BACKGROUND:ECG-based artificial intelligence may enable efficient prediction of incident heart failure (HF) risk to facilitate preventive efforts. Prior models are proprietary, with modest or inconsistent accuracy. We sought to develop and validate a generalizable and publicly available convolutional neural network to predict incident HF using the 12-lead ECG waveform (ECG-to-HF [ECG2HF]). METHODS:We developed ECG2HF in 94 636 patients receiving longitudinal ambulatory care at Massachusetts General Hospital (MGH), and validated it in 3 test sets: MGH, Brigham and Women's Hospital (BWH), and Beth Israel Deaconess Medical Center (BIDMC), among 93 868 individuals aged 30 to 79 years without HF. HF events at 10 years were identified using a validated electronic health record-based natural language processing model. Discrimination was quantified using the area under the receiver operating characteristic curve. We then compared discrimination and net reclassification (at <10%, 10% to 20%, ≥20% 10-year risk categories) using ECG2HF versus the 15-component Pooled Cohorts Equations to Prevent HF score. RESULTS:The test sets comprised MGH (13 954 individuals, 441 events, age 57±13 years, 48% women), BWH (54 396 individuals, 1809 events, age 57±13 years, 55% women), and BIDMC (25 457 individuals, 901 events, age 57±13 years, 53% women). Over 10 years, the cumulative risk of HF was 4.6% (95% CI, 4.1-5.0) in MGH, 5.0% (4.8-5.2) in BWH, and 4.4% (4.1-4.7) in BIDMC. ECG2HF discriminated 10-year incident HF in each test set (area under the receiver operating characteristic curve: MGH 0.86 [0.84-0.87]; BWH 0.85 [0.84-0.86]; BIDMC 0.84 [0.83-0.86]). Compared with the Pooled Cohorts Equations to Prevent HF, ECG2HF provided favorable discrimination (improvement in area under the receiver operating characteristic curve MGH/BWH 0.061 [0.025-0.097]; BIDMC 0.038 [-0.0096 to 0.086]) and net reclassification (NRI MGH/BWH 0.16 [0.077-0.24]; BIDMC 0.23 [0.10-0.35]) of 10-year HF risk. CONCLUSIONS:ECG2HF is a publicly available 12-lead ECG-based artificial intelligence model that discriminates the risk of future HF with favorable and consistent performance across 3 large health care samples from the northeastern United States. ECG2HF may enable efficient prioritization of high-risk individuals for HF-related preventive measures.

BACKGROUND:Stressor-associated atrial fibrillation (AF) refers to new-onset AF that occurs with a reversible, acute stressor. Identifying individuals at highest risk for AF recurrence is essential to guide management. Although clinical factors have shown limited value, the utility of contemporary artificial intelligence (AI)-enabled models using the 12-lead ECG to estimate recurrence risk remains unknown. METHODS:We retrospectively analyzed consecutive primary care and cardiology patients with stressor-associated AF occurring during hospitalization. We quantified the cumulative incidence of recurrence accounting for death as a competing risk. We investigated the relationship between time-varying recurrence and a composite end point of AF-related adverse events (stroke, heart failure, all-cause death) using Cox models. We then developed and validated a penalized regression model to predict recurrence using clinical factors, stressor type, and AF risk estimates from a previously validated ECG-based AI model. RESULTS:We analyzed 3371 patients with stressor-associated AF (mean age, 69±12 years; 40% women). Over a median of 3.7 years (interquartile range, 1.8-7.2), the 10-year cumulative incidence of AF recurrence was 41% (95% CI, 39-44). AF recurrence was strongly associated with AF-related adverse events (hazard ratio, 2.24 [95% CI, 1.81-2.76]). A model incorporating clinical factors, stressor type, and ECG-based AI model AF risk estimates (clinical-AI) discriminated AF recurrence (area under the receiver operating characteristic curve, 0.768 [95% CI, 0.707-0.830]) favorably compared with clinical features (area under the receiver operating characteristic curve, 0.707 [95% CI, 0.642-0.772]; P<0.05). CONCLUSIONS:AF recurrence rates following stressor-associated AF are considerable and are associated with substantially higher risk of adverse cardiovascular events. Models incorporating ECG-based AI risk estimates may prioritize individuals for intensive monitoring and preventive interventions.

