AI-Powered EchoNext Tool Revolutionizes Heart Disease Detection Using ECG Data

AI tool spots hidden heart disease using routine electrocardiogram data

With the help of artificial intelligence (AI), an inexpensive test found in many doctors' offices may soon be used to screen for hidden heart disease. Structural heart disease, including valve disease, congenital heart disease, and other issues that impair heart function, affects millions of people worldwide. Yet in the absence of a routine, affordable screening test, many structural heart problems go undetected until significant function has been lost. "We have colonoscopies, we have mammograms, but we have no equivalents for most forms of heart disease," says Pierre Elias, assistant professor of medicine and biomedical informatics at Columbia University Vagelos College of Physicians and Surgeons and medical director for artificial intelligence at NewYork-Presbyterian. Elias and researchers at Columbia University and NewYork-Presbyterian developed an AI-powered screening tool, EchoNext, that analyzes ordinary electrocardiogram (ECG) data to identify patients who should have an ultrasound (echocardiogram), a non-invasive test that is used to diagnose structural heart problems. In a study published in Nature, EchoNext accurately identified structural heart disease from ECG readings more often than cardiologists, including those who used AI to help interpret the data. "EchoNext basically uses the cheaper test to figure out who needs the more expensive ultrasound," says Elias, who led the study. "It detects diseases cardiologists can't from an ECG. We think that ECG plus AI has the potential to create an entirely new screening paradigm." The (echo)next step in cardiovascular screening The ECG is the most used cardiac test in health care. The test, which measures electrical activity in the heart, is typically used to detect abnormal heart rhythms, blocked coronary arteries, and prior heart attack. ECGs are inexpensive, non-invasive, and often administered to patients who are being treated for conditions unrelated to structural heart disease. While ECGs have their uses, they also have limitations. "We were all taught in medical school that you can't detect structural heart disease from an electrocardiogram," Elias says. Echocardiograms, which use ultrasound to obtain images of the heart, can be used to definitively diagnose valve disease, cardiomyopathy, pulmonary hypertension, and other structural heart problems that require medication or surgical treatment. EchoNext was designed to analyze ordinary ECG data to determine when follow-up with cardiac ultrasound is warranted. The deep learning model was trained on more than 1.2 million ECG-echocardiogram pairs from 230,000 patients. In a validation study across four hospital systems, including several NewYork-Presbyterian campuses, the screening tool demonstrated high accuracy in identifying structural heart problems, including heart failure due to cardiomyopathy, valve disease, pulmonary hypertension, and severe thickening of the heart. In a head-to-head comparison with 13 cardiologists on 3,200 ECGs, EchoNext accurately identified 77% of structural heart problems. In contrast, cardiologists making a diagnosis with the ECG data had an accuracy of 64%. Finding undiagnosed structural heart problems To see how well the tool worked in the real world, the research team ran EchoNext in nearly 85,000 patients undergoing ECG who had not previously had an echocardiogram. The AI tool identified more than 7,500 individuals -- 9% -- as at high-risk of having undiagnosed structural heart disease. The researchers then followed the patients over the course of a year to see how many were diagnosed with structural heart disease. (The patients' physicians were not aware of the EchoNext deployment so they were not influenced by its predictions). Among the individuals deemed high-risk by EchoNext, 55% went on to have their first echocardiogram. Of those, nearly three-quarters were diagnosed with structural heart disease -- twice the rate of positivity when compared to all people having their first echocardiogram without the benefit of AI. At the same positivity rate, if all the patients identified by EchoNext as high-risk had had an echocardiogram, about 2,000 additional patients may have been diagnosed with a potentially serious structural heart problem. "You can't treat the patient you don't know about," Elias says. "Using our technology, we may be able to turn the estimated 400 million ECGs that will be performed worldwide this year into 400 million chances to screen for structural heart disease and potentially deliver life-saving treatment at the most opportune time," Elias says. Elias and his team released a deidentified dataset to help other health systems improve screening for heart disease. The researchers have also launched a clinical trial to test EchoNext across eight emergency departments.

