PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Mount Sinai researchers use new deep learning approach to enable analysis of electrocardiograms as language

Mount Sinai researchers use new deep learning approach to enable analysis of electrocardiograms as language
2023-06-06
(Press-News.org) New York, NY (June 6, 2023) – Mount Sinai researchers have developed an innovative artificial intelligence (AI) model for electrocardiogram (ECG) analysis that allows for the interpretation of ECGs as language. This approach can enhance the accuracy and effectiveness of ECG-related diagnoses, especially for cardiac conditions where limited data is available on which to train.

In a study published in the June 6 online issue of npj Digital Medicine DOI: 10.1038/s41746-023-00840-9, the team reported that its new deep learning model, known as HeartBEiT, forms a foundation upon which specialized diagnostic models can be created. The team noted that in comparison tests, models created using HeartBEiT surpassed established methods for ECG analysis.

“Our model consistently outperformed convolutional neural networks [CNNs], which are commonly used machine learning algorithms for computer vision tasks. Such CNNs are often pretrained on publicly available images of real-world objects,” says first author Akhil Vaid, MD, Instructor of Data-Driven and Digital Medicine (D3M) at the Icahn School of Medicine at Mount Sinai. “Because HeartBEiT is specialized to ECGs, it can perform as well as, if not better than, these methods using a tenth of the data. This makes ECG-based diagnosis considerably more viable, especially for rare conditions which affect fewer patients and therefore have limited data available.”

Thanks to their low cost, non-invasiveness, and wide applicability to cardiac disease, more than 100 million electrocardiograms are performed each year in the United States alone. Nonetheless, the ECG’s usefulness is limited in scope since physicians cannot consistently identify, with the naked eye, patterns representative of disease, particularly for conditions which do not have established diagnostic criteria or where such patterns may be too subtle or chaotic for human interpretation. Artificial intelligence is now revolutionizing the science, however, with most of the work to date centered on CNNs.

Mount Sinai is taking the field in a bold new direction by building on the intense interest in so-called generative AI systems such as ChatGPT, which are built on transformers—deep learning models that are trained on massive datasets of text to generate human-like responses to prompts from users on almost any topic. Researchers are using a related image-generating model to create discrete representations of small parts of the ECG, enabling analysis of the ECG as language.

“These representations may be considered individual words, and the whole ECG a single document,” explains Dr. Vaid. “HeartBEiT understands the relationships between these representations and uses this understanding to perform downstream diagnostic tasks more effectively. The three tasks we tested the model on were learning if a patient is having a heart attack, if they have a genetic disorder called hypertrophic cardiomyopathy, and how effectively their heart is functioning. In each case, our model performed better than all other tested baselines.”

Researchers pretrained HeartBEiT on 8.5 million ECGs from 2.1 million patients collected over four decades from four hospitals within the Mount Sinai Health System. Then they tested its performance against standard CNN architectures in the three cardiac diagnostic areas. The study found that HeartBEiT had significantly higher performance at lower sample sizes, along with better “explainability.” Elaborates senior author Girish Nadkarni, MD, MPH, Irene and Dr. Arthur M. Fishberg Professor of Medicine at Icahn Mount Sinai, Director of The Charles Bronfman Institute of Personalized Medicine, and System Chief, Division of Data-Driven and Digital Medicine, Department of Medicine: “Neural networks are considered black boxes, but our model was much more specific in highlighting the region of the ECG responsible for a diagnosis, such as a heart attack, which helps clinicians to better understand the underlying pathology. By comparison, the CNN explanations were vague even when they correctly identified a diagnosis.”

Indeed, through its sophisticated new modeling architecture, the Mount Sinai team has greatly enhanced the manner and opportunities by which physicians can interact with the ECG. “We want to be clear that artificial intelligence is by no means replacing diagnosis by professionals from ECGs,” explained Dr. Nadkarni, “but rather augmenting the ability of that medium in an exciting and compelling new way to detect heart problems and monitor the heart’s health.”

