Monday, November 03, 2025

 

An AI tool detected structural heart disease in adults using a smartwatch



American Heart Association Scientific Sessions 2025, Abstract 4369348



American Heart Association

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail





Research Highlights:

  • An artificial intelligence (AI) tool detected structural heart problems using a single-lead ECG captured by the electrical heart sensor on the back and digital crown of a smartwatch.
  • The AI algorithm was tested on single-lead ECGs taken on a smartwatch in a group of 600 adults. The algorithm accurately identified structural heart diseases such as weakened pumping ability, damaged valves or thickened heart muscle.
  • Smartwatches with single-lead ECG sensors paired with an AI tool such as the one developed for this study could help make screening for structural heart disease easier and more accessible to everyone.
  • Note: The study featured in this news release is a research abstract. Abstracts presented at American Heart Association’s scientific meetings are not peer-reviewed, and the findings are considered preliminary until published as full manuscripts in a peer-reviewed scientific journal.

Embargoed until 4 a.m. CT/5 a.m. ET, Monday, Nov. 3, 2025

DALLAS, Nov. 3, 2025 — An artificial intelligence (AI) algorithm paired with the single-lead electrocardiogram (ECG) sensors on a smartwatch accurately diagnosed structural heart diseases, such as weakened pumping ability, damaged valves or thickened heart muscle, according to a preliminary study to be presented at the American Heart Association’s Scientific Sessions 2025. The meeting, Nov. 7-10, in New Orleans, is a premier global exchange of the latest scientific advancements, research, and evidence-based clinical practice updates in cardiovascular science.

Researchers said this is the first prospective study to show that an AI algorithm can detect multiple structural heart diseases based on measures taken from a single-lead ECG sensor on the back and digital crown of a smartwatch.

“Millions of people wear smartwatches, and they are currently mainly used to detect heart rhythm problems such as atrial fibrillation. Structural heart diseases, on the other hand, are usually found with an echocardiogram, an advanced ultrasound imaging test of the heart that requires special equipment and isn’t widely available for routine screening,” said study author Arya Aminorroaya, M.D., M.P.H., an internal medicine resident at Yale New Haven Hospital and a research affiliate at the Cardiovascular Data Science (CarDS) Lab at Yale School of Medicine in New Haven, Connecticut. “In our study, we explored whether the same smartwatches people wear every day could also help find these hidden structural heart diseases earlier, before they progress to serious complications or cardiac events.”

Researchers developed the AI algorithm using more than 266,000 12-lead ECG recordings from more than 110,000 adults. Based on this library of data, they developed an algorithm to identify structural heart disease from a single-lead ECG that can be obtained using smartwatch sensors. For this purpose, researchers isolated only one of the 12 leads of the ECG, which resembles the single-lead ECG on smartwatches. They also accounted for random interference in ECG signaling or “noise” that could arise during the recording of a single-lead ECG using real-world smartwatches. The AI model was then externally validated using data from people seeking care at community hospitals, as well as data from a population-based study from Brazil. Then, they prospectively recruited 600 participants who underwent 30-second, single-lead ECGs using a smartwatch to gauge the algorithm’s accuracy in a real-world setting.

The analysis found:

  • Using single-lead ECGs obtained from hospital equipment, the AI model was very effective at distinguishing people with and without structural heart disease, scoring 92% on a standard performance scale (where 100% is perfect).
  • Among the 600 participants with the single-lead ECGs obtained from a smartwatch, the AI model maintained high performance at 88% for detecting structural heart disease.
  • The AI algorithm accurately identified most people with heart disease (86% sensitivity) and was highly accurate in ruling out heart disease (99% negative predictive value).

“On its own, a single-lead ECG is limited; it can’t replace a 12-lead ECG test available in health care settings. However, with AI, it becomes powerful enough to screen for important heart conditions,” said Rohan Khera, M.D., M.S., the senior author of the study, and the director of the CarDS Lab. “This could make early screening for structural heart disease possible on a large scale, using devices many people already own.”

