European Heart Journal - Digital Health

Importance: Consumer wearables such as the Apple Watch can record single-lead electrocardiograms (ECGs) but are used mainly to detect rhythm disorders. Artificial intelligence-enhanced ECG (AI-ECG) could extend these real-world recordings for detecting structural heart disease (SHD), yet prospective validation remains limited. Objective: To prospectively validate a previously developed, noise-adapted AI-ECG model for detecting severe SHD from single-lead Apple Watch ECGs. Design: Prospective cohort study. Setting: Yale New Haven Hospital echocardiography laboratory. Participants: Adults aged >=18 years undergoing outpatient transthoracic echocardiography (TTE) as part of routine clinical care. Exposure: A 30-second, single-lead Apple Watch ECG recorded during the TTE visit and processed through an end-to-end, HIPAA-compliant platform for real-time AI-ECG inference. Main Outcomes and Measures: The primary outcome was discrimination for TTE-defined severe SHD, a composite of left ventricular systolic dysfunction (left ventricular ejection fraction <40%), severe left-sided valvular disease, and/or severe left ventricular hypertrophy, assessed by the area under the receiver operating characteristic curve (AUROC). Secondary measures were sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV) at prespecified thresholds, and screening efficiency, assessed by the number needed to test (NNT) under usual-care versus AI-ECG-guided strategies. Results: Among 596 participants with analyzable Apple Watch ECGs (median age, 62 years [IQR, 46-72]; 51.2% women), severe SHD was present in 30 (5.1%). The model discriminated severe SHD well (AUROC, 0.841; 95% CI, 0.761-0.921), with a sensitivity of 76.7% (59.1-88.2), specificity of 83.2% (79.9-86.1), NPV of 98.5% (97.0-99.3), and PPV of 19.7% (13.5-27.8) at the prespecified threshold. An AI-ECG-guided strategy reduced the NNT to identify one case by more than 60% versus usual care across the composite and individual SHD phenotypes. Conclusions and Relevance: In this prospective cohort, a noise-adapted AI-ECG algorithm identified SHD phenotypes from real-world single-lead Apple Watch ECGs and improved screening efficiency. These findings support a potential role for wearable ECG-based screening in the scalable identification of clinically actionable SHD.

Background: Right ventricular (RV) function predicts survival in pulmonary hypertension (PH) and other cardiovascular diseases, yet echocardiographic AI has largely focused on the left ventricle (LV). Objectives: To develop and evaluate PH-ECHO-AI, a unified deep learning model performing four-chamber segmentation, landmark localisation, biventricular ejection fraction (EF) estimation, deformation analysis, and PH prediction from a single apical four-chamber (A4C) clip. Methods: We developed the model using 8,416 clips from four public datasets and no institutional data: EchoNet-Dynamic, CAMUS, RVENet (apical four-chamber clips paired with 3D-echocardiographic right ventricular ejection fraction, RVEF), and MIMIC-IV-ECHO. Evaluation used held-out, training-excluded data with expert-reviewed reference standards and a per-cohort audit of patient-level separation: 1,416 clips for segmentation; 600 clips for function and deformation (350 referenced to 3D-echocardiographic RVEF, 250 to the EchoNet LVEF); and 1,076 MIMIC-IV patients for PH prediction, with five-fold cross-validation. Performance measures were Dice, correlation, mean absolute error (MAE), Bland-Altman agreement, and area under the receiver operating characteristic curve (AUC). Results: Four-chamber segmentation generalised robustly across all datasets (pooled Dice: LV 0.925, RV 0.836, LA 0.910, RA 0.904). Left ventricular ejection fraction (LVEF) was estimated with r=0.845 (95% CI 0.786 to 0.886) and MAE 4.67%. RVEF, regressed directly from the clip by a supervised head trained on 3D-echocardiographic labels with no geometric assumption, reached r=0.754 (95% CI 0.690 to 0.806) and MAE 4.98%, matching published single-view RVEF ceilings and exceeding geometric RV fractional area change (RVFAC; r=0.278). Deformation and excursion metrics, namely RV free-wall and LV A4C longitudinal strain and tricuspid and mitral annular plane systolic excursion (TAPSE, MAPSE), proved physiologically coherent. Segmentation generalised to the external MIMIC-IV cohort, and PH prediction was developed and evaluated entirely within it; RVEF evaluation was clip-disjoint and same-source, so cross-centre RVEF validation remains outstanding. Using echocardiographic geometry alone, confirmed PH was detected with an AUC of 0.697 and strong calibration (Brier 0.061). Conclusions: A single, reproducible model provides comprehensive right-heart-focused interpretation from one A4C view. It achieves RVEF accuracy competitive with dedicated RV models while simultaneously delivering segmentation, deformation, annular excursion (TAPSE and MAPSE), and PH prediction. Registration: This retrospective study used existing datasets. Code is openly released, and trained model weights are available to credentialed investigators, for independent evaluation.

