ICVH scores and AFF diagnosis after multivariable adjustment in our analyses, at least partially due to the antagonistic associations of AFF with blood pressure and total cholesterol ICVH metrics. Our results suggest that estimating the prevention of AFF burden using global ICVH scores may not be adequate, and ICVH metrics should be considered in separate.

Epicardial Fat Volume Is Associated with Endothelial Dysfunction, but not with Coronary Calcification: From the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). / Volume de Gordura Epicárdica está Associada com Disfunção Endotelial, mas Não com Calcificação Coronariana: Do ELSA-Brasil.

BACKGROUND: The increase in epicardial fat volume (EFV) is related to coronary artery disease (CAD), independent of visceral or subcutaneous fat. The mechanism underlying this association is unclear. Coronary artery calcium (CAC) score and endothelial dysfunction are related to coronary events, but whether EFV is related to these markers needs further clarification. OBJECTIVES: To evaluate the association between automatically measured EFV, cardiovascular risk factors, CAC, and endothelial function. METHODS: In 470 participants from the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) with measures of EFV, CAC score and endothelial function, we performed multivariable models to evaluate the relation between cardiovascular risk factors and EFV (response variable), and between EFV (explanatory variable) and endothelial function variables or CAC score. Two-sided p <0.05 was considered statistically significant. RESULTS: Mean age was 55 ± 8 years, 52.3% of patients were men. Mean EFV was 111mL (IQ 86-144), and the prevalence of CAC score=0 was 55%. In the multivariable analyses, increased EFV was related to female sex, older age, waist circumference, and triglycerides (p<0.001 for all). Higher EFV was associated with worse endothelial function: as compared with the first quartile, the odds ratio for basal pulse amplitude were (q2=1.22, 95%CI 1.07-1.40; q3=1.50, 95%CI 1.30-1.74; q4=1.50, 95%CI 1.28-1.79) and for peripheral arterial tonometry ratio were (q2=0.87, 95%CI 0.81-0.95; q3=0.86, 95%CI 0.79-0.94; q4=0.80, 95%CI 0.73-0.89), but not with CAC score>0. CONCLUSION: Higher EFV was associated with impaired endothelial function, but not with CAC. The results suggest that EFV is related to the development of CAD through a pathway different from the CAC pathway, possibly through aggravation of endothelial dysfunction and microvascular disease.

FUNDAMENTO: O aumento no volume de gordura epicárdica (VGE) está relacionado com doença arterial coronariana (DAC), independentemente de gordura visceral ou subcutânea. O mecanismo dessa associação não é claro. O escore de cálcio coronariano (CC) e a disfunção endotelial estão relacionados com eventos coronarianos, mas não está bem esclarecido se o VGE está relacionado com esses marcadores. OBJETIVOS: Avaliar a associação entre VGE medido por método automatizado, fatores de risco cardiovasculares, escore de CC, e função endotelial. Métodos: Em 470 participantes do Estudo Longitudinal de Saúde do Adulto LSA-Brasil com medidas de VGE, escore de CC e função endotelial, realizamos modelos multivariados para avaliar a relação entre fatore de risco cardiovascular e VGE (variável resposta), e entre VGE (variável explicativa), e função endotelial ou escore de CC. Valor de p<0,05 bilateral foi considerado estatisticamente significativo. RESULTADOS: A idade média foi 55 ± 8 anos, e 52,3% dos pacientes eram homens. O VGE médio foi 111mL (86-144), e a prevalência de escore de CC igual a zero foi 55%. Nas análises multivariadas, um VGE mais alto relacionou-se com sexo feminino, idade mais avançada, circunferência da cintura, e triglicerídeos (p<0,001 para todos). Um VGE mais alto foi associado com pior função endotelial: em comparação ao primeiro quartil, os valores de odds ratio para a amplitude de pulso basal foram (q2=1,22; IC95% 1,07-1,40; q3=1,50, IC95% 1,30-1,74; q4=1,50, IC95% 1,28-1,79) e para a razão de tonometria arterial periférica foram (q2=0,87; IC95% 0,81-0,95; q3=0,86, IC95% 0,79-0,94; q4=0,80, IC95% 0,73-0,89), mas não com escore de CC maior que zero. CONCLUSÃO: Um VGE mais alto associou-se com comprometimento da função endotelial, mas não com escore de CC. Os resultados sugerem que o VGE esteja relacionado ao desenvolvimento de DAC por uma via diferente da via do CC, possivelmente pela piora da disfunção endotelial e doença microvascular.

Cardiovascular Health and Atrial Fibrillation or Flutter: A Cross-Sectional Study from ELSA-Brasil. / Saúde Cardiovascular e Fibrilação ou Flutter Atrial: Um Estudo Transversal do ELSA-Brasil.