The paper is titled “A foundational vision transformer improves diagnostic performance for electrocardiograms.”

This study was funded by the National Heart, Lung, and Blood Institute of the NIH, grant number R01HL155915, and by the National Center for Advancing Translational Sciences of the NIH, grant number UL1TR004419.

To view the full list of authors and competing interests, see DOI: 10.1038/s41746-023-00840-9.

-####-

About the Icahn School of Medicine at Mount Sinai

The Icahn School of Medicine at Mount Sinai is internationally renowned for its outstanding research, educational, and clinical care programs. It is the sole academic partner for the eight- member hospitals* of the Mount Sinai Health System, one of the largest academic health systems in the United States, providing care to a large and diverse patient population.   

Ranked 14th nationwide in National Institutes of Health (NIH) funding and among the 99th percentile in research dollars per investigator according to the Association of American Medical Colleges, Icahn Mount Sinai has a talented, productive, and successful faculty. More than 3,000 full-time scientists, educators, and clinicians work within and across 44 academic departments and 36 multidisciplinary institutes, a structure that facilitates tremendous collaboration and synergy. Our emphasis on translational research and therapeutics is evident in such diverse areas as genomics/big data, virology, neuroscience, cardiology, geriatrics, as well as gastrointestinal and liver diseases. 

Icahn Mount Sinai offers highly competitive MD, PhD, and Master’s degree programs, with current enrollment of approximately 1,300 students. It has the largest graduate medical education program in the country, with more than 2,000 clinical residents and fellows training throughout the Health System. In addition, more than 550 postdoctoral research fellows are in training within the Health System. 

A culture of innovation and discovery permeates every Icahn Mount Sinai program. Mount Sinai’s technology transfer office, one of the largest in the country, partners with faculty and trainees to pursue optimal commercialization of intellectual property to ensure that Mount Sinai discoveries and innovations translate into healthcare products and services that benefit the public.  

Icahn Mount Sinai’s commitment to breakthrough science and clinical care is enhanced by academic affiliations that supplement and complement the School’s programs.  

Through the Mount Sinai Innovation Partners (MSIP), the Health System facilitates the real-world application and commercialization of medical breakthroughs made at Mount Sinai. Additionally, MSIP develops research partnerships with industry leaders such as Merck & Co., AstraZeneca, Novo Nordisk, and others.  

The Icahn School of Medicine at Mount Sinai is located in New York City on the border between the Upper East Side and East Harlem, and classroom teaching takes place on a campus facing Central Park. Icahn Mount Sinai’s location offers many opportunities to interact with and care for diverse communities. Learning extends well beyond the borders of our physical campus, to the eight hospitals of the Mount Sinai Health System, our academic affiliates, and globally.  

------------------------------------------------------- 

* Mount Sinai Health System member hospitals: The Mount Sinai Hospital; Mount Sinai Beth Israel; Mount Sinai Brooklyn; Mount Sinai Morningside; Mount Sinai Queens; Mount Sinai South Nassau; Mount Sinai West; and New York Eye and Ear Infirmary of Mount Sinai.  

 

 

 

END


[Attachments] See images for this press release:
Mount Sinai researchers use new deep learning approach to enable analysis of electrocardiograms as language Mount Sinai researchers use new deep learning approach to enable analysis of electrocardiograms as language 2 Mount Sinai researchers use new deep learning approach to enable analysis of electrocardiograms as language 3

ELSE PRESS RELEASES FROM THIS DATE:

Ba2LuAlO5: A new proton conductor for next-generation fuel cells

Ba2LuAlO5: A new proton conductor for next-generation fuel cells
2023-06-06
The discovery of Ba2LuAlO5 as a promising proton conductor paints a bright future for protonic ceramic fuel cells, report scientists from Tokyo Tech. Experiments show that this novel material has a remarkably high proton conductivity even without any additional chemical modifications, and molecular dynamics simulations reveal the underlying reasons. These new insights may pave the way to safer and more efficient energy technologies.   When talking about sustainability, the ways in which a society ...

