Cedars-Sinai Develops AI to Predict Adverse Cardiac Events

Cedars-Sinai researchers have developed an artificial intelligence (AI) tool that can predict a patient’s chance of adverse cardiac events, such as a heart attack, and demonstrate how that patient’s risk may change over time, according to a study published this week in npj Digital Medicine.  

According to a press release detailing the study’s findings, the AI tool could help provide patients with personalized risk assessments and insights into their heart health. 

“Using a specific type of AI trained to interpret images of the heart and developed at Cedars-Sinai, we could both predict the chance of cardiac events—like death, heart attack, or the need for urgent treatment of the heart vessels—and show how the likelihood of these adverse events changes over time,” explained Piotr Slomka, PhD, director of Innovation in Imaging at Cedars-Sinai and a research scientist in the Division of Artificial Intelligence in Medicine and the Smidt Heart Institute. 

To do so, the researchers trained the AI to evaluate basic clinical data– including gender, age, weight, blood pressure, and heart rate—alongside heart imaging from each patient in the cohort, which shows how the heart expands and contracts and illustrates the blood flow into the heart muscle. 

Using these data, the model uses deep learning to generate predictions. These predictions are presented as graphs that indicate a patient’s risk of having a heart attack, needing an invasive cardiovascular intervention, like a bypass surgery or stent, or dying over a several-year period. 

The graphs are designed to be simple for both clinicians and patients to understand. 

“Doctors and patients can use these graphs to track how risk changes over time and to identify individual risk factors,” said Slomka. “They can also interactively modify certain risk factors to see how it impacts a patient’s particular risk.” 

The researchers noted that their AI tool and others like it could have a significant positive impact on personalized risk assessment and shared decision-making. 

“AI algorithms of this nature could enable physicians to communicate more personalized information regarding potential timing of imminent heart disease events, allowing patients to engage more meaningfully in the shared decision-making process,” said Sumeet Chugh, MD, director of the Center for Cardiac Arrest Prevention in the Smidt Heart Institute, in the press release. “Even more importantly, this tool has the potential to lend data-led, appropriate urgency to heart disease prevention efforts by both patients and providers.” 

Moving forward, the researchers intend to test the model in clinical trials at Cedars-Sinai. 

This research builds on other recent efforts by Cedars-Sinai to advance cardiovascular care using AI. 

Last month, researchers demonstrated that an AI’s ability to assess and diagnose cardiac function using electrocardiogram images was superior to that of human sonographers. The non-inferiority trial, which aimed to show that the tool didn’t perform worse than sonographers, is part of a larger research collaboration between Cedars-Sinai and Stanford University to develop an AI for left ventricular ejection fraction assessment.