Research

01

Deep Adiposity Phenotyping

We use CT radiomics and machine learning to quantify perivascular, epicardial, and systemic fat as scalable markers of cardiometabolic risk and early disease.

AI-Enabled Echocardiography Identifies an Adverse Epicardial Adiposity Phenotype Associated with Cardiometabolic Dysfunction medRxiv 2026.

Early Prediction of Heart Failure From Routine Cardiac CT Using Radiomic Phenotyping of Epicardial Fat J Am Coll Cardiol 2026.

Non-invasive detection of coronary inflammation using computed tomography and prediction of residual cardiovascular risk (CRISP-CT) Lancet 2018.

A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography Eur Heart J 2019.

The role of adipose tissue in cardiovascular health and disease Nat Rev Cardiol 2019.

Standardized measurement of coronary inflammation using cardiovascular computed tomography: integration in clinical care as a prognostic medical device Cardiovasc Res 2021.

02

Digital Valvular Heart Disease Biomarkers

We build biomarkers of aortic stenosis that capture structural, myocardial, and hemodynamic remodeling from routine data to support earlier detection and better-timed intervention.

Digital Phenotyping of Aortic Stenosis-Related Remodeling Reveals Complementary Structural, Electrical, and Hemodynamic Signatures medRxiv 2026.

A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression JAMA Cardiol 2024.

Severe aortic stenosis detection by deep learning applied to echocardiography Eur Heart J 2023.

Artificial Intelligence-Enabled Echocardiography as a Surrogate for Multimodality Aortic Stenosis Imaging: Post Hoc Analysis of a Clinical Trial Circ Cardiovasc Imaging 2025.

03

AI for Scalable Cardiomyopathy Screening

We build ECG and echocardiographic tools to detect transthyretin amyloid and hypertrophic cardiomyopathy before overt presentation across health systems.

Artificial intelligence-guided detection of under-recognised cardiomyopathies on point-of-care cardiac ultrasonography Lancet Digit Health 2025.

Artificial intelligence-enabled electrocardiography and echocardiography to track preclinical progression of transthyretin amyloid cardiomyopathy Eur Heart J 2025.

International Validation of Echocardiographic Artificial Intelligence Amyloid Detection Algorithm J Am Coll Cardiol 2025.

04

Phenomapping-Guided Clinical Trials

We integrate EHR, imaging, and unstructured data to identify signatures of individual treatment response and improve cardiovascular trial design and interpretation.

A phenomapping-derived tool to personalize the selection of anatomical vs. functional testing in evaluating chest pain Eur Heart J 2021.

Phenomapping-Derived Tool to Individualize the Effect of Canagliflozin on Cardiovascular Risk in Type 2 Diabetes Diabetes Care 2022.

Individualising intensive systolic blood pressure reduction in hypertension using computational trial phenomaps Lancet Digit Health 2022.

An explainable machine learning-based phenomapping strategy for adaptive predictive enrichment in randomized clinical trials (ASSIST) NPJ Digit Med 2023.

05

Risk Prediction & Surveillance

We develop strategies for earlier risk detection and longitudinal surveillance, including structural heart disease and treatment-related myocardial injury.

Assessment of Prognostic Value of Left Ventricular Global Longitudinal Strain for Early Prediction of Chemotherapy-Induced Cardiotoxicity JAMA Cardiol 2019.

Artificial Intelligence-Enhanced Risk Stratification of Cancer Therapeutics-Related Cardiac Dysfunction Using Electrocardiographic Images Circ Cardiovasc Qual Outcomes 2025.

Ensemble Deep Learning Algorithm for Structural Heart Disease Screening Using Electrocardiographic Images: PRESENT SHD J Am Coll Cardiol 2025.

TARGET-AI: A Foundational Approach for the Targeted Deployment of Artificial Intelligence Electrocardiography in the Electronic Health Record J Am Coll Cardiol 2025.

06

Best Practices in Clinical AI

We develop frameworks for rigorous cardiovascular AI development, evaluation, and deployment, prioritizing transparency, equity, and clinical impact.

PRIME 2.0: Proposed Requirements for Cardiovascular Imaging-Related Multimodal-AI Evaluation: An Updated Checklist JACC Cardiovasc Imaging 2026.

Updated critical quality criteria for real-world artificial intelligence implementation Eur Heart J 2026.

Artificial intelligence-enhanced patient evaluation: bridging art and science Eur Heart J 2024.