Mayo Clinic researchers are combining biological, environmental and health data with artificial intelligence to identify changes that may signal disease years before clinical symptoms appear 

By the time doctors diagnose Alzheimer's disease, heart failure or cancer, the biological processes behind the illness may have been unfolding silently for years or even decades. 

Mayo Clinic wants to make those invisible years a new target for medicine. 

The healthcare organization is undertaking a sweeping research effort, called Precure Research, to identify the molecular and physiological changes that occur as people move from health toward disease and determine whether doctors can intervene before patients develop clinical symptoms. 

Precure Research initially focuses on diseases of the brain, heart, kidneys, liver and lungs. It brings together genetic information, biological specimens, medical records, environmental exposures, wearable-device data and artificial intelligence (AI). 

The goal is simple: Identify the early stages of disease sooner to improve outcomes. 

Achieving that goal requires answering hard questions. Among the countless biological changes that occur throughout a person's life, which ones reliably signal that disease is beginning, and which can doctors safely do something about? 

Mayo researchers say recent advances are beginning to make that challenge more solvable. 

In one large genetic study, Mayo scientists identified inherited risks for cancer and cardiovascular disease in nearly 2,000 participants, many of whom had no previous indication that they carried the risks. Other Mayo research has found certain precancerous changes that can be detected years before cancer develops. In Alzheimer's disease, scientists increasingly can measure biological changes that begin decades before memory problems become apparent. 

Taken together, those efforts point toward one of medicine’s biggest and transformational ambitions: shifting healthcare from treating established disease to predicting and preventing it. 

Vijay Shah, M.D., Mayo Clinic's Kinney executive dean of research, sees that shift as an extension of Mayo's longstanding approach to medical research: start with an unmet need of the patient, create the knowledge necessary to address it and bring the resulting discoveries back into clinical care. 

"At Mayo Clinic, our research and practice are intertwined," said Dr. Shah. "Everything we do must serve our primary value of putting the needs of the patient first." 

Heidi Dieter, Mayo Clinic's chief research administrator, said the change could ultimately alter the relationship between patients and the healthcare system itself. "We're not just treating disease anymore. We're partnering with people throughout their entire life journey," she said. 

The invisible years 

Doctors have traditionally encountered disease relatively late in its biological history. A tumor becomes visible on a scan. Kidney function declines. A patient develops symptoms of heart failure. Memory problems become noticeable. 

But disease does not begin at that clinical diagnosis. 

Before symptoms emerge, proteins can shift, metabolism can change, immune responses can evolve and environmental exposures can leave measurable biological traces. 

Precure researchers want to reconstruct that progression. 

The initiative combines information from genes, proteins, metabolites and immune signals with longitudinal medical records, environmental information and wearable devices. The approach allows researchers to examine different layers of biology together and how they change over time. 

A person might carry a genetic variant associated with higher disease risk for a lifetime without developing the condition. Researchers hope to understand what happens between inherited susceptibility and actual illness and identify when that trajectory might change. 

But finding a biological signal associated with disease isn't the same as developing a useful screening test. Researchers look for biological signals to develop screening tests that can help physicians intervene early, often when a condition is more easily and effectively treated.  

Looking beyond DNA 

Mayo's approach also extends beyond what is happening physiologically inside the body. 

Researchers are looking beyond genetics and incorporating the exposome, the accumulation of environmental and lifestyle exposures over a person's lifetime and the biological effects they produce. 

Those influences can range from diet, exercise and sleep to pollutants, chemicals and air quality. Researchers increasingly can detect biological traces of some exposures in blood and other specimens and connect them with genetics, clinical histories and geographic information. 

Pilot studies are examining questions including whether long-term air-pollution exposure affects solid-organ transplant outcomes and whether environmental chemicals influence how the body processes medications. Another is testing saliva-based biosensors for biological changes associated with triggers of head and neck cancers. 

Building a biological time machine 

Pulling those pieces together requires infrastructure on a scale that would have been impractical not long ago. 

Mayo says Precure Research ultimately aims to create its largest integrated collection of biological specimens and scientific and health information through Mayo Clinic Platform, connecting what is found in a blood or tissue specimen with molecular measurements, environmental exposures and years of clinical history. 

In effect, researchers want to reconstruct how a patient's biology arrived at a particular disease. 

