Rachel Martin

Cardiologists use echocardiography to diagnose a range of functional or structural abnormalities of the heart. Using often over 100 videos and images that capture different parts of the heart, echocardiographers make dozens of measurements, such as the heart's size and shape, ventricle thickness, and the movement and function of each heart chamber, to assess patient heart health.

 led by Yale School of Medicine (YSM) researchers finds that an artificial intelligence (AI)-enabled tool can interpret echocardiograms with a high degree of accuracy in just a few minutes.

“Echocardiography is a cornerstone of cardiovascular care, but it requires a tremendous amount of clinical time from highly skilled readers to review these studies,” says 

, assistant professor of medicine (cardiovascular medicine) at YSM and of biostatistics (health informatics) at Yale School of Public Health. Khera is the paper's senior author and director of the 

). “We wanted to develop a technology that can assist these very busy echocardiographers to help improve accuracy and accelerate their workflow.”

The researchers found the AI tool, PanEcho, could perform 39 diagnostic tasks based on multi-view echocardiography and accurately detect conditions such as severe aortic stenosis, systolic dysfunction, and left ventricle ejection fraction, among others. This study builds on previous publications, including a 2023 publication in the 

, that demonstrated the technology’s accuracy.

, a PhD student at the University of Texas Austin who is co-advised by Khera and is co-first author of the study, says, “We developed a tool that integrates information from many views of the heart to automatically identify the key measurements and abnormalities that a cardiologist would include in a complete report.”

 was developed using 999,727 echocardiographic videos collected from Yale New Haven Health patients between January 2016 and June 2022. Researchers then validated the tool using studies from 5,130 Yale New Haven Health patients as well as three external data cohorts from the Heart and Vascular Center of Semmelweis University in Budapest, Hungary; Stanford University Hospital; and Stanford Health Care.

“The tool can now measure and assess a wide range of heart conditions, making it much more attractive for future clinical use,” says 

, clinical fellow (cardiovascular medicine) and co-first author of the study. “While it is highly accurate, it can be less interpretable than the read from a clinician. It’s still an algorithm and it requires human oversight.”

Potential roles for AI in interpreting echocardiography

While PanEcho is not yet available for clinical use, the paper discusses several potential future clinical applications of the technology. For instance, echocardiographers could utilize the tool as a preliminary reader to help assess images and videos in the echocardiography lab. It could also serve as a second set of eyes to help identify potentially missed abnormalities in existing databases.

The researchers also note that this technology could be particularly valuable in low-resource settings, where access to equipment and skilled echocardiographers is limited. In these environments, clinicians often rely on handheld, point-of-care ultrasound devices, which produce lower-quality imaging that can be more challenging to interpret.

To validate the model’s accuracy with point-of-care ultrasounds, the researchers used imaging from the Yale New Haven Hospital emergency department, which performs point-of-care ultrasounds as part of routine care.

“We replicated the experience of low-resource settings across the world, where clinicians typically use a handheld ultrasound and wait for those images to be interpreted by a cardiologist elsewhere,” says Khera. “Even with lower-quality images, our model was very resilient and acquired the information needed to make a highly accurate determination.”

Ongoing research to assess effectiveness of AI tools

Khera and his colleagues are now working to conduct studies to assess how using the tool might change patient care in the echocardiography laboratory at Yale.

“We are learning much more about how clinicians use the tool in a real-world setting, including modifications to their workflow, their responses to the information, and the value, if any, that this tool adds in a clinical context,” says Khera.

“AI tools like the one validated in this study have the potential to help us increase our efficiency and accuracy, ultimately allowing us to screen and treat a larger number of patients with cardiovascular conditions,” says 

, Robert W. Berliner Professor of Medicine (cardiovascular medicine) and chief of Yale Cardiovascular Medicine. “I’m proud of Yale’s continued commitment to investing in cutting-edge research to help us innovate new ways to deliver care.”

The full model and weights are available 

, and the research team is encouraging other investigators to test the model using their echocardiographic studies and make improvements.

Additional study authors include Zhangyang Wang, PhD, at the University of Texas at Austin, and Márton Tokodi MD, PhD, and Attila Kovács, MD, PhD, both of Semmelweis University.

The research reported in this news article was supported by

the National Institutes of Health (awards R01HL167858, K23HL153775, R01AG089981, and F32HL170592), Yale University, and other funding sources. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Articles

A recent study highlights the development of an AI-enabled tool, PanEcho, which can interpret echocardiograms with high accuracy in minutes. This tool, developed by Yale School of Medicine researchers, aims to assist echocardiographers by improving accuracy and accelerating workflow. PanEcho can perform 39 diagnostic tasks and has been validated using extensive echocardiographic data. While not yet available for clinical use, it shows promise for future applications, especially in low-resource settings. Ongoing research is assessing its impact on patient care and clinical workflows.