Aims: Structural heart disease (SHD) often remains undetected until symptoms develop. Portable 1-lead ECG devices return an automated rhythm-based interpretation, but whether AI-ECG adds diagnostic value beyond this interpretation is unknown. We prospectively evaluated a noise-adapted 1-lead AI-ECG algorithm for detecting severe SHD from portable KardiaMobile 6L recordings, and its relative diagnostic value beyond the device's rhythm interpretation. Methods and Results: Adults undergoing outpatient echocardiography between June 2024 and January 2025 recorded a 30-second, 1-lead ECG with real-time AI-ECG inference. The primary endpoint was discrimination for echocardiography-defined severe SHD. Secondary analyses assessed net reclassification improvement (NRI) versus the native interpretation and the number needed to test (NNT). Among 597 participants (median age 61.7 years; 51.4% women), 30 (5.1%) had severe SHD. AI-ECG achieved an AUROC of 0.872 (95% CI: 0.806-0.938), meeting the prespecified endpoint, with 86.7% (70.3-94.7) sensitivity, 72.5% (68.7-76.0) specificity, 99.0% (97.5-99.6) negative predictive value, and 14.4% (10.1-20.3) positive predictive value, with comparable performance across subgroups. AI-ECG increased sensitivity by 34.6 percentage points (95% CI: 13.0-56.0) over the native interpretation and yielded a categorical NRI of 24.3% (95% CI: 2.8-45.9), with 76.9% sensitivity and 80.0% specificity among tracings the device read as normal. An AI-ECG-guided strategy for detecting severe SHD reduced the NNT from 19.7 to 6.9 (a 64.8% reduction). Conclusions: A noise-adapted AI-ECG algorithm detected severe SHD from real-world portable 1-lead ECGs and substantially improved case finding beyond the device's rhythm interpretation, supporting AI-ECG-guided triage as a potential scalable screening strategy.

Large epidemiologic studies have historical electrocardiogram (ECG) collections limited to paper tracings or scanned images rather than native digital files, limiting ECG-AI applications. We compared 15 ECGs available as native digital XML files and as PDF tracings digitized using ECGScan software. Both versions were processed using an ensemble of five convolutional neural networks predicting 10-year heart failure risk. Predictions were strongly correlated (Pearson r=0.804; Spearman {rho}=0.893). Predicted probabilities were [mean (SD)] 0.195 (0.048) for native digital ECGs and 0.171 (0.042) for digitized ECGs. These preliminary findings support further evaluation of digitized ECGs for ECG-AI applications.

Background: Established heart-failure (HF) risk scores were developed largely in Western cohorts, assume linear predictor effects, and stop at prognosis without indicating action. We developed and externally validated machine-learning (ML) models for 30-day and 1-year mortality in a multi-ethnic Asian HF population, benchmarked against three established scores, and tested whether they localised correctable guideline-directed medical therapy (GDMT) gaps. Methods: We analysed 9,050 adults hospitalised with HF across eight Singapore hospitals (November 2016?March 2023). Gradient-boosted trees (XGBoost, primary) and elastic-net logistic regression were developed on three hospitals (n=4,034) and validated on five independent hospitals (n=5,016), without patient or site overlap. Comparators (MAGGIC, Singapore HF Score, OPTIMIZE-HF-Asia) were logistically recalibrated on development data. Results: On external validation XGBoost achieved AUROCs of 0.862 (95% CI 0.833?0.890) for 30-day and 0.749 (0.734?0.764) for 1-year mortality, versus 0.711?0.754 and 0.682?0.699 for the three recalibrated scores; logistic regression performed near-identically (0.864, 0.757) and was better calibrated at 1 year. Superiority held under temporal validation, multiple imputation and optimism correction, although the 30-day advantage was no longer distinguishable from MAGGIC once medications were removed. Among predicted-high-risk patients with reduced ejection fraction, mean GDMT exposure was 0.92 of four pillars versus 1.87 across all HFrEF patients, and 36.3% received none of the four versus 2.0% of low-risk patients. Ten variables reproduced full-model 30-day discrimination (AUROC 0.865). Conclusions: In external validation, interpretable models substantially outperformed established HF risk scores for short- and long-term mortality and simultaneously localised correctable therapeutic gaps, supporting a prediction-to-action tool deployable with ten bedside variables.