Study background, details, and design:

  • Researchers used a database of 266,054 ECGs from 110,006 patients who received testing and treatment at Yale New Haven Hospital between 2015 and 2023 to develop an AI-ECG algorithm to detect structural heart disease from single-lead ECGs.
  • The algorithm was matched to heart ultrasound scans to see whether they had structural heart disease or not.
  • The AI model was then validated in 44,591 adults seeking care at four community hospitals and 3,014 participants from the population-based ELSA-Brasil study. The Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) gathers important information about how chronic diseases develop and progress, focusing mainly on cardiovascular diseases and diabetes.
  • To get the AI model ready for interpreting signals from real-world, single-lead ECGs, researchers added some “noise” — think of it like fuzz or static — into the mix for model training. This little tweak helped the AI become resilient and more reliable when dealing with less-than-perfect signals, making it better at spotting structural heart disease even when the data isn’t crystal clear.
  • During the real-world prospective study, 600 patients wore the same type of smartwatch with a single-lead ECG sensor for 30 seconds on the same day they were getting a heart ultrasound.
  • The median age of the participants was 62 years, and about half were women, 44% were non-Hispanic white, 15% non-Hispanic Black, 7% Hispanic, 1% Asian and 33% others. About 5% were found to have structural heart disease on the heart ultrasound.

Study limitations include a small number of patients with the actual disease in the prospective study and the number of false positive results.

“We plan to evaluate the AI tool in broader settings and explore how it could be integrated into community-based heart disease screening programs to assess its potential impact on improving preventive care,” Aminorroaya said.

Co-authors, disclosures, and funding sources are listed in the abstract.

Statements and conclusions of studies that are presented at the American Heart Association’s scientific meetings are solely those of the study authors and do not necessarily reflect the Association’s policy or position. The Association makes no representation or guarantees as to their accuracy or reliability. Abstracts presented at the Association’s scientific meetings are not peer-reviewed; rather, they are curated by independent review panels and are considered based on the potential to add to the diversity of scientific issues and views discussed at the meeting. The findings are considered preliminary until published as a full manuscript in a peer-reviewed scientific journal.

The Association receives more than 85% of its revenue from sources other than corporations. These sources include contributions from individuals, foundations and estates, as well as investment earnings and revenue from the sale of our educational materials. Corporations (including pharmaceutical, device manufacturers and other companies) also make donations to the Association. The Association has strict policies to prevent any donations from influencing its science content and policy positions. Overall financial information is available here.

Additional Resources:

###

About the American Heart Association

The American Heart Association is a relentless force for a world of longer, healthier lives. Dedicated to ensuring equitable health in all communities, the organization has been a leading source of health information for more than one hundred years. Supported by more than 35 million volunteers globally, we fund groundbreaking research, advocate for the public’s health, and provide critical resources to save and improve lives affected by cardiovascular disease and stroke. By driving breakthroughs and implementing proven solutions in science, policy, and care, we work tirelessly to advance health and transform lives every day. Connect with us on heart.org, Facebook, X or by calling 1-800-AHA-USA1.

Smartphones can monitor patients with neuromuscular diseases


Smartphones track neuromuscular diseases



Stanford Medicine

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail



Because researchers have made such striking progress in developing drugs to treat neuromuscular diseases, Scott Delp, PhD, was surprised to learn that scientists conducting clinical trials were still relying on a decidedly low-tech tool to track whether those treatments were working: a stopwatch.

In a study published in the New England Journal of Medicine, Delp, a professor of bioengineering, and his collaborators showed that a smartphone could do the job as well or better. With two smartphone cameras and a free app, they were able to replicate results from standard movement tests for two neuromuscular diseases and capture more detail about patients’ physical abilities.

“Our goal was to bring the world’s most sophisticated biomechanical modeling and computer vision to bear in order to match what’s happening on the drug development side,” Delp said.

Delp is the senior author of the study. Parker Ruth, a doctoral student in computer science at Stanford University, is the lead author.

