(Video animation shows blood stem cells dividing and multiplying. Getty Images).

Deep inside the body, a slow-growing cluster of mutated blood cells can form. This cluster, found in 1 in 5 older adults, can raise the risk of leukemia and heart disease, often without warning. 

To better understand this hidden risk, Mayo Clinic researchers have developed an artificial intelligence (AI) tool to help investigators uncover how it contributes to disease risk and progression.

In a study published in Genomics, Proteomics & Bioinformatics, the tool showed promising results in identifying early signs of this condition, known as clonal hematopoiesis of indeterminate potential, or CHIP.

When blood cells mutate

CHIP starts in the bone marrow, where blood stem cells make the cells that keep organs working, oxygen flowing and the immune system strong. But if one of those cells acquires a mutation in a gene linked to blood cancer, it can multiply abnormally, forming a cluster of mutated cells that gradually expands. 

This can cause CHIP, a condition with no symptoms that researchers link to higher rates of death, especially from heart disease. Because its effects vary, CHIP is hard to track and often goes undetected for years. 

CHIP makes leukemia more than 10 times more likely and raises the risk of heart disease up to four times, even in healthy adults. Finding it earlier could help guide proactive monitoring or preventive care.

A new tool for early detection 

The new tool, called UNISOM — short for UNIfied SOmatic calling and Machine learning — was developed by Shulan Tian, Ph.D., under the leadership of Eric Klee, Ph.D., co-senior author of the study and the Everett J. and Jane M. Hauck Midwest Associate Director of Research and Innovation.  

UNISOM helps clinicians identify CHIP-related mutations in standard genetic datasets, opening new avenues for research and discovery. In the past, that level of detection required more complex and advanced sequencing methods. 

"Detecting disease at its earliest molecular roots is one of the most meaningful advances we can make in medicine," says Dr. Klee. "UNISOM is just one of many examples of how we're translating genomic science into innovative tools that support timely and informed care." 

UNISOM helped researchers detect nearly 80% of CHIP mutations using whole-exome sequencing, which analyzes the protein-coding regions of DNA.  

The team also tested UNISOM on whole-genome sequencing data from the Mayo Clinic Biobank, which captures nearly all of a person's genetic code. In that data, it detected early signs of CHIP, including mutations present in fewer than 5% of blood cells. Standard techniques often miss these small but important changes.

"We're engineering a path from genomic discovery to clinical decision-making," says Dr. Tian, the co-senior author and a bioinformatician at Mayo Clinic. "It's rewarding to help bring these discoveries closer to clinical care, where they can inform decisions and support more precise treatment." 

Next, the team plans to apply UNISOM to larger and more diverse datasets to support research and expand its use in clinical practice. 

Review the study for a complete list of authors, disclosures and funding.   

The post Mayo Clinic AI tool finds early signs of blood mutations linked to cancer and heart disease appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Mayo Clinic took a pivotal step toward integrating AI solutions in the clinical setting with the deployment of NVIDIA DGX SuperPOD with NVIDIA DGX B200 systems, an advanced infrastructure that provides state-of-the-art AI compute capabilities.

Mayo Clinic and NVIDIA collaborated to enable the rapid innovation and development of foundation models in support of Mayo’s platform approach to healthcare, contributing to Mayo Clinic’s Bold. Forward. strategy and new innovations for generative AI solutions and digital pathology. These innovations are delivering new insights as Mayo is driving to improve patient outcomes and transform healthcare.

"Our aspiration for AI is to meaningfully improve patient outcomes by detecting disease early enough to intervene. What was once a hypothetical — 'If only we had the right data' — is now becoming reality thanks to AI and advanced computing," says Matthew Callstrom, M.D., Ph.D., medical director of the Department of Strategy and leader of Mayo Clinic’s Generative Artificial Intelligence Program.

The advanced computing infrastructure will initially support foundation model development for pathomics, drug discovery and precision medicine.