Deep video networks estimate left ventricular ejection fraction (EF) from echocardiograms with expert-level accuracy, but the compute cost of running them is rarely reported. This leaves anyone building a handheld or bedside tool without clear guidance on what to deploy. We measured the accuracy-versus-compute tradeoff for EF estimation on EchoNet-Dynamic by training 22 configurations that varied clip length (8 to 64 frames), frame sampling period (1 to 4), and backbone: R(2+1)D-18, R3D-18, MC3-18, X3D-S, X3D-M, and a 2D ResNet-18 with temporal pooling. All models used one fixed training recipe. Every configuration was evaluated for accuracy using mean absolute error, R-squared, and Bland-Altman agreement; clinical utility using sensitivity and specificity at the clinically relevant EF cutoffs of 40% and 50%, plus error stratified by EF band; and cost using floating-point operations, parameter count, GPU and CPU latency, and peak memory under a single frozen measurement protocol. We stress-tested the main findings with replicate training seeds. Sparse temporal sampling outperformed dense sampling at matched frame budgets. A sampling period of 4 outperformed a period of 1 at every tested frame count while also reducing per-video cost. In the seed-replicated 8-frame comparison, the advantage averaged one full point lower mean absolute error across all nine cross-seed pairings. A standard R3D-18 achieved the best accuracy in the study, with a mean absolute error of 3.99, while requiring 19% less CPU latency than the reference configuration. A 16-frame, period-4 R(2+1)D-18 cut reference cost in half with no statistically confirmed loss in accuracy. Removing temporal modeling entirely substantially reduced accuracy, with a mean absolute error of 5.65, setting a practical floor for how inexpensive this task can be. We release the code, cost-measurement protocol, and per-configuration results.

Background: Rheumatic mitral stenosis (RMS) disproportionately affects low-resource settings where echocardiography is limited. We evaluated foundation model (FM) feasibility for RMS detection using limited, indirectly labeled ECGs. Methods: An ECG-FM was fine-tuned using 804 RMS-positive ECGs per fold and externally validated across clinical and wearable lead configurations. Results: Internal AUROCs were 0.89, 0.87, and 0.87, for 12-Lead, 6-Lead, and 1-Lead respectively. External AUROCs were 0.82, 0.80, and 0.77. Performance remained comparable across demographic subgroups. Conclusions: FM fine-tuning enables RMS detection using limited ICD-derived labels, supporting further evaluation of reduced-lead ECG screening and echocardiography triage in resource-constrained settings.

Background: Artificial intelligence (AI) may improve electrocardiographic differentiation of Takotsubo syndrome from acute anterior ST-segment elevation myocardial infarction (STEMI), but its impact on human diagnostic performance, the added value of visual explanations, and differences by reader background and experience remain uncertain. Methods: Using 12-lead electrocardiogram (ECG) images from two hospitals, we developed and externally validated an ensemble of three deep learning models after self-supervised pretraining and fine-tuning. The diagnostic task used ECGs recorded within 14 days after symptom onset, regardless of reperfusion status. We conducted a four-phase reader study. Phases 1-3 compared unaided interpretation, a reference sheet, and additional AI assistance. In Phase 4, readers evaluated a new ECG set after randomization to reference-sheet support alone, with AI predictions, or with AI predictions plus gradient-weighted class activation mapping (Grad-CAM) heatmaps. Diagnostic correctness was analyzed using generalized linear mixed-effects models. Exploratory analyses examined differences by cardiologist status and experience. Results: Development and external-validation cohorts, including healthy controls, comprised 832 and 95 participants, respectively. For Takotsubo-STEMI discrimination, external-validation accuracy was 0.914, with areas under the receiver operating characteristic and precision-recall curves of 0.970 and 0.984. Seventy healthcare providers completed the reader study. The estimated probability of correct diagnosis increased from 0.632 without assistance to 0.864 with AI assistance (odds ratio [OR], 3.71; P<0.001). In randomized Phase 4, AI assistance improved accuracy vs reference-sheet support alone (OR, 4.28; 95% CI, 3.08-5.95; P<0.001), and Grad-CAM provided additional benefit (OR, 1.53; 95% CI, 1.04-2.25; P=0.033). Exploratory analyses showed greater improvement among less experienced readers; with AI assistance, non-cardiologists outperformed cardiologists. AI-assisted readers remained less accurate overall than the model alone. Conclusions: An ECG image-based ensemble differentiated Takotsubo syndrome from anterior STEMI and improved reader accuracy. Visual explanations provided additional benefit, while experience-related differences highlight the importance of effective human-AI interaction.