Precure Research connects molecular information with deep, longitudinal clinical context and Mayo Clinic expertise through existing pathways and infrastructure, such as Digital Pathology, Mayo Clinic Platform and Research Data Atlas, to support research across diseases and data types. The resulting resources are intended to support discovery and translation, including research into biomarkers, diagnostics, therapeutics, clinical trial strategies and new clinical tools. 

AI is central to the strategy because the number of possible relationships quickly exceeds what researchers can examine manually. AI systems can search across genetic variants, proteins, medical records, imaging, environmental measurements and wearable-device readings for patterns that conventional analysis might miss. 

Mayo Clinic is building a research foundation designed to support discovery across diseases, not one study at a time. Connecting clinical information, biospecimens and molecular data at scale can reveal biological relationships that would otherwise remain hidden, allowing an insight from one disease to inform the understanding, prediction or treatment of another. 

A historic institution looks to medicine’s future 

Mayo Clinic is positioned to pursue an ambition as large as Precure Research in part because transforming how medicine is practiced is embedded in its history. 

For more than 160 years, Mayo Clinic has sought fundamentally better ways to care for patients. Its development of the group practice of medicine brought physicians with different specialties together around the needs of an individual patient. Its adoption of a longitudinal medical record gave those physicians something medicine once lacked: data to allow the ability to understand a patient's health not simply at a moment in time, but across years. 

Those innovations changed more than the tools available to physicians. They helped change how medical care was delivered. 

Precure Research is Mayo's next step to extend that history and culture of transformation into a new era. 

The difference is the resolution.

Where a longitudinal clinical record allowed physicians to see a patient's medical history across years, Precure researchers hope to observe the biological history occurring beneath it. 

That ambition also rests on another part of Mayo’s history: patients participating in research. 

Patients who contribute clinical information and biological specimens help researchers identify patterns that no individual patient or physician could reveal alone. Their contributions can help researchers generate knowledge that could lead to better ways to predict, prevent and treat disease, with the potential to benefit patients at Mayo Clinic and beyond. 

By contributing information and specimens over time, patients can help researchers better understand the progression from health to disease and explore opportunities to preserve health for themselves, their families and for future generations. 

From predicting disease to preventing it 

The long-term ambition extends beyond early diagnosis. 

Precure Research will allow for the study of biological processes including inflammation, aging and metabolic dysfunction that cut across diseases traditionally treated by different medical specialties. 

A patient eventually diagnosed with heart failure, kidney disease or dementia might share some underlying biological pathways years earlier. Identifying those mechanisms could give doctors opportunities to intervene before irreversible damage occurs. 

Mayo describes the ultimate objective as extending healthspan, which is the portion of a person's life spent in good health and without significant chronic disease or disability. 

That means identifying not just who is likely to develop a disease, but also when risk becomes actionable and which intervention can alter the trajectory. 

Precure Research is built on the premise that the next major advance in medicine may not come from a single new drug, device or technology, but from understanding human health in ways that avoid disease all together.

The post Can disease be identified before symptoms begin? Mayo Clinic researchers are looking for answers appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — A liver disease affecting nearly 30% of adults worldwide is not a single illness but five biologically distinct subtypes, Mayo Clinic researchers have found. Each carries different risks for heart disease, liver failure, cancer and the need for liver transplantation.

The study, published in Nature Communications and conducted in collaboration with scientists at Virginia Tech, shows that metabolic dysfunction-associated steatotic liver disease has multiple pathways — some tied to obesity and diabetes, others driven by inherited genetic factors.

Notably, genetic subtypes are associated with a higher risk of progression to advanced liver disease, including in patients without typical metabolic risk factors.

The findings could help identify high-risk patients earlier and guide more precise screening and personalized treatment.

"When clinical and genomic data are analyzed together at this scale, you begin to see patterns of disease progression that would otherwise remain hidden," says Shulan Tian, Ph.D., co-senior author and a bioinformatician at Mayo Clinic. "Once you separate these subtypes, you can start to match treatments to the biology that's actually driving the disease."

Metabolic dysfunction-associated steatotic liver disease, formerly called nonalcoholic fatty liver disease, occurs when fat builds up in the liver. It often develops without symptoms but can progress to inflammation, scarring and irreversible damage. It is a leading cause of cirrhosis, liver cancer and transplantation worldwide.