The NVIDIA Blackwell-powered DGX SuperPOD is built to efficiently process large, high-resolution imaging essential for AI foundation model training. Designed for speed and scalability, the Blackwell infrastructure enables Mayo Clinic to accelerate pathology slide analysis and foundation model development — reducing four weeks of work to just one, ultimately improving patient outcomes. This advanced computing infrastructure will also advance Mayo Clinic’s generative AI and multimodal digital pathology foundation model development.

Mayo Clinic, in partnership with Aignostics, developed a leading pathology foundation model called Atlas, trained on more than 1.2 million histopathology whole-slide images. With Atlas, Mayo Clinic clinicians and researchers can improve accuracy and reduce administrative tasks. The new computing capabilities will accelerate and improve clinical model development.

"This compute power, coupled with Mayo’s unparalleled clinical expertise and platform data of over 20 million digitized pathology slides, will allow Mayo to build on its existing foundation models. We’re transforming healthcare by quickly and safely developing innovative AI solutions that can improve patient outcomes and enable clinicians to dedicate more time to patient care while also accelerating commercial affiliations with other industry leaders," says Jim Rogers, CEO of Mayo Clinic Digital Pathology.

Journalists: Media kit with images for download available here.

###

About Mayo Clinic Digital Pathology
Mayo Clinic Digital Pathology facilitates the global scaling of digital pathology solutions to benefit clinicians and patients, advancing key areas such as scanning, storage, foundation model development and the creation and deployment of cutting-edge algorithms. Working with Mayo Clinic innovators and external collaborators, Mayo Clinic Digital Pathology is wholly owned by Mayo Clinic and seeks to incubate and start impactful companies while investing in and acquiring existing companies, spurring innovation across pathology.

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.

Media contact:

• Terri Malloy, Mayo Clinic Communications, newsbureau@mayo.edu

The post Mayo Clinic deploys NVIDIA Blackwell infrastructure to drive generative AI solutions in medicine appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — A team of Mayo Clinic researchers has developed an artificial intelligence (AI) system that can detect surgical site infections (SSIs) with high accuracy from patient-submitted postoperative wound photos, potentially transforming how postoperative care is delivered.

Published in the Annals of Surgery, the study introduces an AI-based pipeline the researchers created that can automatically identify surgical incisions, assess image quality and flag signs of infection in photos submitted by patients through online portals. The system was trained on over 20,000 images from more than 6,000 patients across nine Mayo Clinic hospitals.

"We were motivated by the increasing need for outpatient monitoring of surgical incisions in a timely manner," says Cornelius Thiels, D.O., a hepatobiliary and pancreatic surgical oncologist at Mayo Clinic and co-senior author of the study. "This process, currently done by clinicians, is time-consuming and can delay care. Our AI model can help triage these images automatically, improving early detection and streamlining communication between patients and their care teams."

The AI system uses a two-stage model. First, it detects whether an image contains a surgical incision and then evaluates whether that incision shows signs of infection. The model, Vision Transformer, achieved a 94% accuracy in detecting incisions and an 81% area under the curve (AUC) in identifying infections.

"This work lays the foundation for AI-assisted postoperative wound care, which can transform how postoperative patients are monitored," says Hala Muaddi, M.D., Ph.D., a hepatopancreatobiliary fellow at Mayo Clinic and first author. "It’s especially relevant as outpatient operations and virtual follow-ups become more common."

The researchers are hopeful that this technology could help patients receive faster responses, reduce delays in diagnosing infections and support better care for those recovering from surgery at home. With further validation, it could function as a frontline screening tool that alerts clinicians to concerning incisions. This AI tool also paves the way for developing algorithms capable of detecting subtle signs of infection, potentially before they become visually apparent to the care team. This would allow for earlier treatment, decreased morbidity and reduced costs.

"For patients, this could mean faster reassurance or earlier identification of a problem," says Dr. Muaddi. "For clinicians, it offers a way to prioritize attention to cases that need it most, especially in rural or resource-limited settings."

Importantly, the model demonstrated consistent performance across diverse groups, addressing concerns about algorithmic bias. 

While the results are promising, the team says that further validation is needed. 

