TARGET-HCM: Targeted Artificial Intelligence Screening of Hypertrophic Cardiomyopathy in the Electronic Health Record
Description: Hypertrophic cardiomyopathy (HCM) is one of the most common forms of cardiomyopathy, with a prevalence of 0.2% to 0.5%. Despite its association with increased morbidity and premature mortality, HCM remains under-diagnosed. Early identification, risk stratification and targeted interventions are critical to improving outcomes. However, current methods for disease detection rely on advanced imaging, which is not suitable for large-scale screening and may contribute to disparities in diagnostic access. Artificial intelligence (AI) offers an opportunity to address these challenges by leveraging routine tests such as electrocardiograms (ECGs) to support scalable and accessible screening. Nevertheless, AI-ECG-based screening faces barriers, including high false-positive rates and potential inequities if deployed only during opportunistic healthcare encounters. In this Career Development Award application, Dr. Evangelos Oikonomou proposes a multimodal informatics approach to guide the precision implementation of AI-ECG screening for HCM across diverse electronic health record (EHR) systems. Aim 1 will analyze structured data and unstructured clinical notes from two health systems to identify encounters and phenotypes that maximize diagnostic accuracy while reducing false positives. Aim 2 will develop an EHR-based digital twinning strategy to identify factors contributing to diagnostic disparities that may be worsened by opportunistic AI deployment. Aim 3 will design a simulation framework incorporating clinician and patient feedback to inform an AI-ECG-enabled clinical decision support system for HCM screening. The algorithms developed will be openly shared to promote adaptability across healthcare settings and use in screening other forms of cardiovascular disease. Finally, Dr. Oikonomou will receive training in clinical informatics, natural language processing and community-based participatory research under the mentorship of national experts, supporting his long-term goal of leading multi-center evaluations of equitable AI tools for under-recognized cardiomyopathies. Collectively, this work aligns with the American Heart Association’s mission by advancing earlier detection, expanding access to high-quality cardiovascular care, and improving long-term outcomes for individuals at risk of heart disease.
Funder: American Heart Association
Amount: $231,000
Funding type: fellowship
Funder scheme: Career Development Award
Start date: 2026-04-01
End date: 2029-03-31
Investigator: Evangelos Oikonomou (lead)
Institution: Yale University
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Funded outputs count: 5
Funder award ID: 26CDA1612298
OpenAlex ID: G3200439773