American Heart Association

11/09/2026 | Press release | Distributed by Public on 11/09/2026 10:41

AI-interpreted echocardiograms comparable to human reports, cardiologists’ time cut by about 50%

AI-interpreted echocardiograms comparable to human reports, cardiologists' time cut by about 50%

American Heart Association Scientific Sessions 2026, Late-Breaking Science Abstract 28202

Research Highlights:

  • In a study to test an artificial intelligence (AI) model for evaluating heart ultrasound exams (echocardiograms), the AI-assisted interpretations were comparable in accuracy to preliminary interpretations prepared by sonographers and cardiologists.
  • Having AI-generated preliminary interpretations reduced the time cardiologists spent interpreting each scan by nearly half, from 8.5 to 4.6 minutes, and the AI-generated reports were more consistent with historical clinical reports.
  • Researchers say these results demonstrate the potential for AI to be a useful tool that can assist cardiologists and improve the efficiency of cardiology practice.
  • Note: The study featured in this news release is a research abstract. Abstracts presented at the American Heart Association's scientific meetings are not peer-reviewed, and the findings are considered preliminary until published as a full manuscript in a peer-reviewed scientific journal.

Embargoed until 10:22 a.m. CT/11:22 a.m. ET, Monday, Nov. 9, 2026

CHICAGO, Nov. 9, 2026 - AI-generated (artificial intelligence created) interpretations of echocardiograms were comparable in accuracy to preliminary interpretations prepared by ultrasound technicians (sonographers) and cardiologists. The assistance of AI preliminary interpretations also reduced the time cardiologists spent interpreting each scan almost by half. All of this is according to new, independent, preliminary late-breaking science presented today at the American Heart Association's Scientific Sessions 2026. The meeting on Nov. 6-9 in Chicago is a premier global exchange of the latest scientific advancements, research and evidence-based clinical practice updates in cardiovascular science.

An echocardiogram or heart ultrasound is the most widely used type of heart imaging, giving healthcare professionals key information to diagnose heart conditions and select treatment options. The current process is for a sonographer to acquire the images, and a cardiologist to review the images and write a report assessing various heart structures and function. In this study, researchers tested the use of an AI tool to analyze ultrasound images and draft preliminary reports to assist cardiologists.

Researchers say this is the first randomized trial testing an AI tool to craft a full echocardiogram report including interpretations and measurements. In the research study, an AI tool, a sonographer and a cardiologist each prepared preliminary reports for the same 1,200 echocardiograms previously acquired during routine clinical care. The preliminary interpretations were then randomly assigned to cardiologists for review and finalization without knowing whether the first draft was made by a sonographer, a cardiologist or the AI tool. Researchers assessed accuracy by looking at how often cardiologists made substantial changes to the preliminary interpretations before finalizing them. Additionally, the time spent completing each interpretation and consistency with historical interpretations in the medical record were evaluated.

What are the study's key findings?

  • Cardiologists made substantial changes to 50.6% of the AI-generated preliminary interpretations, compared with 49.7% of the preliminary interpretations prepared by sonographers and cardiologists. The results showed that the AI-assisted approach was comparable in accuracy to the human-assisted approaches. The results met the study's criteria for the AI-assisted approach to be considered non-inferior, or comparable in accuracy, to the human-assisted approaches.
  • Cardiologists spent an average of 4.6 minutes per echocardiogram reviewing and finalizing AI-generated preliminary interpretations, compared with 8.5 minutes to generate interpretation reports without AI assistance, a time savings of about 46%. These results demonstrate the potential for AI to improve the efficiency of everyday cardiology practice.
  • The AI-assisted reports were more consistent with historical reports in the medical record than reports in the comparison group.
  • The reviewing cardiologists could not identify whether the preliminary interpretation was prepared by the AI tool, a sonographer or another cardiologist.

"We designed this study to capture even small differences between the preliminary reports and the cardiologists' final interpretations, allowing us to take a careful look at how well AI performed in a rigorous scientific manner," said co-senior author Keane K. Lee, M.D., M.S., a cardiologist at Kaiser Permanente Santa Clara Homestead Medical Center in Santa Clara, California. "Based on our prior work, we expected AI to demonstrate excellent accuracy, which was confirmed in this randomized trial. However, what surprised us was the extent to which using AI-generated reports reduced the time cardiologists needed to interpret echocardiograms."

"Because of the large number of echocardiograms cardiologists read, even a few minutes saved per interpretation can add up to a significant amount of time over the course of a day," Lee said. "For patients, this could potentially mean faster turnaround of results and more access to care, and for cardiologists, more time to spend with patients."

"AI cannot, however, replace the human team," Lee added. "The cardiologist remains ultimately responsible for interpreting the echocardiogram and certifying the accuracy of the final report, even when AI assists with the process. Moreover, the physician applies clinical judgment and knowledge of the patient to the final interpretation to develop a personalized care plan for each individual."

According to a July 2026 study published in the Journal of the American Heart Association, experts anticipate a shortage of cardiologists in the U.S. over the next two decades, with research projections from the U.S. Department of Health and Human Services' Health Resources and Services Administration estimating a national shortfall of about 7,000cardiologists by 2036. That study notes the need to implement strategies to strengthen the cardiology workforce.

What are the study's details, background, design and limitations?

  • The study included 1,200 echocardiogram exams performed over two weeks in March 2025 in hospital and outpatient clinic settings within 21 medical centers across Kaiser Permanente Northern California.
  • The patients' average age at the time of the echocardiograms was 69 years old, and 47% of participants were women and 53% were men. About 54% of participants self-identified as white adults; 16% were Hispanic adults; about 16% were Asian adults; 8.8% were Black adults; and 5.8% self-identified as other.
  • Nine sonographers (average of 7.2 years of experience) and 20 cardiologists (average of 11.7 years of experience) participated in the study.
  • The AI tool, sonographers and cardiologists each prepared a preliminary report for every echocardiogram. The reports were randomly assigned to cardiologists, who finalized them without knowing who prepared them.
  • The study measured how often cardiologists made substantial changes to preliminary interpretations, how long they spent completing interpretations, consistency with historical reports in the medical record and whether they could tell if the preliminary interpretation was AI- or human-generated.
  • Limitations of the study include that it did not test whether using AI to help interpret echocardiograms improves patients' long-term health. In addition, cardiologists knew they were part of this study, so they may have adjusted their usual work patterns.
  • More research is needed to assess how AI-assisted interpretation may perform in real-world clinical settings with larger scale and volume of exams.

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 guarantee 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.

For Media Inquiries and American Heart Association Expert Perspective:

American Heart Association Communications & Media Relations in Dallas: 214-706-1173; [email protected]

Michelle Kirkwood: [email protected]

For Public Inquiries: 1-800-AHA-USA1 (242-8721)

heart.org and stroke.org

American Heart Association published this content on November 09, 2026, and is solely responsible for the information contained herein. Distributed via Public Technologies (PUBT), unedited and unaltered, on November 09, 2026 at 16:41 UTC. If you believe the information included in the content is inaccurate or outdated and requires editing or removal, please contact us at [email protected]