"Our hope is that the AI models we developed — and the large dataset they were trained on — have the potential to fundamentally reshape how surgical follow-up is delivered," says Hojjat Salehinejad, Ph.D., a senior associate consultant of health care delivery research within the Kern Center for the Science of Health Care Delivery and co-senior author. "Prospective studies are underway to evaluate how well this tool integrates into day-to-day surgical care."

This research was supported by the Dalio Philanthropies Artificial Intelligence/Machine Learning Enablement Award and the Simons Family Career Development Award in Surgical Innovation.

###

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.

Media contact:

• Chloe Corey, Mayo Clinic Communications, newsbureau@mayo.edu

The post Mayo Clinic researchers develop AI tool to detect surgical site infections from patient-submitted photos appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Every year, some mothers die after giving birth due to heart problems, and many of these deaths could be prevented. The ability to screen for heart weakness before pregnancy could play a crucial role in identifying women who may need additional care to improve pregnancy outcomes. Mayo Clinic researchers, led by Anja Kinaszczuk, D.O., and Demilade Adedinsewo, M.D., tested artificial intelligence (AI) tools, using recordings from an electrocardiogram (ECG) and a digital stethoscope, to find unknown heart problems in women of childbearing age seen in primary care.   

Study findings published in the Annals of Family Medicine show high diagnostic performance of these technologies to detect left ventricular ejection fraction below 50%, indicating heart muscle weakness. These tools were tested on two groups of women aged 18 to 49.  

• Group 1: 100 women already scheduled for an echocardiogram (the best test to evaluate heart muscle function). They also had a standard clinical ECG and digital stethoscope recording of the heart’s electrical activity and heart sounds.  

• Group 2: 100 women seen for routine primary care visits to see how often the AI tools would find heart problems.   

The AI-ECG demonstrated an area under the curve (AUC) of .94 while the AI digital stethoscope, Eko DUO, achieved an even higher AUC of 0.98, indicating strong diagnostic accuracy. In the second cohort, the prevalence of positive AI screening results was 1% for the AI-ECG and 3.2% for the AI-stethoscope. 

"Statistically, nearly half of pregnancies in this country are unplanned, and approximately 1% to 2% of women may have heart problems they don't know about. Our research findings suggest that these AI tools could be used to screen women before pregnancy, allowing for improved pregnancy planning and risk stratification, early treatment, and better health outcomes which addresses a critical gap in current maternal care," says Dr. Adedinsewo, a cardiologist and senior author of the study.  

This research builds upon earlier published studies, including a pilot prospective study evaluating AI digital tools to detect pregnancy-related cardiomyopathy among obstetric patients in the U.S. and a pragmatic randomized clinical trial of women in Nigeria who were pregnant or had recently given birth. Collectively, this research highlights the potential of AI to modernize cardiovascular screening, enabling earlier identification and management of heart muscle weakness in women of reproductive age. Further research is underway to explore the potential of using these technologies to screen for heart weakness in broader populations.  

Mayo Clinic has licensed the underlying technology to EKO Health for its digital stethoscope with embedded ECG electrodes and to Anumana for the 12-lead ECG. Mayo Clinic and some study authors have a financial interest in this technology. Mayo Clinic will use any revenue it receives to support its not-for-profit mission in patient care, education and research. 

### 

About Mayo Clinic 
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.  

Media contact: 

• Terri Malloy, Mayo Clinic Communications, newsbureau@mayo.edu 

The post AI-ECG tools can help clinicians identify heart issues early in women planning to have children  appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Heart surgery is a serious and invasive medical procedure, and that can be intimidating for a patient. A new study published in Mayo Clinic Proceedings suggests that virtual reality (VR) can be an effective tool to reduce preoperative anxiety in older patients undergoing their first open-heart surgery. While much of the research to date using VR involved younger patient populations, these research findings suggest that immersive VR was effective and well tolerated in older patients. These reductions in anxiety are particularly significant given the known link between preoperative anxiety and negative postoperative outcomes, including increased pain, reduced activity and higher medication use. 