A clinician performing an echocardiogram of a patient's heart


AI Tool Interprets Echocardiograms in Minutes, New Yale Study Finds

Colorectal cancer is the third most common cancer and a leading cause of cancer death in the United States. Colonoscopy, recommended for all adults aged 45 or older, is a crucial screening tool where gastroenterologists remove polyps to prevent them from becoming cancerous. Recognizing the importance of detecting these polyps, the FDA authorized the first AI-assisted device for colonoscopies in 2021.

Dr. Gyanprakash Ketwaroo at the West Haven VA emphasizes the value of AI in providing a "second set of eyes" during colonoscopies. This technology, known as computer-aided detection (CADe), has shown promise in increasing adenoma detection rates, according to a meta-analysis led by Dr. Dennis Shung. The analysis, which reviewed 44 studies, found that CADe systems improved adenoma detection compared to standard colonoscopies, although the increase in advanced colorectal neoplasia detection was slight.

Shung's meta-analysis suggests further research is needed to assess AI's impact on interval colorectal cancer rates and recommends that future studies should randomize colonoscopists to understand better where CADe can be most effective. Yale has implemented this AI technology at the West Haven VA campus, providing additional support for endoscopists and trainees during procedures.

The American Gastroenterological Association (AGA) is also preparing new clinical guidelines for using AI in colonoscopies, for which Dr. Shung is the co-first author. These draft guidelines conditionally recommend CADe for polyp detection in adults, considering the technology's safety and efficiency. The AGA is gathering feedback from both providers and patients on AI use in screening, aiming to publish the final guideline in March 2025, with regular updates as the technology evolves.

Overall, AI-assisted colonoscopies represent a significant advancement in colorectal cancer screening, with the potential to enhance detection rates and outcomes for patients. Clinicians are advised to stay informed on evolving guidelines and technological developments to offer the best care possible.

Colorectal cancer ranks as the third most prevalent cancer and a major cause of cancer mortality in the U.S. Colonoscopy is vital for early detection, with AI-assisted devices enhancing polyp detection. The FDA approved the first AI device for colonoscopies in 2021, and studies show improved adenoma detection rates with AI. Further research is needed to evaluate AI's impact on interval cancer rates. The American Gastroenterological Association is developing guidelines for AI use in colonoscopies, with final recommendations expected in March 2025, emphasizing the importance of staying updated on advancements.

Computer-aided detection during colonoscopies with AI may help increase adenoma detection rates.

AI-Assisted Colonoscopy: New Research and Guidelines for Clinical Use

Hypertension is a prevalent condition in the U.S. that can lead to severe health complications, particularly among Black or Hispanic adults, as well as rural, uninsured, and low-income populations. Regular screening is crucial, as high blood pressure often presents no symptoms. Dr. Erica Spatz at Yale School of Medicine, along with Dr. Rafael Pérez-Escamilla, is spearheading the Pressure Check study to address disparities in blood pressure management, supported by a substantial PCORI funding award.

The study involves a partnership with community-based organizations (CBOs) across four diverse health sites. It aims to compare three strategies for blood pressure control: education and wireless monitoring with a referral to a primary care provider, the addition of biweekly telehealth support, and the integration of a community health worker to assist with social barriers to health.

To date, CBOs have screened nearly 2,000 individuals and enrolled over 330 in the study, which will monitor participants over 18 months to evaluate the most effective control method. The approach emphasizes community engagement and trust-building, acknowledging past research mistrust. The study uses cellular-enabled blood pressure cuffs provided by Stel, which allow secure data transfer without the need for smartphones or Wi-Fi, addressing technology barriers.

Participants also manually record their blood pressure readings to observe trends. The goal is to highlight the importance of controlling blood pressure by delivering care that meets individuals where they are. The study is embedded within Yale's Department of Internal Medicine, recognized for its excellence in integrating clinical care, research, and education. For more information, readers are encouraged to visit the Internal Medicine page of the Yale School of Medicine website.

Hypertension is a significant health issue in the U.S., disproportionately affecting Black, Hispanic, rural, uninsured, and low-income populations. The Pressure Check study, led by Dr. Erica Spatz and Dr. Rafael Pérez-Escamilla, aims to address disparities in blood pressure management through community-based partnerships. The study evaluates three strategies: education with wireless monitoring, biweekly telehealth support, and community health worker integration. Nearly 2,000 individuals have been screened, with over 330 enrolled. The study emphasizes community engagement, trust-building, and overcoming technology barriers using cellular-enabled blood pressure cuffs.

The Pressure Check study at Yale aims to address disparities in blood pressure management.