Could AI replace heart catheterization? 4 things to know

An AI-powered neural network, or deep machine learning model, may be as effective as catheterization at monitoring heart health, according to a study published Jan. 7 in Communications Medicine

Advertisement

Here are four things to know about the study. 

  1. The model is called Cardiac Hemodynamic AI monitoring System, or CHAIS, and was developed by researchers from Cambridge-based Massachusetts Institute of Technology and Boston-based Harvard Medical School.
  2. In a clinical trial, the model analyzed electrocardiogram signals to predict a patient’s risk of heart failure. For the trial, patients who were already scheduled for catheterization were asked to wear a single adhesive, commercially available patch on their chest to monitor their heart for 24 to 48 hours prior to the procedure.
  3. The model had the same level of accuracy of more invasive procedures such as catheterization or heart monitoring procedures, which require patients to remain in the hospital for an extended period of time.
  4. “The goal of this work is to identify those who are starting to get sick even before they have symptoms so that you can intervene early enough to prevent hospitalization,” Collin Stultz, MD, PhD, director of Harvard-MIT Program in Health Sciences and Technology and practicing cardiologist at Boston-based Massachusetts General Hospital, said in a Feb. 10 news release from MIT. 
Advertisement

Next Up in Cardiology

Advertisement

Leave a Reply

Your email address will not be published. Required fields are marked *