"This research represents a step forward in improving the patient experience and potentially using this approach to optimize postoperative recovery," says Jordan Miller, Ph.D., a cardiovascular disease researcher at Mayo Clinic and senior author of the study.  

Joseph Dearani, M.D., and John Stulak, M.D., both cardiac surgeons at Mayo Clinic involved with the study, emphasize the importance of emotional state before and after cardiac surgery. "We currently offer music and massage therapy after cardiac surgery because we know what a negative impact high anxiety has on recovery from surgery. Our team is now exploring broader implementation of VR — which can be used at any time and place, inside or outside the hospital — throughout the surgical episode to further evaluate its impact on clinical outcomes." 

Unlike traditional anti-anxiety medications, which can have drawbacks such as increased difficulty placing the tube that helps a patient breathe during surgery and a longer time to remove the tube after surgery, VR offers a nonpharmacological alternative. The study also highlights the potential of VR as a flexible tool, with the tablet-based option providing a viable alternative for patients susceptible to VR-induced motion sickness. 

The research included 100 participants who were scheduled for open-heart surgery. Each patient wore a monitor to record vital signs and completed a standardized, clinically validated anxiety test before and after the VR intervention on the day of surgery. The test asked them to rate their current state with 20 questions related to feelings ranging from calm to upset. Participants rated each feeling on a scale of 1 to 4, with 1 being "not at all" and 4 being "very much." 

Half of the participants were assigned to a VR tablet and the other half to immersive VR goggles while they waited in the holding area prior to surgery. The VR provided a 10-minute nature experience with guided breathing as they viewed trees and a waterfront that changed through four seasons. The tablet played a video of the content seen by patients in VR, while people who used the immersive VR headset were able to look all around and identify environmental features, which helped them advance through the scene. Both interventions reduced the pulse rate of participants, but they did not affect respiration rate or oxygen levels. 

Overall anxiety scores decreased an average of 2 points with the tablet treatment and 2.9 points with the VR goggles. Additionally, the researchers note that the scores improved considerably in up to seven of the anxiety-focused questions with the tablet and VR goggles. Several of those responses specifically represent a more positive outlook change from their previously negative feelings — a finding that has the researchers feeling optimistic about the abilities of VR to make surgery less stressful for patients.  

### 

About Mayo Clinic 
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.  

Media contact: 

• Terri Malloy, Mayo Clinic Communications, newsbureau@mayo.edu 

The post Mayo Clinic researchers and surgeons test virtual reality to calm presurgery jitters   appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Mayo Clinic today unveiled separate groundbreaking collaborations with Microsoft Research and with Cerebras Systems in the field of generative artificial intelligence (AI), designed to personalize patient care, significantly accelerate diagnostic time and improve accuracy.

Announced during the 43^rd Annual J.P. Morgan Healthcare Conference, the projects focus on developing and testing foundation models customized for various applications, leveraging the power of multimodal radiology images and data (including CT scans and MRIs) with Microsoft Research and genomic sequencing data with Cerebras. The innovations have the potential to transform how clinicians approach diagnosis and treatment, ultimately leading to better patient outcomes. 

Foundation AI models are large, pre-trained models capable of adapting to and carrying out many tasks with minimal extra training. They learn from massive datasets, acquiring general knowledge that can be used across diverse applications. This adaptability makes them efficient and versatile building blocks for numerous AI systems.

Mayo Clinic and Microsoft Research advance AI for chest X-rays

Mayo Clinic and Microsoft Research are collaboratively developing foundation models that integrate text and images. For this use case, Mayo and Microsoft Research are working together to explore the use of generative AI in radiology using Microsoft Research’s AI technology and Mayo Clinic’s X-ray data.