Background. Real-world 12-lead electrocardiograms (ECGs) often have missing or corrupted leads. A deep-learning classifier can be prepared for this by random lead masking during training, or by injecting clinical knowledge, for example by pulling its attention towards the leads that guidelines use for each diagnosis. Whether this knowledge adds robustness beyond masking is unknown. Methods. Pre-registered comparison of three arms sharing one network (per-lead 1D-ResNet encoder and per-diagnosis attention over the 12 leads): standard training (M0); random whole-lead masking (M1); masking plus a Kullback-Leibler penalty pulling attention towards a fixed guideline-derived key-lead map (M2, guideline-based attention guidance). Six diagnoses; five seeds per arm. Development on PTB-XL (21,799 ECGs); single sealed evaluation on PTB-XL fold 10 (2,198 ECGs) and on CODE-15% (233,204 exams, external validation). Primary endpoint: AUROC difference M2 - M1, averaged over first-degree AV block, right and left bundle branch block and atrial fibrillation and over 1 to 6 lost (zeroed) leads, with a patient-level paired BCa bootstrap 95% confidence interval. Results. The guidance did not change robustness: {Delta}AUROC -0.0010 (95% CI -0.0033 to +0.0006), an interval entirely within the pre-specified +-0.02 margin; the result was unchanged with another bootstrap seed, other interval methods and leave-one-diagnosis-out analyses. Masking improved AUROC: M1 - M0 = +0.0134 (95% CI +0.0102 to +0.0172) when one key lead was lost, and the number of lost leads tolerated before AUROC fell by more than 0.02 rose from 7 (M0) to 10 (M1). M2 attention matched the map and M2 was non-inferior on intact ECGs, but its calibration slope was lower for all six diagnoses in both datasets. M2 lost slightly more when all key leads were lost together (-0.0067) and gained only when one to three leads remained (exploratory; AUROC 0.9408 vs 0.9210 with 11 leads lost). CODE-15% reproduced every pattern (primary -0.0007, 95% CI -0.0011 to -0.0003). Conclusions. Random lead masking suffices to make an ECG classifier robust to missing leads; adding guideline knowledge aligns attention with clinical criteria but adds no robustness and worsens calibration. Guideline-aligned attention should not be taken as evidence of robustness.

Background: Regurgitant valvular heart disease (rVHD) is a major cause of cardiovascular morbidity. Echocardiography is the diagnostic standard but is resource-intensive for large-scale screening. Electrocardiography (ECG) has shown promise for predicting incident rVHD, yet performance varies across phenotypes, particularly for aortic regurgitation (AR). Chest radiography (CXR) provides complementary structural and hemodynamic information. We hypothesized that a multimodal model integrating ECG and CXR would improve prediction of incident moderate-to-severe rVHD. Methods: In this retrospective multicenter study, we identified 212,888 paired ECG-CXR examinations from 116,380 patients across two Chinese centers. Baseline ECG and CXR were obtained within 60 days of echocardiography. Outcome was progression to moderate-to-severe AR, mitral regurgitation (MR), or tricuspid regurgitation (TR). We developed a multimodal neural network with pretrained unimodal encoders, token-level cross-modal fusion, and a class-specific gating mechanism that adaptively weighted ECG-only, CXR-only, and fused predictions. Performance was assessed using C-index, AUROC, AUPRC, decision curve analysis, net reclassification improvement (NRI), and Kaplan-Meier stratification. Results: Multimodal fusion consistently outperformed unimodal models across all phenotypes. For AR, C-index improved from 0.616 (ECG-only) to 0.713 (multimodal; AUROC 0.729, AUPRC 0.972). For MR, multimodal C-index was 0.801 (AUROC 0.814, AUPRC 0.972), versus 0.782 for ECG and 0.775 for CXR alone. For TR, multimodal and CXR-only models showed similar discrimination (C-index 0.802), but multimodal fusion yielded greater net benefit on decision curve analysis. NRI was positive across all time horizons (1-5 years) for all valve types. Grad-CAM interpretability analyses revealed that ECG attention localized to leads II, V-V (AR), leads I, II, aVF, V-V (MR), and inferior/right precordial leads (TR); CXR attention highlighted chamber-specific enlargement and pulmonary congestion patterns consistent with pathophysiology. Conclusion: A multimodal deep learning model integrating ECG and CXR significantly improved prediction of incident rVHD compared with ECG alone, with the greatest benefit observed for AR. The model leveraged complementary electrical and structural information, demonstrated biological plausibility through interpretability analyses, and provided consistent clinical utility. Given the widespread availability and low cost of both modalities, this approach offers a scalable tool for risk stratification in routine care. Prospective studies are warranted to validate clinical implementation.