Fine-tuning 3D lab-grown mini tumors to help predict how patients respond to cancer therapies

2023-06-06
Scientists from the UCLA Jonsson Comprehensive Cancer Center have developed a new method to bioprint miniature tumor organoids that are designed to mimic the function and architecture of real tumors. The improved process allows researchers to use an advanced imaging method to study and analyze individual organoids in great detail, which can help researchers identify personalized treatments for people with rare or hard-to-treat cancers. The method is described in the journal Nature Communications. “Tumor organoids have become fundamental tools to ...

Social media ‘trust’/’distrust’ buttons could reduce spread of misinformation

2023-06-06
The addition of ‘trust’ and ‘distrust’ buttons on social media, alongside standard ‘like’ buttons, could help to reduce the spread of misinformation, finds a new experimental study led by UCL researchers. Incentivising accuracy cut in half the reach of false posts, according to the findings published in eLife. Co-lead author, Professor Tali Sharot (UCL Psychology & Language Sciences, Max Planck UCL Centre for Computational Psychiatry and Ageing Research, and Massachusetts Institute of Technology) said: “Over the past few years, the spread of misinformation, or ‘fake news’, has skyrocketed, ...

Programmable 3D printed wound dressing could improve treatment for burn, cancer patients

Programmable 3D printed wound dressing could improve treatment for burn, cancer patients
2023-06-06
One of the challenges in treating burn victims is the frequency of dressing changes, which can be extremely painful.  To bring relief to this and other problems, University of Waterloo researchers have created a new type of wound dressing material using advanced polymers. This new dressing could enhance the healing process for burn patients and have potential applications for drug delivery in cancer treatment as well as in the cosmetic industry. "To treat burn victims, we can customize the shape using a 3D printer, secondly, the material has fine-tuned surface adhesion, which is a key feature", said Dr. Boxin Zhao, a professor in Waterloo's Department of ...

Do chatbot avatars prompt bias in health care?

2023-06-06
Chatbots are increasingly becoming a part of health care around the world, but do they encourage bias? That’s what University of Colorado School of Medicine researchers are asking as they dig into patients’ experiences with the artificial intelligence (AI) programs that simulate conversation. “Sometimes overlooked is what a chatbot looks like – its avatar,” the researchers write in a new paper published in Annals of Internal Medicine. “Current chatbot ...

Team develops smartphone app to enhance midwifery care in Tanzania

Team develops smartphone app to enhance midwifery care in Tanzania
2023-06-06
An international research team from Tanzania and Japan created a smartphone app and conducted a pilot study of how the app might be used to improve midwives’ knowledge and skills in Tanzania. Their study focused on the app’s potential effects on the learning outcomes of midwives and birth preparedness of pregnant women in Tanzania. The team’s work is published in the journal PLOS ONE on March 31, 2023. “The smartphone app for midwives showed significant improvements in their learning outcomes, leading to better birth preparations for pregnant women in Tanzania. This study highlights the potential of leveraging technology ...

Webb telescope detects universe’s most distant organic molecules

Webb telescope detects universe’s most distant organic molecules
2023-06-06
An international team of astronomers has detected complex organic molecules in the most distant galaxy to date using NASA’s James Webb Space Telescope. The discovery of the molecules, which are familiar on Earth in smoke, soot and smog, demonstrates the power of Webb to help understand the complex chemistry that goes hand-in-hand with the birth of new stars even in the earliest periods of the universe’s history. At least for galaxies, the new findings cast doubt on the old adage that where there’s smoke, there’s ...