"Multimodal foundation models hold immense promise in tackling significant roadblocks across the radiology ecosystem. The innovations we’re creating with Microsoft Research will help unlock valuable insights for the future of medical imaging to improve how radiologists work and how patients are cared for," says Matthew Callstrom, M.D. Ph.D., chair of Mayo Clinic Radiology in the Midwest and medical director for Generative AI and Strategy. "Focusing on chest X-ray reports, Mayo's clinical teams and Microsoft researchers will collaborate to advance the state-of-the-art in multimodal AI radiology, helping bring innovation to real-world application faster and at scale, which is key to making exemplary healthcare more accessible." 

Empowering clinicians with instant access to the information they need is at the heart of this research project. Mayo Clinic aims to develop a model that can automatically generate reports, evaluate tube and line placement in chest X-rays, and detect changes from prior images. This proof-of-concept model seeks to improve clinician workflow and patient care by providing a more efficient and comprehensive analysis of radiographic images.

"This collaboration is a crucial step towards our mutual goal of developing generative AI that improves patient outcomes and the clinician experience," says Jonathan Carlson, Ph.D., managing director, Health Futures at Microsoft Research. "The fusion of Microsoft's recognized research innovations in biomedical AI and Mayo Clinic's radiology excellence will empower clinicians with the tools they need to deliver more precise and accessible care and furthers Microsoft’s commitment to bringing the power of emerging AI to clinical researchers worldwide."

Mayo Clinic and Cerebras create a world-leading genomic foundation model

Mayo Clinic and Cerebras have created a genomic foundation model that combines publicly available human reference genome data that represents an ideal version of the human genome, with Mayo's comprehensive patient exome data and the power of its Mayo Clinic Platform. Exome data focuses on the protein-coding region of the genome where several disease-causing mutations take place. Cerebras's high-powered computing and generative AI capabilities make it possible to train and develop the model at scale, positioning it to be further refined for more specific uses.

"The genomic foundation model represents a significant advancement in personalized medicine," says Dr. Callstrom. "Its ability to analyze genomic data and compare them in almost real-time with patients with similar traits allows for more precise prediction of disease and treatment response, leading to faster diagnoses and the selection of targeted therapies for patients."

For example, rheumatoid arthritis (RA) is a debilitating autoimmune disease, and the standard treatment approach often requires trials of different therapies to achieve disease remission. It can take several months to know if a therapy is working. A new genomic model developed by Mayo Clinic and Cerebras offers a potential solution to shorten the time to identify effective treatment and avoid long-term morbidity associated with the untreated disease. Early findings demonstrate high performance against benchmarks and show early promise in identifying patient response to therapy. As more patient data is added, the model's predictive power is expected to increase, leading to faster, more effective personalized treatment for RA patients.   

"Mayo’s genomic foundation model sets a new bar for genomic models, excelling not only in standard tasks like predicting functional and regulatory properties of DNA but also enabling discoveries of complex correlations between genetic variants and medical conditions," says Natalia Vassilieva, Field CTO at Cerebras Systems. "Unlike current approaches focused on single-variant associations, this model enables the discovery of connections where collections of variants contribute to a particular condition."

###

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.

Media contact:

• Terri Malloy, Mayo Clinic Communications, newsbureau@mayo.edu

The post Mayo Clinic accelerates personalized medicine through foundation models with Microsoft Research and Cerebras Systems appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Against the backdrop of the 43^rd Annual J.P. Morgan Healthcare Conference, Mayo Clinic announced the formation of Mayo Clinic Digital Pathology, designed on a platform architecture to boldly unlock the power of its extensive archive of digital slides to revolutionize pathology and accelerate medical breakthroughs.

Mayo Clinic's expertise, de-identified clinical data, and its Platform architecture, combined with technical expertise and resources of NVIDIA, a world leader in accelerated computing, is powering the ability to accelerate this transformation. In addition, to improve performance and scalability of generative AI in pathology, Mayo Clinic is collaborating with Aignostics, an industry leader in building artificial intelligence (AI) models for digital solutions in precision medicine in a way that mirrors its established approach to patient care. This collaborative, multidisciplinary effort leverages both medical and technological strengths, and the early achievements are promising.