Clinicians typically use a stopwatch to capture how long it takes people with movement-related conditions to complete specific tasks, such as standing up from a chair or walking 10 meters. Known as a timed function test, this method is quick and inexpensive, but it can’t detect subtle changes in how patients move, especially in diseases that progress slowly.

For a more detailed view, patients need to visit a motion analysis lab, where hourslong biomechanical assessments require highly trained technicians and equipment that costs hundreds of thousands of dollars. “The status quo is that very few people can have their motion measured, and this is rarely used clinically — usually between zero and once in a person’s lifetime,” Delp said.

To test whether mobile phones could do the job, Delp and his collaborators used up to three smartphone cameras to record nearly 130 people as they performed nine movements, such as a 10-meter run and calf raise. Two-thirds of participants had a neuromuscular disease — facioscapulohumeral muscular dystrophy (FSHD) or myotonic dystrophy (DM) — while the rest had no diagnosed movement problems. At the same time, clinical evaluators performed four traditional timed function tests. The process took an average of just 16 minutes.

Researchers converted the videos into 3D models using OpenCap, an open-source tool that Delp and his team at Stanford released in 2023. The software automatically created a “digital twin” of each participant, allowing the team to measure range of motion, stride length, speed and other aspects of movement. Researchers then translated the data into 34 features of movement that are relevant to FSHD and DM, such as how high patients lift their ankles while walking.

Based on the smartphone data, researchers inferred nearly identical time scores to those measured with a stopwatch. When a subset of participants repeated the tests the next day, the smartphone system proved just as reliable. “With just a video, you can reproduce what an experienced and busy clinician would do in a clinic,” Delp said.

A better diagnostic tool

The videos also revealed disease-specific movement patterns that timed tests can’t capture. For example, people with FSHD took shorter strides and lifted their ankles higher while walking, while those with DM had more difficulty rising from a chair. Based on the footage, a computer model could identify the disease a person had with 82% accuracy, compared with 50% accuracy for the stopwatch method.

The findings suggest that analyses once confined to specialized labs can now be done quickly, anywhere and for free.

“It’s really encouraging,” Delp said. “By democratizing access with smartphone videos, we think we’ll be able to detect movement disorders for free in the community. We can detect diseases earlier so patients can seek treatment sooner or participate in drug trials earlier.”

Delp and his team have begun examining how tools like OpenCap can be incorporated into clinical trials. His hope is that this approach will make measurements of therapies for neuromuscular diseases more precise, accessible and easy to implement. “We’ll have more sophisticated measures to see if therapies are working,” he said.

In the meantime, thousands of labs around the world are already using OpenCap to assess conditions such as cerebral palsy and arthritis. Germany’s national volleyball team, for example, used the tool to evaluate sports injuries in 160 athletes. “It used to take them years to get that kind of data, and with OpenCap they did it in one season,” Delp said. “They’re gaining insight into how they can perform better, avoid injury and improve faster.”

Delp emphasizes that further research is needed to ensure the tool’s accuracy for each new application. Still, he believes the technology represents the future of how doctors diagnose and track movement disorders. “This method of accurately and rapidly assessing movement is on the verge of transforming multiple fields,” he said.

Scott Uhlrich, who earned a PhD at Stanford University and is now assistant professor at the University of Utah, is also a first author on the study. Stanford Medicine’s John Day, MD, PhD, professor of neurology, and research scientist Tina Duong, PhD, and their team also played a major role in the study.

Funding came from the Wu Tsai Human Performance Alliance; the Mobilize Center at Stanford University; and the Myotonic Dystrophy Foundation, which played no role in the study design or analysis.

Journal

NEJM AI

DOI

10.1056/AIoa2401137 

Method of Research

Imaging analysis

Subject of Research

People

Article Title

Video-Based Biomechanical Analysis Captures Disease-Specific Movement Signatures of Different Neuromuscular Diseases

Posted by at

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)