Abstract Background: Hypertrophic cardiomyopathy (HCM) is a heterogeneous condition with variable morphology and symptoms, leading to adverse outcomes such as atrial fibrillation, heart failure and sudden cardiac death. Data-driven phenotyping may help refine risk stratification and guide management. Objectives: To propose an automated machine learning framework (HCM-PhenotypeNet) that integrates echocardiographic video and clinical data to identify clinically meaningful HCM phenotypes. Methods: We developed a multimodal pipeline using a deep neural network to extract features from 1,553 echocardiography video clips, combined with >100 clinical variables from 156 HCM patients. Patientlevel vectors were reduced using UMAP and clustered using Deep Embedded Clustering (DEC). Cluster quality was assessed using internal validation metrics, and clusters were characterized through statistical comparisons and association rule mining. Results: The cohort included 156 HCM patients (mean age 53.6 +/- 13.9 years, 40.4% female) with preserved systolic function and diverse racial/ethnic backgrounds. The optimal pipeline (DEC with 4 clusters) yielded phenogroups with strong separation (silhouette {approx} 0.89): (A) Advanced Obstructive/Metabolic phenotype; (B) Early-onset, Genotype Positive phenotype; (C) Late-onset, mild non-obstructive phenotype; and (D) Hypertrophic Heart Failure-predominant phenotype. Whilst there was no mortality difference, there was a trend towards increased heart failure and atrial fibrillation burden in the Advanced Obstructive/Metabolic and Heart Failure-predominant subgroups. Conclusions: HCM-PhenotypeNet enabled automated identification of four clinically relevant HCM subgroups. These phenogroups highlight the heterogeneity of HCM and may support personalized risk stratification and management but require validation in larger cohorts. Keywords: Cardiomyopathy Subtypes, Echocardiography, Phenotyping, Video Analysis, Clustering

Background: Unstructured biomedical data, such as echocardiography reports, are rich in information but time consuming to analyze at scale. Rule-based, regular expression-driven terminology mapping can only extract individual variables while large language models (LLMs) offer scalable and clinically meaningful interpretations of heterogeneous disease processes. Right ventricular dysfunction (RVD) is an example of a multifactorial disease state in which key structural and physiologic features are captured both narratively and in structured fields, making it an ideal test case for evaluating whether LLMs can recover complex phenotypes that rules based methods routinely miss. Purpose: To compare an LLM-based extraction method to a conventional rules-based schema for identifying and phenotyping echocardiographic features associated with RVD in a large TTE dataset. Methods: MIMIC-III NOTE2NUM echocardiography reports (n = 45,794) were analyzed using GPT-4o-based LLM extraction deployed within a secure health system enclave and were benchmarked against echocardiographic measurements defined in the MIMIC-III dictionary schema. In MIMIC-III, PH was recorded qualitatively (mild/moderate/severe) based on tricuspid regurgitant (TR) jet velocity and then re-coded as present vs. absent. LLM based extraction defined RVD as (1) RV structural abnormality (>= 1 of hypertrophy, dilation, or wall hypo-/akinesis) or (2) RV pressure/volume overload (>= 2 of the following: estimated right atrial pressure > 8 mmHg, TR jet velocity > 2.8 m/s, fractional area change < 35%, tricuspid annular planar systolic excursion < 17 mm, S' < 9.5 cm/s, or E/e' > 14), with PH defined as estimated pulmonary artery systolic pressure > 35 mmHg or qualitative documentation of PH. Results: LLM extraction identified PH in 15,394 (33.6%), RV pressure/volume overload in 14,449 (31.6%), and RV structural abnormalities in 11,955 (26.1%). Co-occurrence was common: overload + structural changes in 9,380 (20.5%), overload + PH in 9,756 (21.3%), structural changes + PH in 6,183 (13.5%), and all three in 5,620 (12.3%). Using the MIMIC-III dictionary schema, PH prevalence was similar (15,371; 33.6%), but RV overload fields were captured less often (pressure overload 1,357 [3.0%], volume overload 1,128 [2.5%], pressure + volume overload 1,093 [2.4%]; any overload field 3,578 [7.8%]), and RV pressure/volume overload with PH was identified in only 731 (1.6%). Conclusions: LLM-based extraction outperforms rules-based schemas for identifying complex disease states not defined by any single variable. By synthesizing multifactorial signals, LLMs can phenotype RVD with higher fidelity and support population-level assessment. Further validation using multimodality imaging, invasive hemodynamics, and clinical outcome data is needed.