Decoding liver disease at scale

To uncover these subtypes, researchers integrated genetic sequencing with detailed clinical data from more than 4,600 patients with the disease. The dataset spanned a wide range of measures — from liver enzymes, body mass index and lipid levels to coexisting conditions such as diabetes, depression and sleep apnea.

Using advanced computational modeling, the team identified groups of patients who shared underlying biological signals, defining distinct subtypes of the disease.

"What's emerging here is a way to systematically identify meaningful subgroups within complex disease," says Eric Klee, Ph.D., co-senior author and the Everett J. and Jane M. Hauck Midwest Associate Director of Research and Innovation. "It helps us map complex disease with such precision that we can begin to anticipate its course and intervene before the most serious damage occurs."

The discovery was powered by Mayo Clinic's Research Data Atlas, a platform that connects genetic data with patient records to reveal patterns across large populations — a system Dr. Klee helped build. A key component of the Atlas is the Tapestry Study, which has generated Mayo Clinic's largest collection of exome data from more than 100,000 participants. The dataset captures key genetic information that shapes how diseases develop and progress.

"This is exactly the kind of insight large-scale genomic research was built to deliver," says Konstantinos Lazaridis, M.D., the Carlson and Nelson Endowed Executive Director for the Center for Individualized Medicine who led the Tapestry Study and is a co-author of the research. "When you connect genetic data with detailed clinical information across large populations, you can start to redefine diseases in ways that directly impact patient care."

Liver disease's hidden effects across the body

The study also revealed links beyond the liver. For the first time, researchers found that specific subtypes are associated with conditions such as depression, sleep apnea and migraine, underscoring the disease's broad systemic impact across multiple organ systems.

Next, the team plans to test the approach in broader patient populations and explore how these subtypes respond to different treatments, including therapies such as GLP-1 receptor agonists.

First author Tahmina Sultana Priya, now a Ph.D. student at Virginia Tech, contributed to the research while at Mayo Clinic. For a complete list of authors, disclosures and funding, review the study.

###

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:  

• Kelley Luckstein, Mayo Clinic Communications, newsbureau@mayo.edu

The post 5 subtypes of common liver disease discovered — including rapidly progressing genetic forms appeared first on Mayo Clinic News Network.

PHOENIX — Mayo Clinic researchers have developed and externally validated an artificial intelligence (AI) model that can identify a potentially significant heart obstruction from routine ultrasound videos without relying on specialized Doppler imaging. The technology could help clinicians flag patients with hypertrophic cardiomyopathy (HCM) who may need additional testing, particularly in settings where specialized echocardiography expertise is limited. Study findings are published in Circulation: Cardiovascular Imaging.  

HCM is a genetic condition that causes the heart muscle to become abnormally thick. About two-thirds of these patients develop left ventricular outflow tract (LVOT) obstruction, which restricts blood leaving the heart, causing symptoms such as chest pain and shortness of breath with exertion or when lying flat. Knowing which patients develop LVOT obstruction is important because it influences treatment decisions and long-term management for patients with HCM. 

"Measuring LVOT obstruction typically requires Doppler echocardiography, which depends on precise ultrasound-beam alignment and operator expertise," says Imon Banerjee, Ph.D., an AI researcher at Mayo Clinic in Phoenix and senior author of the study. "We wanted to determine whether AI could recognize subtle patterns that are imperceptible to the human eye in routinely acquired B-mode ultrasound videos and identify patients with LVOT obstruction earlier, enabling timely confirmatory Doppler evaluation and referral when appropriate." 

The study included 1,833 patients in the Mayo Clinic cohort. The model was tested in 275 patients and externally validated in 46 patients from a hospital in South Korea. The AI model used only resting, non-Doppler ultrasound videos to predict whether a patient had a potentially significant obstruction to blood leaving the heart. Researchers found that combining information from three standard ultrasound views improved the model's ability to distinguish patients with elevated LVOT gradients. The model also helped identify obstruction that may only appear when the heart is under stress. 

The model maintained strong performance in the South Korean group despite substantial differences between that population and the patients used to develop the model, supporting further study of the technology across different patient populations and clinical settings.  