Breastfeeding for longer may be linked to better exam results in later life

2023-06-06
Children who are breastfed for longer appear to be more likely to gain slightly better results in their school GSCEs at age 16 compared with non-breastfed children, suggests a study published online in the journal Archives of Disease in Childhood. The evidence of improved educational outcomes is still apparent even when various factors are taken into account such as people’s socio-economic status and their parents’ intelligence. Previous studies have suggested that children breastfed for longer have improved educational outcomes later in life. However these are relatively scarce, and ...

Close contact intervention between a mother and her premature baby may reduce risk of mortality by almost a third

2023-06-06
A method of care involving skin-to-skin contact between a mother and her prematurely born or low birth weight baby appears to impact the child’s chances of survival significantly, suggests a study published online in the journal BMJ Global Health. Starting the intervention within 24 hours of birth and carrying it out for at least eight hours a day both appear to make the approach even more effective in reducing mortality and infection, researchers found. The method of care known as ‘Kangaroo mother care’ (KMC) involves an infant being carried, usually by the mother, in a sling with skin-to-skin contact ...

Defibrillators used in just 10 per cent of out of hospital cardiac arrests - study shows

2023-06-06
Defibrillators are being used in just one in ten cardiac arrests where the lifesaving devices are available, according to new research presented at the British Cardiovascular Society Conference in Manchester.   The research drew upon data from the East of England Ambulance Service and The Circuit, the national defibrillator network developed by the British Heart Foundation (BHF). The Circuit maps the location of defibrillators across the whole of the UK, so that emergency services can direct bystanders to the nearest defibrillator in the event of ...

LAST 30 PRESS RELEASES:

Study finds senescent immune cells promote lung tumor growth

Study examines benefits and obstacles of library data storytelling

Cost of living crisis set to cut UK lives short and significantly widen wealth-health gap

Flawed body of research indicates true ‘long COVID’ risk likely exaggerated

Wealthier kids in UK may have experienced steepest fall in mental health during pandemic

Stem cell therapy can safely slow progression of relapsing-remitting MS

NASA’s Interstellar Mapping and Acceleration Probe passes system integration review

National Science Foundation taps Worcester Polytechnic Institute fire protection expertise and resources for the Wildfire Interdisciplinary Research Center

Doctor and pharmacist revamp standard processes for ordering and documenting mifepristone use

Screening for adverse childhood experience can improve trauma-informed care, though time constraints and limited referral resources present challenges

Understanding parents’ care expectations for a child with gastroenteritis could prevent after-hours care requests

Learning collaborative promotes mifepristone education and utilization training in federally qualified health centers

Men who trust their doctors, receive adequate time and general information about prostate cancer screening are more likely to have productive discussions

Study identifies patient and clinician-level characteristics associated with sexual history screening administration

Researchers identify important strategies for diabetes care and quality improvements in the primary care setting

Attentiveness to resting leg cramps may afford greater insight into advancing age and declining health

Staffing challenges and general time constraints may harm primary care teams’ ability to implement quality improvement efforts

Primary care investigators, clinicians, patients and community members reflect on NAPCRG’s 50 years of leadership and service

September/October Annals of Family Medicine 2023 tip sheet

Combination radiation with immunotherapy shows promise against “cold” breast cancer tumors

A new AI model has been developed to improve accuracy of breast cancer tumor removal

Finding the balance: Opioids and pain control after surgery

UC Irvine scientists reveal what fuels wildfires in Sierra Nevada Mountains

US Department of Energy Office of Science awards $115M for High Rigidity Spectrometer project at FRIB

Algorithm would predict disease relapses

Exercise-mimicking drug sheds weight, boosts muscle activity in mice

Did life exist on Mars? Other planets? With AI's help, we may know soon

Wind energy projects in North America are more likely to be opposed by white, wealthy communities

Naming and shaming can be effective to get countries to act on climate

Scientists develop method of identifying life on other worlds

[Press-News.org] Mount Sinai researchers use new deep learning approach to enable analysis of electrocardiograms as language