The Cardiovascular Data Science (CarDS) Lab is a leading research laboratory at Yale School of Medicine, driving data-driven innovation in cardiovascular care.¹ The Lab is a multidisciplinary group, comprising data scientists, postdoctoral trainees, graduate, and undergraduate students and is led by Dr. Rohan Khera, a cardiologist-data scientist, and an Associate Editor for Artificial Intelligence and Digital Health at JAMA.

The CarDS Lab is seeking a student Research Associate/Analyst to lead on aspects of cutting-edge AI projects in cardiovascular medicine. The CarDS lab specializes in the development and deployment of artificial intelligence (AI) approaches to large-scale medical datasets. Notably, Yale undergraduate students working in CarDS lab have a track record for leading projects from conception to publication, with recent outputs in Nature Cardiovascular Research, Nature Communications, npj Digital Medicine, and Circulation.^2–5

Potential projects:

1.     Next-generation AI tools for cardiovascular medicine. In recent work, CarDS lab has demonstrated the limited selectivity of existing AI models for cardiac disease, which may restrict utility in widespread deployment.⁶ The team member will pursue key responsibilities in AI tool development. This will include developing AI models using existing pipelines, then introducing increasing levels of sophistication to cohort selection, model architectures, and hyperparameter tuning to move the needle for state-of-the-art performance.

2.     Interrogating the Biological Mechanisms underlying healthcare AI predictions. As biological markers guiding clinical care, CarDS lab members have demonstrated the utility of relating predictions to underlying disease biology.^7,8 The team member will pursue key responsibilities in discovery science. This will include analyzing existing AI models in the context of underlying genomic and exposomic drivers which may be influencing disease pathophysiology, with the potential to uncover novel disease-modifiable targets.

This position offers an excellent opportunity to work with leading investigators in the field, contributing to next generation of knowledge in medicine. The Research Associate/Analyst will be expected to maintain regular communication with their supervisor, providing weekly progress updates, identifying challenges, and offering recommendations for improvement. They will have the opportunity to present literature summaries and preliminary findings to faculty and postdocs during internal lab meetings, as well as document project progress using standardized lab records, and participate in manuscripts arising from this work.

Bibliography

1. Khera, R. et al. Transforming cardiovascular care with artificial intelligence: From discovery to practice: JACC state-of-the-art review. J. Am. Coll. Cardiol. 84, 97–114 (2024).

2. Sangha, V. et al. Detection of left ventricular systolic dysfunction from electrocardiographic images. Circulation 148, 765–777 (2023).

3. Sangha, V. et al. Automated multilabel diagnosis on electrocardiographic images and signals. Nat. Commun. 13, 1583 (2022).

4. Khunte, A. et al. Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices. NPJ Digit. Med. 6, 124 (2023).

5. Sangha, V. et al. Identification of hypertrophic cardiomyopathy on electrocardiographic images with deep learning. Nat. Cardiovasc. Res. 4, 991–1000 (2025).

6. Croon, P. M., Dhingra, L. S., Biswas, D., Oikonomou, E. K. & Khera, R. Phenotypic selectivity of artificial intelligence-enhanced electrocardiography in cardiovascular diagnosis and risk prediction. Circulation (2025) doi:10.1161 CIRCULATIONAHA.125.076279.

7. Biswas, D. et al. A clonal expression biomarker associates with lung cancer mortality. Nat. Med. 25, 1540–1548 (2019).

8. Biswas, D. et al. Prospective validation of ORACLE, a clonal expression biomarker associated with survival of patients with lung adenocarcinoma. Nat. Cancer 6, 86–101 (2025).