BACKGROUND: The association between ideal cardiovascular health (ICVH) status and atrial fibrillation or flutter (AFF) diagnosis has been less studied compared to other cardiovascular diseases. OBJECTIVE: To analyze the association between AFF diagnosis and ICVH metrics and scores in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). METHODS: This study analyzed data from 13,141 participants with complete data. Electrocardiographic tracings were coded according to the Minnesota Coding System, in a centralized reading center. ICVH metrics (diet, physical activity, body mass index, smoking, blood pressure, fasting plasma glucose, and total cholesterol) and scores were calculated as proposed by the American Heart Association. Crude and adjusted binary logistic regression models were built to analyze the association of ICVH metrics and scores with AFF diagnosis. Significance level was set at 0.05. RESULTS: The sample had a median age of 55 years and 54.4% were women. In adjusted models, ICVH scores were not significantly associated with prevalent AFF diagnosis (odds ratio [OR]:0.96; 95% confidence interval [95% CI]:0.80-1.16; p=0.70). Ideal blood pressure (OR:0.33; 95% CI:0.15-0.74; p=0.007) and total cholesterol (OR:1.88; 95% CI:1.19-2.98; p=0.007) profiles were significantly associated with AFF diagnosis. CONCLUSIONS: No significant associations were identified between global ICVH scores and AFF diagnosis after multivariable adjustment in our analyses, at least partially due to the antagonistic associations of AFF with blood pressure and total cholesterol ICVH metrics. Our results suggest that estimating the prevention of AFF burden using global ICVH scores may not be adequate, and ICVH metrics should be considered in separate.

FUNDAMENTO: A associação entre o status de saúde cardiovascular ideal ( ideal cardiovascular health ( ICVH) e diagnóstico de fibrilação ou flutter atrial (FFA) foi menos estudado em comparação a outras doenças cardiovasculares. OBJETIVOS: Analisar a associação entre o diagnóstico de FFA e métricas e escores de ICVH no Estudo Longitudinal de Saúde do Adulto (ELSA-Brasil). MÉTODOS: Este estudo analisou dados de 13141 participantes com dados completos. Os traçados eletrocardiográficos foram codificados de acordo com o Sistema de Minnesota, em um centro de leitura centralizado. As métricas do ICVH (dieta, atividade física, índice de massa corporal, tabagismo, glicemia de jeju, e colesterol total) e escores do ICVH foram calculados conforme proposto pela American Heart Association . Modelos de regressão logística bruta e ajustada foram construídos para analisar associações de métricas e escores do ICVH com diagnóstico de FFA. O nível de significância foi estabelecido em 0,05. RESULTADOS: A idade mediana da amostra foi de 55 anos, e 54,4% eram mulheres. Nos modelos ajustados, os escores de ICVH não apresentaram associação significativa com diagnóstico de FFA prevalente [odds ratio (OR):0,96; intervalo de confiança de 95% (IC95%):0,80-1,16; p=0,70). Perfis de pressão arterial ideal (OR:0,33; IC95%:0,1-0,74; p=0,007) e colesterol total ideal (OR:1,88; IC95%:1,19-2,98; p=0,007) foram significativamente associados com o diagnóstico de FFA. CONCLUSÕES: Não foram identificadas associações significativas entre escores de ICVH global e diagnóstico de FFA após ajuste multivariado em nossas análises, devido, ao menos em parte, às associações antagônicas da FFA com métricas de pressão arterial e de colesterol total do ICVH. Nossos resultados sugerem que estimar a prevenção da FFA por meio de escore de ICVH global pode não ser adequado, e as métricas do ICVH devem ser consideradas separadamente.

Increased Prevalence of Depression and Anxiety Among Subjects With Metabolic Syndrome in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil).

BACKGROUND: Metabolic syndrome (MetS) and common mental disorders are prevalent conditions. However, the relationship of MetS and its components with depression, anxiety, and common mental disorders has not been sufficiently addressed in low-/middle-income countries. OBJECTIVE: To investigate whether depression, anxiety, and common mental disorders are associated with MetS and its components in the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). METHODS: A cross-sectional analysis of the ELSA-Brasil baseline visit (2008-2010) was performed. Adults without cardiovascular diseases had their MetS status defined by the National Cholesterol Education Program's Adult Treatment Panel III criteria. We assessed mental disorders using the Clinical Interview Schedule-Revised. We employed multiple logistic regression models adjusted for sociodemographic and behavioral factors. The dependent variables were mental disorders, and the independent variables were MetS and its components. We also performed analyses stratified by age and gender. RESULTS: Our sample included 12,725 participants (54.9% women, mean age of 51.8 ± 8.9 y). MetS and depressive disorders were significantly associated (odds ratio [OR] = 1.55, 95% confidence interval [CI] 1.30-1.85). Increased abdominal circumference (OR = 1.54, 95% CI 1.29-1.84), diabetes mellitus (OR = 1.24, 95% CI 1.02-1.50), hypertriglyceridemia (OR = 1.33, 95% CI 1.11-1.60), and low high-density lipoprotein cholesterol (only when adjusted for sociodemographic factors) (OR = 1.25, 95% CI 1.02-1.52) were also associated with depression. This association remained significant for all stratified analyses. Finally, MetS was also significantly associated with anxiety disorders (OR = 1.19, 95% CI 1.07-1.32) and common mental disorders (OR = 1.27, 95% CI 1.17-1.39). CONCLUSIONS: Our cross-sectional findings suggested that depression, anxiety, and common mental disorder are associated with MetS. Depression was also associated with abdominal obesity, elevated blood glucose, elevated triglycerides, and reduced high-density lipoprotein cholesterol, but not with hypertension.