"Mayo Clinic is reimagining what is possible in disease detection and prediction, both within its own system and globally. We are doing this by using large, diverse datasets to build powerful artificial intelligence models in pathology. This will make diagnoses faster, more accurate, and more efficient, improving treatment approaches and speeding new cures to patients," says Jim Rogers, CEO, Mayo Clinic Digital Pathology.

"AI-driven insights can accelerate diagnostics, enhance precision medicine and revolutionize patient care," said Kimberly Powell, VP of Healthcare and Life Sciences, NVIDIA. "By digitizing and harnessing the power of vast datasets through its Digital Pathology platform, powered by NVIDIA's accelerated computing, Mayo Clinic is helping pave the way for a future with faster medical breakthroughs, better treatments and improved outcomes for patients across the globe."

"Merging Mayo Clinic's data and expertise with our advanced machine learning capabilities will produce breakthrough foundation models and AI products that advance the field of precision medicine and meaningfully improve patient care," says Viktor Matyas, CEO of Aignostics.

The vast majority of pathology practices remain tethered to analog processes, hindering access to critical diagnostic data that could be used to expand diagnostics and treatments and speed the development of new therapies to benefit patients. To address this challenge, Mayo Clinic has moved quickly, investing in digitizing its pathology practice and by scanning its extensive archive of pathology slides, as well as prospectively scanning pathology slides from current patients. To date, Mayo Clinic Digital Pathology has leveraged 20 million digital slide images linked to 10 million patient records that incorporate treatments, medications, imaging, clinical notes, genomic data and more.

In less than two months, Mayo Clinic and Aignostics developed a leading foundation model built on 1.2 million deidentified slides from Mayo Clinic and Charité – Universitätsmedizin Berlin, findings of which were published in a paper on Jan. 9. Current efforts include developing and deploying new solutions enabled by this model. Future plans are focused on building new models, including one being trained on 5 million slides.   

The NVIDIA collaboration will create a first-in-class infrastructure for building and deploying foundation models to accelerate generative AI advances in pathology and beyond. With NVIDIA's healthcare-specific full stack computing architecture for artificial intelligence, NVIDIA Clara, Mayo Clinic is building models that will open new frontiers in medicine and lay the foundation for more personalized patient experiences.      

The development of Mayo Clinic Digital Pathology has been a planned process over many years. The pathology platform takes advantage of the portfolios of Mayo Clinic Platform, a global network that drives digital innovation around diagnosis, treatment and operational improvements worldwide, and Mayo Clinic Laboratories, which provides advanced testing and pathology services for healthcare organizations worldwide. Continuing its efforts to transform healthcare, Mayo Clinic is working with investors and data providers to continue building a pathology platform that spurs innovation and transforms the medical practice for the benefit of healthcare systems and patients worldwide.

"These new capabilities using digital pathology data will unlock this critically important clinical information for building AI solutions for advanced diagnosis and care of patients and that will improve the lives of patients globally," says Matthew Callstrom, M.D. Ph.D., chair of Mayo Clinic Radiology in the Midwest and medical director for Generative AI and Strategy.

###

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.

Media contact:

• Terri Malloy, Mayo Clinic Communications, newsbureau@mayo.edu

The post Mayo Clinic launches Mayo Clinic Digital Pathology to modernize pathology, speed medical breakthroughs appeared first on Mayo Clinic News Network.

In a new study, Mayo Clinic researchers and collaborators have described — for the first time — the prevalence of autoimmune diseases in the U.S. Their research, published in the Journal of Clinical Investigation, reports that about 15 million people are estimated to have one or more of 105 autoimmune diseases. The study also found that autoimmune diseases occur most often in women and identified the top autoimmune diseases by prevalence, sex and age.

"Knowing the number of patients with an autoimmune disease in the U.S. is critical to assess whether these diseases are increasing or decreasing over time and with treatment," says the study's corresponding author, DeLisa Fairweather, Ph.D., vice-chair of translational research for the Department of Cardiovascular Medicine at Mayo Clinic in Florida. "Knowing this number is also critical for funding agencies to raise money and awareness for research into autoimmune diseases as a group and for individual autoimmune diseases like rheumatoid arthritis or multiple sclerosis. Knowing which diseases occur more often in males or females and at what age is critical in understanding the pathogenesis of disease and how they impact the healthcare system."  Dr. Fairweather also leads the Translational Cardiovascular Disease Research Laboratory.

