ROCHESTER, Minn. — The first sign of cardiovascular disease is often a serious event, such as a heart attack, stroke, or cardiac arrest. Now, Mayo Clinic researchers and clinicians are using artificial intelligence (AI) technology to detect heart problems early, harnessing the power of the electrocardiogram (ECG), a diagnostic test used for more than a century. It’s increasing.

Early detection of heart disease can make a huge difference in a patient’s quality of life and longevity, but the lack of definitive symptoms adds further complexity. AI-enabled ECGs detect heart disease early and track disease progression using tests that are relatively inexpensive, readily available, and often already part of a patient’s electronic health record. Provide possible ways.

Mayo Clinic is currently using an ECG-AI algorithm in research to predict a patient’s likelihood of developing heart conditions such as atrial fibrillation, amyloidosis, aortic stenosis, low ejection fraction, and hypertrophic cardiomyopathy (HCM). has been developed. AI can also predict a patient’s biological age using traditional 12-lead and single-lead ECGs from smartwatches and portable devices.

One standout application is the use of ECG-AI to detect low ejection fraction, commonly referred to as a weak heart pump. A 12-lead algorithm for detecting this condition has been cleared for clinical use by the Food and Drug Administration (FDA) and licensed to Anumana. The single-lead algorithm for a handheld device applied externally to the chest has been licensed to Eko Health for commercial development.

Diagnose heart pump weakness

About 3% of Americans have a treatable condition called low ejection fraction, which weakens the heart and pumps less blood to the body. Although the underlying causes and symptoms are often treatable, people may not realize their condition until symptoms such as shortness of breath, fatigue, or swelling in the legs worsen. If left untreated, heart failure can worsen, affect quality of life, and become severe enough to require a heart transplant or lead to cardiac arrest.

Unfortunately, symptoms caused by a slow heart pump can be confused with those seen in normal pregnancy. At the Mayo Clinic in Florida, cardiologist Demirado Adiinsewo, MD, MB, Ch.B., is using her AI as a tool to detect a disease in women called peripartum cardiomyopathy. Peripartum cardiomyopathy is a weak heart pump that can occur during pregnancy or immediately after childbirth. Myocardial weakness can be predicted using her AI from her conventional 12-lead ECG, as well as her AI-enabled digital stethoscope that captures single-lead ECG and heart sound recordings.

“Our study of obstetric patients in Nigeria shows that portable technology, like an AI-enabled digital stethoscope, alerts twice as many cases of peripartum cardiomyopathy compared to routine care. This suggests that it is possible,” Dr. Adiyinsewo said. “This could be a powerful tool to bring portable cardiomyopathy diagnostics to more women in underserved urban and rural areas around the world. Access is an important consideration in addressing health disparities in the United States, as women are up to 16 times more likely to develop peripartum cardiomyopathy compared to white women. ”

Watch: Dr. Demirado Adinsewo explains peripartum cardiomyopathy in Mayo Clinic Proceedings

Amyloid accumulates in the heart

Amyloidosis is a rare disease in which proteins misfold, forming amyloid deposits in organs, nerves, and tissues. There are several different types, and when enough amyloid builds up in the heart, it can cause symptoms such as heart failure, shortness of breath, fluid buildup, and fainting. Patients may also have heart rhythm problems and may require a pacemaker. Although there is no cure for amyloidosis, early diagnosis is important because it can be treated with new treatments that can dramatically reduce amyloid production and halt disease progression.

Mayo Clinic clinicians may be able to use ECG-AI to flag patients in the early stages of cardiac amyloidosis. This technology is being used in research and has been designated as an FDA Breakthrough Device.

“We have done some research that shows that when applied to ECGs alone, artificial intelligence can often suggest whether a patient has a diagnosis before the clinician even suspects the diagnosis. “We believe this is the way to make a diagnosis: early diagnosis,” says Dr. Martha Grogan, a cardiologist at the Mayo Clinic in Rochester, Minnesota. “Now we need to put this into a clinical context. AI ECG is not just one of those things, and it can be very helpful in suspecting amyloidosis.”

“This is a very powerful tool because it’s inexpensive and available almost everywhere. Our research shows that even a single lead, which can be run on a watch or a simple mobile device, can predict amyloidosis. ”. Dr. Grogan. “Thus, we can imagine that in underserved populations around the world, especially high-risk groups, a simple electrocardiogram could help determine whether a patient has amyloidosis. ”

Video: Dr. Martha Grogan talks about using AI and ECG to detect cardiac amyloidosis

Journalists: Broadcast quality soundbites by Dr. Grogan are available in the downloads at the end of the post. Courtesy: “Mayo Clinic News Network.” Super/CG Name: Martha Grogan MD/Cardiovascular Medicine/Mayo Her Clinic.

hypertrophic cardiomyopathy

Hypertrophic cardiomyopathy is one of the most common inherited heart diseases, affecting 1 in 200 to 500 people. HCM occurs when the heart’s walls thicken over time, blocking the heart’s electrical signals and increasing the risk of sudden cardiac death. Unfortunately, symptoms are often not noticed until the disease is advanced. It’s like there’s a silent intruder inside your mind.

Early detection is important but difficult. HCM is not always visible on basic tests such as a 12-lead ECG. Most patients do not undergo resource-intensive tests, such as echocardiograms or MRIs, unless a problem is suspected. However, ECG-AI can detect HCM by recognizing subtle patterns that even expert clinicians may miss.

“Applying this AI algorithm to routine ECGs could make early detection of HCM more practical as part of a heart health exam,” said Konstantinos Siontis, MD, cardiac electrophysiologist at the Mayo Clinic in Rochester. “It shows promise as a means of making it more accurate, more accessible, and easier to use.” “Athletes with undiagnosed HCM may be at higher risk of developing dangerous arrhythmias during exercise and may benefit from early detection. Additionally, HCM often runs in families. Therefore, early detection in one person can lead to identifying other family members at risk.”

###

About Mayo Clinic
Mayo Clinic is a nonprofit organization dedicated to innovation in clinical practice, education and research, providing compassion, expertise and answers to all who need healing. For more Mayo Clinic news, visit Mayo Clinic News Network.

Media contact:

Related article