BACKGROUND: Coronary angiography remains the reference standard for diagnosing coronary artery disease and guiding revascularization, yet its interpretation requires expert integration of multi-view anatomy, lesion morphology and procedural context. Existing artificial intelligence approaches are largely task-specific, annotation-dependent and limited in capturing the semantic relationship between angiographic findings and interventional decision-making. Whether large-scale vision-language pretraining can enable transferable foundation-model representations for invasive coronary imaging remains unknown. METHODS We developed CAG-MIND, a domain-specific vision-language foundation model for coronary angiography, using 135,475 CAG examinations paired with procedural reports, comprising 812,850 angiographic videos from Zhongshan Hospital and Shanghai Geriatric Medical Center. Each case consisted of standardized six-view angiographic acquisitions paired with structured procedural semantics extracted from routine reports using a large language model-assisted pipeline. The model was pretrained by aligning multi-view angiographic representations with report-derived semantic embeddings through bidirectional contrastive learning. Performance was evaluated under zero-shot and supervised fine-tuning settings across 11 downstream tasks grouped into structural abnormality detection, atherosclerotic plaque assessment, and interventional decision prediction, using both an internal validation cohort and an independent external test cohort. RESULTS CAG-MIND demonstrated robust performance across all three task categories. In the zero-shot setting, the model achieved mean AUROCs of 0.686 in the internal validation cohort and 0.745 in the external test cohort, indicating transferable multimodal representations without task-specific supervision. Following supervised fine-tuning, the mean AUROC increased to 0.827 and 0.846, respectively, with excellent performance for coronary stenosis detection (AUROC 0.940 in both cohorts), balloon/stent prediction (0.900 and 0.907), and CABG recommendation (0.877 and 0.875). Compared with representative biomedical vision-language models and conventional image-based architectures, CAG-MIND consistently achieved superior performance in both zero-shot and supervised settings and remained superior to fully fine-tuned competing models when trained with only 10% of the labelled data. Grad-CAM visualization demonstrated anatomically plausible lesion-focused attention, supporting the interpretability of the learned representations. CONCLUSIONS CAG-MIND is, to our knowledge, the first large-scale vision-language foundation model for coronary angiography trained at more than 100,000-patient scale. By aligning standardized multi-view angiographic videos with report-derived procedural semantics, CAG-MIND enables robust zero-shot transfer, data-efficient fine-tuning and cross-center generalization. These findings support domain-aligned multimodal pretraining as a scalable foundation-model paradigm for invasive cardiovascular imaging and future cath-lab decision support.

Aims: Myocardial strain enables sensitive assessment of cardiac function, but its clinical application has largely focused on individual chambers or selected patient populations. We evaluated the feasibility and clinical relevance of fully automated multi-chamber strain assessment in consecutive patients undergoing routine transthoracic echocardiography (TTE). Methods and results: This retrospective study included 8,350 consecutive adults undergoing TTE. A hospital-wide artificial intelligence (AI)-based system automatically measured left ventricular (LV) global longitudinal strain (LVGLS), left atrial (LA) reservoir strain (LASr), and right ventricular (RV) free-wall strain (RVFWS). AI-derived LVGLS was available from at least one apical view in 97.1% of patients and from all three views in 94.8%; LASr and RVFWS were available in 94.1% and 94.5%, respectively, resulting in complete multi-chamber strain assessment in 90.3%. Strain measures showed modest correlations with conventional chamber-specific echocardiographic parameters and differential associations with clinical outcomes. Gaussian mixture modeling identified three distinct clusters characterized by preserved multi-chamber function, RV-dominant dysfunction, and pan-chamber dysfunction. Compared with the preserved cluster, pan-chamber dysfunction was associated with the highest risk of all-cause death or heart failure hospitalization (adjusted hazard ratio, 3.44; 95% CI, 2.43-4.88; P<0.001). Prognostic associations remained evident in patients with LV ejection fraction (LVEF) [&ge;]50%, and cluster assignment provided incremental prognostic information beyond clinical factors, LVEF, and RV fractional area change. Conclusions: Fully automated multi-chamber strain assessment was feasible in a large consecutive TTE cohort. Integrating strain across cardiac chambers may provide complementary functional characterization and identify clinically relevant clusters with prognostic information beyond conventional assessment.

Background: Heart failure with preserved ejection fraction (HFpEF) accounts for approximately half of the more than 64 million heart failure cases globally, yet its pathophysiology is incompletely understood, its molecular determinants are poorly defined, and disease-specific therapies remain limited. Comprehensive characterization of the cardiac motion abnormalities central to HFpEF has not been feasible at the population level. Methods: We developed a deep learning framework integrating image segmentation with optical flow motion analysis and applied it to standard cine cardiac magnetic resonance images from 83,569 UK Biobank participants, deriving 32 myocardial and inner cavity velocity phenotypes spanning the cardiac cycle, including mid-diastolic velocities not previously quantified at population scale. We examined the prognostic relevance, genetic architecture, and candidate causal mediators of the optical flow velocity phenotypes. Results: In a pragmatically defined HFpEF subcohort, mid-diastolic and late-diastolic optical flow velocities were reduced relative to healthy reference participants, while higher systolic left ventricular myocardial velocity was associated with lower all-cause mortality (HR 0.61 per SD; 95% CI 0.45-0.82). Genome-wide association analyses identified 12 risk loci associated with optical flow velocity phenotypes. Phospholamban (PLN), the canonical regulator of sarcoplasmic reticulum calcium reuptake, demonstrated the broadest pleiotropy across all cardiac phases. SOX5, a transcription factor involved in extracellular matrix development, showed significant genome-wide association exclusively with mid-diastolic velocities. Mendelian randomization implicated RABGAP1L as a candidate causal mediator of early diastolic velocity (IVW {beta} = -0.255 per NPX for early diastolic right ventricular inner circumferential velocity; p = 5.49 x 10^-22), nominating a calcium-handling pathway in diastolic dysfunction. Conclusion: Genetic and causal-inference evidence implicates intracellular calcium handling and extracellular matrix remodeling as candidate mechanisms underlying diastolic dysfunction. Together, this work establishes deep-learning-enabled cardiac motion phenotyping as a scalable approach to interrogate the molecular basis of HFpEF and nominates candidate targets for therapeutic development.