Background:The epidemiology of permanent pacemaker [PPM] implantation in the community setting is unclear. Methods:We examined Framingham Heart Study cohort participants aged ≥45 years, without a history of PPM, who attended ≥1 exam cycle during 1972-2019. Fine-Gray subdistribution hazard models were used to calculate subdistribution hazard ratios [sHR] and 95% confidence intervals [CI] for the association between clinical characteristics (age, sex, body mass index [BMI], systolic and diastolic blood pressure [BP], smoking, hypertension treatment, diabetes, history of atrial fibrillation [AF], myocardial infarction, and heart failure) and incident PPM implantation. For continuous measures, sHRs were expressed per 1 standard deviation [SD]. Multiple imputation was used to account for missing data. Results:A total of 11,993 participants contributed 44,711 exam cycles (mean age 63 ± 11 years, 56% women) to the analysis. During follow-up (mean 4.9 ± 2.2 years), there were 382 PPM implantations and 4298 deaths. In multivariable-adjusted models, the following factors were associated with incident PPM implantation: age (sHR [per 1 SD = 11 years] =1.39), female sex (sHR = 0.49), BMI (sHR [per 1 SD = 5.1 kg/m2] =1.17), higher systolic BP (sHR [per 1 SD = 20 mmHg] =1.46), lower diastolic BP (sHR [per 1 SD = 10 mmHg] = 0.68), hypertension treatment (sHR = 1.40), smoking (sHR = 0.59), and history of AF (sHR = 2.60). Conclusions:Higher age, BMI, systolic BP, hypertension treatment, and history of AF were associated with increased rate of PPM implantation, while female sex, smoking, and diastolic BP showed an inverse association. Further study is needed to confirm these findings.

Background:Atrial fibrillation (AF) is linked to adverse left atrial (LA) remodeling, including fibrosis and mechanical dysfunction. LA strain is an imaging marker of atrial function that may improve risk stratification for AF, but its predictive and prognostic value in the primary care population remains unclear. Objective:This study aimed to evaluate whether LA strain is associated with new-onset AF and adverse clinical outcomes after AF diagnosis. Methods:We performed a 2-part study within a longitudinal primary care cohort (2001-2019). In a nested case-control analysis, 216 patients with new-onset AF were compared with 216 age- and sex-matched controls. LA strain parameters, including peak atrial longitudinal strain (PALS), peak atrial contractile strain, and LA conduit strain (LACS), were measured using speckle-tracking echocardiography before AF onset. In 127 patients with new-onset AF, Cox models examined associations between LA strain and all-cause mortality, stroke, myocardial infarction, and heart failure hospitalization. Results:Lower PALS and LACS were independently associated with more than 3-fold higher odds of AF (both P < .001). Addition of strain measures to the LA volume index improved discrimination (area under the curve 0.66-0.73 for PALS; 0.72 for LACS). Over 4.6 years of follow-up, lower PALS remained independently associated with all-cause mortality (HR 2.70; P = .02) and the composite outcome (HR 2.31; P = .02). Conclusion:In a primary care cohort, impaired LA strain was independently associated with new-onset AF and adverse outcomes after AF diagnosis, supporting its role in AF risk stratification.

BACKGROUND:Accurate prediction of incident heart failure (HF) may help prioritize HF preventive therapies. Deep learning interpretation of echocardiograms may improve HF risk prediction beyond clinical risk models. We trained and validated a deep learning model to predict incident HF from transthoracic echocardiographic images (Echocardiogram-to-Heart Failure, or "Echo2HF") METHODS: Echo2HF was developed using 4,057,664 echocardiogram videos from 70,763 patients receiving longitudinal ambulatory care at Massachusetts General Hospital (MGH). Performance for 10-year incident HF was evaluated in an internal MGH test set and an external test set of 34,802 individuals without prevalent HF from Brigham and Women's Hospital (BWH). Model performance was evaluated using the area under the receiver operating characteristic curve and compared with the Pooled Cohorts Equations to Prevent Heart Failure and the Predicting Risk of cardiovascular disease EVENTs clinical risk scores. RESULTS:Echo2HF was trained in 64,167 individuals and evaluated in a hold-out sample of 6394 individuals from MGH (279 HF events, age 62 ± 17 years, 48% women) and 34,802 individuals from BWH (1280 events, age 62 ± 15 years, 56% women). Echo2HF discriminated incident HF, with 10-year area under the receiver operating characteristic curve of 0.84 (95% confidence interval 0.81-0.87) and 0.84 (95% confidence interval 0.82-0.85) at BWH, with numerically greater discrimination vs both Pooled Cohorts Equations to Prevent Heart Failure and Predicting Risk of cardiovascular disease EVENTs. CONCLUSION:Deep learning analysis of echocardiograms accurately discriminated future HF risk, with favorable performance over current clinical HF scores. Future work should assess whether broader use of artificial intelligence-enabled echocardiographic risk stratification may improve HF prevention and clinical outcomes, including among individuals who do not have a clinical indication for echocardiography.

