Current Areas of Exploration in Artificial Intelligence

The Chugh Laboratory at the Smidt Heart Institute focuses on prediction and prevention of sudden cardiac arrest. We use a large clinical data archive assembled over two decades from a catchment population of 1.85 million residents of Portland, Oregon and Ventura, California. These well-phenotyped cohorts are connected to a biobank where we correlate phenotypes with whole genome and proteome findings using both conventional and artificial intelligence tools. We are testing discoveries in a separate longitudinal EHR cohort of approximately 400,000 residents of Los Angeles County. Based on these discoveries we are designing new clinical trials to facilitate translation to the clinic as well as the community, with the goal of reducing the population burden of sudden cardiac arrest and sudden cardiac death.

The Chugh Laboratory is affiliated with the Smidt Heart Institute and Department of Medicine.

Current research in the Slomka Laboratory focuses on developing innovative methods for fully automated analysis of cardiac imaging data using novel algorithms and machine-learning techniques, and on the development of integrated motion-corrected analysis of positron emission tomography (PET)/computerized tomography (CT) and CT angiography imaging. Research in the Slomka Laboratory is supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health (NIH). The resources include large ( > 40,000 cases) multisite international registry of cardiac imaging SPECT data (REFINE SPECT).

With the exponential rise in the amount of data being collected in clinical care, there are huge opportunities to apply the additional data to personalize care and improve diagnosis and treatment of cardiovascular disease. In parallel, we are deeply interested in the active deployment of artificial intelligence models in healthcare and designed the first blinded, randomized clinical trial of AI in cardiology (Nature 2023). As clinicians, computer scientists, informaticians and statisticians, we are fascinated by how we understand, visualize, and interpret data.

The Zhang lab develops automated deep learning methods to accommodate the rapid biotechnology development with modern deep learning. These automated, data-driven models help us understand the causal effects of genetic variations in various contexts, including epigenetics, transcription, post-transcriptional regulation, genome editing, and in disease areas such as tumors. In the long term, we hope our methods will democratize deep learning and thereby accelerate scientific discoveries in biomedicine.

The Cedars-Sinai Clinical Data Lake and Data Warehouse is deep, data rich and one of the most research-ready data repositories of its kind. Containing more than a decade of medical data, it seamlessly brings together multiple internal and external data sources to provide researchers with access to approximately 50 million encounters for over 5 million patients. The Enterprise Data Intelligence team at Cedars-Sinai works closely with researchers and clinicians to provide a wealth of knowledge about patients, their medical conditions and their outcomes.