Conventional electrocardiography is highly effective for waveform and rhythm diagnosis, but it is less suited to showing how the internal shape of hundreds or thousands of consecutive heartbeats changes over time. We introduce FOXTAIL, a complementary view that represents each cardiac cycle as an ordered sequence of changes in signal direction. Overlaying these sequences in a fixed visual field makes beat-to-beat organization visible and allows the density, size, stability, and scale persistence of those changes to be measured. We evaluated the representation in recordings containing normal sinus rhythm, paroxysmal atrial fibrillation, severe heart failure, ventricular tachyarrhythmia, and controlled electrode-motion noise. Paired recordings showed that FOXTAIL descriptors can reveal within-person state changes that are not conveyed by a single average beat. The noise and pre-fibrillation analyses also showed that a dense event pattern is not automatically equivalent to physiological complexity, measurement artifact, or impending disease. FOXTAIL is therefore not proposed as a replacement for the diagnostic ECG or as a new classifier, but as an observation and measurement domain for asking a more basic question: how is the electrical organization of the heart changing from one beat to the next, and which of those changes persist across scale?

Standard cardiac biomarkers such as ejection fraction, ventricular volumes, and strain compress complex three-dimensional heart dynamics into a small set of predefined measurements, leaving clinically important heterogeneity unrecognised. Here we propose a personalised normative cardiac framework in which each individual is compared to a digital twin representing expected healthy cardiac function given their age, sex, and body habitus. We show that structured patterns of deviation from these normative twins, discovered through systematic exploration of a generative cardiac dynamics space, constitute novel dynamic phenotypes that are not captured by conventional biomarkers. Applied independently to two UK Biobank cardiac cohorts with distinct shape representation, a 128-dimensional four-chamber statistical shape descriptor (HeartSSM, n = 52,365) and a 64-dimensional deep generative latent space from a conditional variational mesh autoencoder (MeshHeart cVAE, n = up to 39,376), we identify reproducible, continuous deviation-from-normative-twin scores (three discrete deviation phenotypes in the HeartSSM cohort) that improve cardiovascular risk stratification beyond ejection fraction, ventricular volumes, myocardial mass, and strain. The strongest effect was seen for incident atrial fibrillation among individuals with preserved ejection fraction (at least 50%): incremental C-index delta C = +0.068 (5-fold cross-validated delta C = +0.063; likelihood-ratio P = 3.3 x 10^-8), with a separate, smaller effect for incident stroke in the same preserved-EF subgroup in the independent MeshHeart cVAE representation (which showed no signal for atrial fibrillation) (delta C = +0.024, P = 2.6 x 10^-4). Both effects were checked against placebo controls in which the deviation scores were replaced by Gaussian noise. To test whether the normative twin generalises beyond UK Biobank's specific scanning and processing pipeline, we applied the MeshHeart cVAE normative twin, unmodified, to an independent external cohort of healthy volunteers imaged at a different hospital (GenScan/Hammersmith, n = 315): deviation scores in this cohort were of comparable magnitude to the UK Biobank healthy reference (ratio of means = 1.09; Mann-Whitney P = 1.4 x 10^-5), indicating that the normative twin captures cross-site-transferable structure rather than a scanner- or pipeline-specific artefact. Our findings suggest that cardiac phenotyping can move beyond predefined measurements toward data-driven dynamic phenotypes that better capture the heterogeneity underlying cardiovascular disease risk, even among individuals whose ejection fraction appears normal.