Background Screening for atrial fibrillation (AF) may lead to earlier detection and initiation of preventive measures. Current AF screening approaches using a guideline age-based threshold of ≥65 years have shown limited yield. Objectives In an AF screening trial, we assessed whether the screening effect was larger among individuals at elevated AF risk using validated clinical and electrocardiogram (ECG)-based artificial intelligence (AI) risk models. Methods VITAL-AF was a cluster-randomized trial of patients aged ≥65 years treated at 1 of 16 primary care practices affiliated with Massachusetts General Hospital. Patients randomized to a screening practice were screened using a single-lead ECG. Among VITAL-AF participants without prevalent AF with at least one 12-lead ECG within 3 years before enrollment, we estimated AF risk using 3 validated models derived outside of VITAL-AF: the Cohorts of Heart and Aging Research in Genomic Epidemiology-AF (CHARGE-AF) clinical score, an AI-based model using a 12-lead ECG alone (ECG-AI), and a model combining ECG-AI and CHARGE-AF (CH-AI). Two-year incident AF discrimination was assessed by the time-dependent area under the receiver-operating characteristic curve (AUROC) and average precision. AF screening effect was defined as the difference in 2-year incident AF diagnosis rate (per 100 person-years) in screening vs control across AF risk deciles. Results Of 30,630 VITAL-AF participants without prevalent AF, 16,937 had pretrial ECG and clinical data. Each score discriminated 2-year AF risk according to AUROC (CHARGE-AF: 0.711 [95% CI: 0.671-0.749]; ECG-AI: 0.784 [95% CI: 0.743-0.819]; CH-AI: 0.788 [95% CI: 0.754-0.824]) and average precision (0.0952 [95% CI: 0.0836-0.112]; 0.132 [95% CI: 0.113-0.157]; 0.133 [95% CI: 0.117-0.159]). An AF screening effect was observed in the top decile of CH-AI (AF diagnosis rate in screening 10.07/100 person-years [95% 8.28-11.87] vs 7.76 [95% 6.30-9.21] in control, P < 0.05), corresponding to a difference in AF diagnosis rate of 2.32/100 person-years (95% CI: 0.01-4.63) and number-needed-to-screen of 43 per year. Conclusions Use of ECG-based AI and clinical factors identified individuals at particularly high risk for AF who may benefit from screening. Findings suggest a trade-off between increasing AF screening efficiency and decreasing population coverage (ie, restriction of the screening pool). Future studies are needed to determine whether a risk-based approach is optimal or whether consideration of additional clinical- and systems-level factors (eg, access, health care system engagement) can further refine AF screening strategies. (Screening for Atrial Fibrillation Among Older Patients in Primary Care Clinics [VITAL-AF]; NCT03515057)

Purpose Atrial fibrillation (AF) care has shifted dramatically, with a focus on early rhythm control to reduce AF-related morbidity and mortality and improve quality of life. However, clinical trials for AF rely on historical definitions of treatment failure, including freedom from recurrence of ≥30 seconds of AF/flutter/tachycardia, which is a poor predictor of AF severity, or traditional clinical endpoints (ie, stroke, heart failure, death) which have low incidence in contemporary AF populations. Therefore, a directly measurable and clinically meaningful measure for these clinical endpoints has the potential to accelerate clinical trials of rhythm control in AF while reducing overall trial overhead. Results The Cardiovascular Sciences Research Consortium hosted a Think Tank comprising scientists, clinicians, regulators, and industry representatives to develop a roadmap to establish AF burden as a valid surrogate clinical endpoint. This document reviews currently available data to support the use of AF burden as a surrogate endpoint, provides standards for measuring AF burden across measurement modalities and devices, and establishes a practical roadmap for a collaborative approach to validating the use of AF burden. Conclusion Moving beyond historical definitions of AF treatment success and failure, AF burden has the potential to be a patient-centric endpoint that can leverage contemporary monitoring technologies while serving as an early signifier of AF-related risk.

