Skip to Main Content

Cardiovascular Data Science (CarDS) Lab

The Cardiovascular Data Science (CarDS) Lab is committed to improving cardiovascular health using data-driven insights into how we deliver care to patients.

Our group focuses on a multifaceted data-driven evaluation of cardiovascular care and outcomes.

About Us

Areas of Investigation

The CarDS Lab focuses on a multifaceted data-driven evaluation of cardiovascular care and outcomes.
  • Healthcare Quality
  • Deep Phenotyping
  • Health Policy
  • Cardiovascular Therapy
Visit the CarDS Lab or email khera.lab@yale.edu for more updates.

Healthcare Quality

In large national registries and datasets, we have defined both methodologic best practices for rigorous investigation and identified adherence to evidenced-based cardiovascular care

Deep Phenotyping

A series of ongoing investigations focus on multimodality digital health data to evaluate the phenotypic variability of patients with cardiovascular disease and the quality of care they receive

Precision Diagnosis and Therapy

We are developing tools that personalize the assessment of randomized clinical trials through the application of advanced data science and machine learning

Health Policy

Our work focuses on a rigorous evaluation of health policies and their association with cardiovascular health and outcomes

Financial Toxicity from Cardiovascular Care

We have uncovered a large burden of financial toxicity from healthcare among patients with cardiovascular disease, a function of both their emergency and acute care needs as well as out-of-pocket expenses on health insurance and health maintenance

Cardiovascular Therapy

CarDS Lab at Northwestern Cardiovascular Young Investigators' Forum (NCYIF)

We have evaluated both the effectiveness and risk-stratification tools used to define the need for therapy in different populations

Therapeutic effectiveness

We pursued a series of comparative effectiveness studies spanning the synthesis of randomized clinical trials as well as observation comparative effectiveness in real-world data