Acute myocardial infarction (MI) is a major precursor to heart failure (HF), yet few biomarkers are routinely used to predict post-MI HF, and limited therapeutic options exist to prevent its development. Furthermore, identifying patients at extremely high risk of recurrent MI remains challenging. These gaps highlight the need for improved biomarkers, therapeutic targets, and computational approaches for risk assessment and treatment-response prediction. To address risk assessment, we developed a systems bioinformatics (SB), graph-based framework representing patient information as personalized networks and integrating omics, clinical, and molecular prior-knowledge data. Graph neural network (GNN) machine learning (ML) models were compared with conventional ML approaches. Two large-scale public plasma proteomic datasets were used to predict post-MI HF. To investigate treatment response, regression models were applied to longitudinal clinical data from >400 hospitalized patients enrolled in the EMMY trial evaluating empagliflozin. ML-driven feature selection identified proteins and clinical parameters with the greatest predictive value. The graph-based framework demonstrated strong and consistent performance across independent post-MI cohorts. GNN models outperformed conventional approaches, including generalized linear models and XGBoost, particularly when attention mechanisms were incorporated. Using biomarker panels alone, the best GNN achieved an external test AUC of 0.82, compared with 0.77 for the best conventional ML model. When biomarkers were combined with clinical and demographic variables, GNN and conventional ML models achieved AUCs of 0.80 and 0.77, respectively. Regression models also showed promise for predicting biomarker changes associated with treatment response, with the best model achieving a test RMSE of 0.56. Feature-importance analysis identified NT-proBNP (NPPB), cardiac troponins (TNNI3/TNNT2), and prior HF history as the most influential predictors, consistent with established clinical evidence. Overall, these findings support graph-based ML and regression analysis as promising approaches for improving post-MI HF risk prediction and therapeutic response and identifying clinically relevant markers.

Time-embedded electrocardiographic descriptors combine high-order derivatives in nonlinear ratios, making their numerical calibration essential. We analyzed 200 LUDB participants (1,748 QRS windows) and a fixed external sample of 1,000 PTB-XL participants (9,735 windows). Four prespecified derivative operators were evaluated at three nominal Butterworth cutoffs; a fifth, regularized operator was added post hoc. Extensions added transfer functions, matched response crossings and a Gaussian transient with exact derivatives. The expanded calibration comprised 1,005 mathematical signal/noise realizations. At 150 Hz, spectral differentiation (SPEC) increased external participant-level mean absolute torsion by a median 78.97% relative to successive finite differences (FD; 95% confidence interval 77.39-80.53). Reducing the cutoff to 40 Hz yielded weak rank preservation: Spearman correlations were 0.045 for SPEC and 0.099 for FD. Matching each derivative's first normalized -3-dB crossing at 20 Hz reduced the external SPEC-FD median difference to 0.016%, but introduced 4.26-4.70% noiseless error on the Gaussian transient. Agreement was therefore not accuracy against the known target. For the Gaussian transient with 20-microvolt noise, relative root mean squared errors at 150 Hz were 719.52% for SPEC and 99.96% for the regularizer; the latter error remained comparable to the target magnitude, and regularization also introduced noiseless bias. Almost-curvature approximated a normalized voltage slope under the specified coordinates and did not converge to classical curvature under reparametrization. Explicit transfer functions, absolute descriptor levels and analytic targets explain important processing effects while separating numerical agreement from clinical validity. No universally optimal estimator or diagnostic benefit is established.

Background Patients with normal perfusion, normal myocardial flow reserve (MFR) and no coronary artery calcium (CAC) on myocardial perfusion imaging are considered low risk. Yet, adverse events still occur and no routinely reported imaging marker stratifies residual risk. This study aims to determine whether fully automated ascending aortic calcification (AAC) from the attenuation correction CT stratifies risk in these patients. Methods In the multicenter REFINE-PET registry, AAC was quantified from non-contrast CT using deep learning aortic segmentation and Agatston scoring. Triple-normal was defined as stress total perfusion deficit (TPD) <5%, MFR >2 and CAC 0. The primary endpoint was cardiovascular death, myocardial infarction or heart failure admission, with heart failure admission as key secondary endpoint. Cox models were adjusted for clinical confounders. Results Of 21,923 patients, 3,580 (16.3%) were triple-normal, of whom 1,322 (36.9%) had AAC (median Agatston 65, IQR 22-212). Agreement with three blinded readers was good to excellent (Intraclass correlation coefficient 0.87-0.90). Over a median follow-up of 52 months (IQR 26-69), 194 primary events occurred. Per standard deviation, AAC was independently associated with the primary endpoint (adjusted HR 1.24, 95% CI 1.09-1.40; p<0.001), heart failure admission (adjusted HR 1.30, 95% CI 1.10-1.55; p=0.003) and all-cause mortality (adjusted HR 1.17, 95% CI 1.04-1.32; p=0.009). AAC improved model fit beyond clinical factors, MFR and TPD (p< or =0.009), with modest gains in discrimination ({Delta}C 0.007-0.009). Conclusions In patients with normal PET readouts, automated AAC was independently associated with adverse outcomes, most strongly heart failure admission, beyond clinical risk factors, perfusion and flow.