Rare coding genetic variants may exert large effects on risk of common disease, yet their contribution to disease architecture and their utility in gene prioritization remain limited by inadequate sample sizes. Here, we performed a massive-scale rare variant association study (RVAS), analyzing over 1.1 million sequenced participants among which 130,000 had atrial fibrillation (AF). Through a multi-mask burden testing approach, we identified 15 genes significantly associated with AF through rare large-effect variation. Integrative analyses revealed strong convergence between genes implicated by rare and common variation, and highlighted instances where RVAS data may aid in GWAS prioritization. Nevertheless, several RVAS genes were not among GWAS loci ( FAM189A2 , ACTC1 , FNIP1 , FBN1 ), or were not nominated through contemporary GWAS prioritization ( KDM5B , ZFP36L2 ). Finally, we observed that ultra-rare protein-disrupting variants - concentrated in a small number of large-effect size genes - explained at least 2% of AF susceptibility across European and African ancestry groups. These findings refine the genetic architecture of AF, while highlighting the value and cost of RVAS for genomic discovery in common disease.

To broaden our understanding of bradyarrhythmias and conduction disease, we performed common variant genome-wide association analyses in up to 1.3 million individuals and rare variant burden testing in 460,000 individuals for sinus node dysfunction (SND), distal conduction disease (DCD) and pacemaker (PM) implantation. We identified 13, 31 and 21 common variant loci for SND, DCD and PM, respectively. Four well-known loci (SCN5A/SCN10A, CCDC141, TBX20 and CAMK2D) were shared for SND and DCD, while others were more specific for SND or DCD. SND and DCD showed a moderate genetic correlation (rg = 0.63). Cardiomyocyte-expressed genes were enriched for contributions to DCD heritability. Rare-variant analyses implicated LMNA for all bradyarrhythmia phenotypes, SMAD6 and SCN5A for DCD and TTN, MYBPC3 and SCN5A for PM. These results show that variation in multiple genetic pathways (for example, ion channel function, cardiac developmental programs, sarcomeric structure and cellular homeostasis) appear critical to the development of bradyarrhythmias. Genome-wide analyses identify variants associated with sinus node dysfunction, distal conduction disease and pacemaker implantation, implicating ion channel function, cardiac developmental programs and sarcomeric structure in bradyarrhythmia susceptibility.

Atrial fibrillation (AF) is a prevalent and morbid abnormality of the heart rhythm with a strong genetic component. Here, we meta-analyzed genome and exome sequencing data from 36 studies that included 52,416 AF cases and 277,762 controls. In burden tests of rare coding variation, we identified novel associations between AF and the genes MYBPC3, LMNA, PKP2, FAM189A2 and KDM5B. We further identified associations between AF and rare structural variants owing to deletions in CTNNA3 and duplications of GATA4. We broadly replicated our findings in independent samples from MyCode, deCODE and UK Biobank. Finally, we found that CRISPR knockout of KDM5B in stem-cell-derived atrial cardiomyocytes led to a shortening of the action potential duration and widespread transcriptomic dysregulation of genes relevant to atrial homeostasis and conduction. Our results highlight the contribution of rare coding and structural variants to AF, including genetic links between AF and cardiomyopathies, and expand our understanding of the rare variant architecture for this common arrhythmia.

The 12-lead electrocardiogram (ECG) is inexpensive and widely available. Whether conditions across the human disease landscape can be detected using the ECG is unclear. We developed a deep learning denoising autoencoder and systematically evaluated associations between ECG encodings and ~1,600 Phecode-based diseases in three datasets separate from model development, and meta-analyzed the results. The latent space ECG model identified associations with 645 prevalent and 606 incident Phecodes. Associations were most enriched in the circulatory (n = 140, 82% of category-specific Phecodes), respiratory (n = 53, 62%) and endocrine/metabolic (n = 73, 45%) categories, with additional associations across the phenome. The strongest ECG association was with hypertension (p < 2.2×10-308). The ECG latent space model demonstrated more associations than models using standard ECG intervals, and offered favorable discrimination of prevalent disease compared to models comprising age, sex, and race. We further demonstrate how latent space models can be used to generate disease-specific ECG waveforms and facilitate individual disease profiling.