AI can identify hidden heart valve defects from a patient's EKG

An AI algorithm could help to predict which patients might develop significant heart problems years in advance, just based on EKG readings. In a study published in the European Heart Journal, researchers found that their AI could spot very early changes in the heart's structure from an EKG, a common test which shows the heart's electrical activity. The advanced algorithm could detect issues in the heart's valves -- which keep blood flowing in the correct direction through the heart's chambers -- even before the appearance of symptoms or physical changes that can be detected by ultrasound scans. The AI could accurately predict who would go on to develop significant leaks in the heart's mitral, tricuspid, or aortic valves -- conditions known as regurgitant valvular heart diseases. It was able to correctly identify the risk of a leaky heart valve in the years following the EKG (from high to low) in about 69%-79% of cases. People flagged as "high-risk" by the algorithm were up to 10 times more likely to develop these diseases than those classed as lower risk. According to the team from Imperial College London and Imperial College Healthcare NHS Trust, their AI-enhanced predictions could potentially transform doctors' approach to treating heart valve disease. It's estimated that 41 million people worldwide, including 1.5 million people in the U.K., live with these heart valve diseases, which can lead to heart failure, hospital admissions and death. Early diagnosis is key for successful treatment. But the symptoms, which can include shortness of breath, dizziness, feeling tired and having heart palpitations, can be easily confused with other causes, while some patients don't show any symptoms until the disease is advanced. Earlier detection Dr. Arunashis Sau, one of the study leads, Academic Clinical Lecturer at Imperial College London's National Heart and Lung Institute, and cardiology registrar at Imperial College Healthcare NHS Trust said, "Our hearts are incredibly complex and hard-working organs, but we rarely give them much consideration unless something goes wrong. By the time symptoms and structural changes appear in the heart, it may be too late to do much about it. "Our work is harnessing AI to detect subtle changes at the earliest stage from a simple and common test, and we think this could be really transformative for doctors and patients. Rather than waiting for symptoms, or relying only on expensive and time-consuming imaging tests, we could use AI-enhanced EKGs to spot those most at risk earlier than ever before. "This means that many more people could get the care they need before their hidden condition affects their quality of life or becomes life-threatening." The study was part of an international collaboration led by researchers Drs. Sau and Dr. Fu Siong Ng and involving researchers in China, based at Shanghai's Zhongshan Hospital. AI models were trained using nearly 1 million EKG and heart ultrasound (echocardiogram) records from more than 400,000 patients in China. The technology was then tested on a separate group of more than 34,000 patients in the United States, showing that it works well across ethnically diverse populations and health care systems. Issues with heart valves may first appear as very small changes to the heart's electrical activity which are not apparent to doctors. These electrical changes become larger but by this point, symptoms have often started to develop. The AI system can detect these subtle electrical patterns much earlier, hopefully before symptoms develop at all. Dr. Ng, the senior author, Reader in Cardiac Electrophysiology at the National Heart & Lung Institute at Imperial College London and a consultant cardiologist at Imperial College Healthcare NHS Trust and Chelsea and Westminster Hospital NHS Foundation Trust, said, "AI has enormous potential for improving health care around the world, but it requires huge amounts of data to train and test these algorithms. Our work is an example of the benefits of international collaboration in this fast-growing area. By training the model in an almost exclusively Chinese population and then testing in a U.S. cohort, we can show that our AI tool has the potential to be applied in various countries and settings around the world. This ultimately means it has the potential to help even more patients." Continued work The research follows on from the team's development of the related AI-EKG risk estimation model, known as AIRE, which can predict patients' risk of developing and worsening disease from an EKG. Other AI models from this project have been trained to analyze EKGs to predict problems such as female heart disease risk, health risks including early death, high blood pressure and type 2 diabetes.

Exclusive | New AI tool can detect 'hidden' heart disease 77% of the time,...

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.