To conduct the study, Dr. Fairweather and co-senior author Aaron Abend from the Autoimmune Registry used electronic health record data from over 10 million patients from six large medical systems in California, Florida, Massachusetts, Iowa, Wisconsin and Missouri who had been diagnosed with at least one of 105 autoimmune diseases considered in the study. They then extended the data to an estimated U.S. population of 333.3 million. The researchers developed a program algorithm to compute the first nationwide prevalence estimate of autoimmune diseases as a category. Dr. Fairweather says previous U.S. estimates were based on meta-analyses and extrapolations for individual autoimmune diseases, which can make estimations of prevalence inaccurate. She says many challenges have existed to obtain accurate prevalence data, including the lack of international consensus on a definition of autoimmune disease.

The findings indicated that about 15 million people, or 4.6% of the U. S. population, were diagnosed with at least one autoimmune disease between January 2011 and January 2022, and that 34% of those individuals were diagnosed with more than one autoimmune disease.

The study also found:

• Females (63% of those with autoimmune disease) were almost twice as likely as males (37%) to be diagnosed with an autoimmune disease.
• 65% of patients had one autoimmune disease.
• 24% of patients had two autoimmune diseases.
• 8% of patients had three autoimmune diseases.
• 2% of patients had four or more autoimmune diseases.

The top five diseases based on prevalence were rheumatoid arthritis, psoriasis, type I diabetes, Graves' disease and autoimmune thyroiditis.

"What dramatically stands out with this assessment is that the most prevalent autoimmune diseases occur in women and autoimmune diseases that occur more often in men occur rarely," says Dr. Fairweather. "This raises important questions that need to be answered with more research. For example, could this be the result of diagnosis bias, or is this a fundamental biological sex difference?"

Dr. Fairweather served on a National Academy of Sciences, Engineering and Medicine (NASEM) committee on autoimmune diseases and testified before Congress in May 2022 to give recommendations for advancing research in autoimmune diseases. This led to the establishment of a new National Institutes of Health (NIH) Office of Autoimmune Disease Research within the Office of Research on Women's Health. In December 2023, the NIH sought input from members of the scientific community, federal partners, academic institutions, the private sector, health professionals, professional societies, advocacy groups, patient communities and other interested people for the development of an NIH-wide strategic plan to advance autoimmune disease research.

Dr. Fairweather says her team has provided the program algorithm freely to the research community, allowing anyone to leverage this research tool to replicate the study using almost any healthcare database. In addition, researchers can use the tool over time to track shifts in the prevalence of autoimmune diseases, offering valuable insights for future research.

This research was partially funded by a National Institutes of Health grant under award R01 HL164520. For a complete list of authors, disclosures and funding, see the paper.

The post New study calculates autoimmune disease prevalence in U.S. appeared first on Mayo Clinic News Network.

In this Mayo Clinic Minute, Dr. Hugo Botha, a Mayo Clinic behavioral neurologist, explains how voice samples collected for research can help diagnose neurodegenerative diseases early.

Watch: The Mayo Clinic Minute

Journalists: Broadcast-quality video (1:10) is in the downloads at the end of this post. Please courtesy: "Mayo Clinic News Network." Read the script.

"There are some diseases where the very first manifestation is in someone's voice or their speech," says Dr. Botha. Those include Parkinson’s disease; atypical parkinsonism such as multiple system atrophy, progressive supranuclear palsy and corticobasal syndrome; amyotrophic lateral sclerosis (ALS); myasthenia gravis; and some types of frontotemporal dementia that can result in aphasia.

As part of clinical practice, Mayo Clinic's neurology patients often are recorded when they have their voice or speech examined, which gives clinicians the opportunity to track the disease over time.

