Cedars-Sinai researchers are developing a deep-learning algorithm to personalize patient cardiac risk predictions in a patient-friendly, graphical report.

Researchers used multiple AI models to evaluate EHR data from more than 322,000 heart failure patients. By identifying these subtypes, the group thinks clinicians could perform better risk assessments and make more informed treatment decisions. 

New research suggests AI could offer physicians a new, state-of-the-art approach to sudden cardiac arrest risk management.

There are now numerous AI algorithms for electrophysiology. Jagmeet Singh, MD, examined how this advanced technology is being applied.

Cardiology is linked to the second largest group of FDA-cleared clinical AI algorithms, and the number is still growing. 

Marcelo DiCarli, MD, and Rob Beanlands, MD, discussed the long-term value of investing in the development and implementation of AI technologies. 

The video-based deep neural network showed potential for limiting invasive exams and improving patient care. 

A research lab led by a veteran cardiothoracic surgeon found that ChatGPT—particularly the GPT-4 model—could 'potentially revolutionize' training in the years ahead.