8 hours ago
1
This new AI heart disease detector can’t be beat.
Structural heart disease (SHD) refers to defects in the heart’s valves, wall or chambers that are present at birth or develop over time. These abnormalities can impair the heart’s ability to pump blood effectively.
SHD is sometimes described as “hidden” heart disease because it can progress without noticeable symptoms — until there’s a major event like a heart attack or stroke.
Now, researchers at Columbia University and NewYork-Presbyterian have developed an AI-
powered screening tool to identify who should undergo a key ultrasound used to diagnose structural heart problems.
“There has been a growth in the number of AI models to detect, or opportunistically screen, disease,” Dr. Pierre Elias, an assistant professor of medicine and biomedical informatics at Columbia’s Vagelos College of Physicians and Surgeons, told The Post.
“Some of the most exciting can look for coronary disease on CT scans or look at mammograms to help doctors find breast cancer more accurately,” he added. “EchoNext is the first model to detect all forms of structural heart disease from ECGs.”
An electrocardiogram (ECG) is a quick, non-invasive procedure that measures the heart’s electrical activity.
It’s one of the most frequently used cardiac tests, often ordered when patients experience symptoms such as shortness of breath, chest pain, palpitations or sudden loss of consciousness.
While an ECG can detect some heart conditions, it’s not reliable for catching SHD on its own.
Enter EchoNext. The tool, fine-tuned over four years, analyzes ECG data to determine when follow-up with an echocardiogram is necessary.
An echocardiogram is an ultrasound imaging test used to diagnose a range of heart conditions, including valve disorders and congenital heart defects.
“EchoNext basically uses the cheaper test to figure out who needs the more expensive ultrasound,” said Elias, study leader and medical director for artificial intelligence at NewYork-Presbyterian.
“It detects diseases cardiologists can’t from an ECG,” he continued. “We think that ECG plus AI has the potential to create an entirely new screening paradigm.”
EchoNext was trained on over 1.2 million ECG–echocardiogram pairs from 230,000 patients.
The tool accurately detected 77% of structural heart problems on 3,200 ECGs, outperforming 13 cardiologists who logged a 64% accuracy.
EchoNext then identified over 7,500 people from a pool of nearly 85,000 study participants as high risk for undiagnosed SHD.
The researchers followed the patients for a year without telling their physicians about the forewarning.
Some 55% went on to have their first echocardiogram. Of those, almost three-quarters were diagnosed with SHD, a much higher positivity rate than usual.
The findings were published Wednesday in the journal Nature.
“The goal is to get the right patients to the right doctor and treatment sooner,” Elias said.
“The reality is many patients that need a cardiologist are often missed, and EchoNext helps facilitate getting these patients to the cardiologist who can then get the patient to the treatment they need.”
Looking ahead, Columbia has submitted a patent application on the EchoNext ECG algorithm.
A clinical trial to test EchoNext in eight emergency departments is also underway.
English (US)