ABSTRACTBackgroundOne-time atrial fibrillation (AF) screening trials have produced mixed results; however, it is unclear if there is a subset for whom screening is effective. Identifying such a subgroup would support targeted screening.MethodsWe conducted a secondary analysis of VITAL-AF, a randomized trial of one-time, single-lead ECG screening during primary care visits. We tested two approaches to identify a subgroup where screening is effective. First, we developed an effect-based model using a T-learner. Specifically, we separately predicted the likelihood of AF diagnosis under screening and usual care conditions; the difference in probabilities was the predicted screening effect. Second, we used a validated AF risk model to test for a heterogeneous screening effect. We used interaction testing to determine if observed AF diagnosis rates in the screening and usual care groups differed when stratified by decile of the predicted screening effect and predicted AF risk.ResultsBaseline characteristics were similar between the screening (n=15187) and usual care (n=15078) groups (mean age 74 years, 59% female). In the effect-based analysis, in the highest decile of predicted screening effectiveness (n=3026), AF diagnosis rates were higher in the screening group (6.50 vs. 3.06 per 100 person-years, rate difference 3.45, 95%CI 1.62 to 5.28). In this group, the mean age was 84 years and 68% were female. The risk-based analysis did not identify a subgroup where screening was more effective. Predicted screening effectiveness and predicted baseline AF risk were poorly correlated (Spearman coefficient 0.13).ConclusionsIn a secondary analysis of the VITAL-AF trial, we identified a small subgroup where one-time screening was associated with increased AF diagnoses using an effect-based approach. In this study, predicted AF risk was a poor proxy for predicted screening effectiveness. These data caution against the assumption that high AF risk is necessarily correlated with high screening effectiveness.

BACKGROUND Attaining guideline-recommended levels of physical activity is associated with substantially lower risk of cardiometabolic diseases. OBJECTIVES Although physical activity commonly follows a weekend warrior pattern, in which most moderate-to-vigorous physical activity is concentrated in 1 to 2 days rather than spread more evenly across the week (regular), the effects of activity pattern on imaging-based biomarkers of cardiometabolic health are unknown. METHODS We analyzed 17,146 UK Biobank participants who wore accelerometers for 1 week, and later underwent cardiac magnetic resonance imaging. Activity was categorized as inactive, regular, or "weekend warrior". Associations between activity pattern and magnetic resonance imaging-derived visceral adipose tissue (VAT) and epicardial and pericardial adipose tissue (EPAT) were assessed using multiple linear regression adjusted for confounding factors. RESULTS Compared to inactive, VAT was progressively lower with weekend warrior (-0.71 L, 95% CI-0.78 to-0.64, P < 0.001) followed by regular activity (-0.96 L, 95% CI-1.04 to-0.88, P < 0.001). Observations were similar for EPAT (weekend warrior activity-2.84 cm(2), 95% CI-3.20 to-2.49, P < 0.001; regular activity-3.62 cm(2), 95% CI-4.03 to-3.20, P < 0.001). When compared directly, weekend warriors had modestly higher adipose tissue than regular activity (VAT difference 0.25 L, 95% CI 0.17-0.32, P < 0.001; EPAT 0.78 cm2, 95% CI 0.40-1.15, P < 0.001). No differences were observed after adjustment for total moderate-to-vigorous physical activity minutes (VAT 0.07 L, 95% CI-0.01 to 0.14, P = 0.09; EPAT 0.04 cm2, 95% CI-0.35 to 0.43, P = 0.84). CONCLUSIONS Guideline-adherent physical activity is associated with favorable quantitative measures of cardiometabolic health, with no differences based on activity pattern for a given activity volume. (JACC Adv. 2025;4:101603) (c) 2025 The Authors. Published by Elsevier on behalf of the American College of Cardiology Foundation. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).