"But separate from the clinical practice, we have a large research program at Mayo, where we are collecting voice and speech samples using an application that runs on the person's phone or the laptop computer," Dr. Botha explains.

To collect the voice samples, patients are tasked with running through a series of exams remotely.

"They could do it — say every couple of weeks, every couple of months — so we can really get a longitudinal view of their disease instead of just a snapshot," says Dr. Botha.

The creation of this large and growing speech bank, which securely stores all speech and voice samples, can be used for research, including using it to train artificial intelligence (AI) algorithms.  

"There are some signals in someone's voice and speech that a computer or an algorithm might pick up on, that a human listener wouldn't pick up on. And so that's more of the sort of research, AI side of things, where we're trying to use hundreds of recordings and patients with various diseases, and then trying to see if the computer can separate those diseases, even though human listeners may not be able to," says Dr. Botha.

The post Mayo Clinic Minute: Using voice to detect neurodegenerative disease appeared first on Mayo Clinic News Network.

Clinicians at Mayo Clinic can use artificial intelligence (AI) tools to effectively screen patients for a weak heart pump via a simple electrocardiogram (ECG). A new study addresses the next question: Is it good value for the money spent? 

ROCHESTER, Minn.  — Earlier research showed that primary care clinicians using AI-ECG tools identified more unknown cases of a weak heart pump, also called low ejection fraction, than without AI. New study findings published in Mayo Clinic Proceedings: Digital Health suggest that this type of screening is also cost-effective in the long term, especially in outpatient settings.

Incremental drops in heart function are treatable with medication but can be hard to spot. Patients may or may not have symptoms when their heart is not pumping effectively, and doctors may not order an echocardiogram or other diagnostic test to check ejection fraction unless there are symptoms. Peter Noseworthy, M.D., a Mayo Clinic cardiologist and co-author of the study, notes that using AI to catch the hidden signals of heart failure during a routine visit can mean earlier treatment for patients, delaying or stopping disease progression, and fewer related medical costs over time.

According to the study, the cost-effectiveness ratio of using AI-ECG was $27,858 per quality-adjusted life year — a measure of the quality of life and years lived. The program was especially cost-effective in outpatient settings, with a much lower cost-effectiveness ratio of $1,651 per quality-adjusted life year.

The researchers studied the economic impact of using the AI-ECG tool by using real-world information from 22,000 participants in the established EAGLE trial and following which patients had weak heart pumps and which did not. They simulated the progression of disease in the longer term, assigning values for the health burden on patients and the resulting effect on economic value.

"We categorized patients as either AI-ECG positive, meaning we would recommend further testing for low ejection fraction, or AI-ECG negative with no further tests needed. Then we followed the normal path of care and looked at what that would cost. Did they have an echocardiogram? Did they stay healthy or develop heart failure later and need hospitalization? We considered different scenarios, costs and patient outcomes," says Xiaoxi Yao, Ph.D., a professor of Health Services Research at Mayo Clinic.

Dr. Yao, who is the senior author of the study, notes that cost-effectiveness is an important aspect of the evaluation of AI technologies when considering what to implement in clinical practice.

"We know that earlier diagnosis can lead to better and more cost-effective treatment options. To get there, we have been establishing a framework for AI evaluation and implementation. The next step is finding ways to streamline this process so we can reduce the time and resources required for such rigorous evaluation," says Dr. Yao.

This study was funded by Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery. Mayo Clinic and some of the researchers have a financial interest in the technology referenced in this news release. Mayo Clinic will use any revenue it receives to support its not-for-profit mission in patient care, education and research.

###

About Mayo Clinic
Mayo Clinic is a nonprofit organization committed to innovation in clinical practice, education and research, and providing compassion, expertise and answers to everyone who needs healing. Visit the Mayo Clinic News Network for additional Mayo Clinic news.

Media contact:

• Terri Malloy, Mayo Clinic Communications, newsbureau@mayo.edu

The post Research study shows the cost-effectiveness of AI-enhanced heart failure screening appeared first on Mayo Clinic News Network.