In a subset of cases, the AI model identified obstruction more accurately than two expert echocardiographers who reviewed the same non-Doppler images. The findings highlight how difficult it can be to recognize LVOT obstruction from routine two-dimensional images without Doppler measurements. 

"This technology is intended to complement, not replace, Doppler echocardiography," Dr. Banerjee says. "By enabling earlier identification of patients with potential LVOT obstruction, it could escalate timely detection and prompt confirmatory Doppler measurements, stress testing, or referral to an HCM specialty center. It also could support evaluation using portable ultrasound or in settings where comprehensive Doppler assessment may not be readily available, helping expand access to earlier screening and risk assessment." 

Dr. Banerjee notes that the next steps include additional prospective validation across broader clinical settings, ultrasound platforms and patient populations. 

The list of authors and disclosures may be found in the article, Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCM. This study received no external funding. 

### 

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 AI model helps clinicians detect heart obstruction using routine ultrasound images appeared first on Mayo Clinic News Network.

Healthcare AI is evolving beyond predicting outcomes to helping clinicians and researchers make informed decisions.

This shift was a key focus of Mayo Clinic's AI Research Summit, where more than 750 researchers, clinicians, AI scientists, engineers, students and other innovators gathered June 4–5 in Rochester, Minnesota, and online.

"The future of healthcare AI is not simply about building better predictor models, it's about developing integrated decision intelligence systems," said Cui Tao, Ph.D., the Nancy Peretsman and Robert Scully Chair of AI and Informatics at Mayo Clinic.

The summit highlighted emerging approaches such as multi-agentic AI, in which multiple agents work together on complex tasks, and simulations that use real-world data to test ideas and generate insights faster.

Helping personalize patient care

A key application of healthcare AI is personalized decision support at the point of care.

Yong Chen, Ph.D., of the University of Pennsylvania, said clinicians need tools that go beyond prediction to help them determine which actions will lead to the best patient outcomes.

Healthcare is a sequence of interconnected decisions that evolve over time — which treatment to use, when to intervene and when to adjust care. Integrated AI tools could help care teams determine the optimal next step for each patient.

For example, when patients receive an implant such as a stent, personalized decision-making support systems could help clinicians determine the best timing for antiplatelet therapy while reducing the risk of complications.

Changing how discoveries are tested

AI and automation may help researchers accelerate the discovery and testing of new medical treatments, said Matt Redlon, chair of the AI Program and vice president of Digital Biology, Mayo Clinic Digital Pathology.

For many diseases, thousands of existing drugs could be studied for potential repurposing, said Redlon.

Multi-agentic AI systems could be used to simultaneously analyze data from multiple sources such as biospecimens and clinical records, helping researchers identify the most promising treatments for further study.

Researchers also are exploring virtual trials, which use AI and existing healthcare data to simulate clinical trials, as a strategy to generate early signals from real-world data. This could substantially shorten the timeline for assessing promising new therapies for patients.

Watch: Mayo Clinic summit highlights shift in healthcare AI research

Journalists: Broadcast-quality sound bites are available in the downloads at the bottom of the posts. Name super/CG: Cui Tao, Ph.D./Nancy Peretsman and Robert Scully Chair of AI and Informatics at Mayo Clinic/Mayo Clinic/Matt Redlon/Chair of AI Program, Vice President of Digital Biology in Digital Pathology/Mayo Clinic/Micky Tripathi, Ph.D./Chief AI Implementation Officer/Mayo Clinic

Supporting clinicians and researchers

In addition to delivering more personalized care, AI technologies are being developed to streamline work for healthcare staff.

Some solutions are designed to augment human capabilities by "doing things that humans literally can't do with the limitations of our senses," said Micky Tripathi, Ph.D., chief AI implementation officer at Mayo Clinic.

For example, researchers have developed AI models that can help clinicians detect pancreatic cancer early from routine abdominal scans before tumors are visible.

Building the foundation for responsible AI

Peter Lee, Ph.D., president of Microsoft Science, emphasized that AI in healthcare has rapidly moved from idea to infrastructure, with solutions such as ambient tools that capture data in patient care now widely used.

As these capabilities expand, healthcare organizations must build the governance, oversight and supporting infrastructure needed to deploy technologies safely, responsibly and reliably.

Tripathi compared this to building a car. "You defined an engine; that's great. But it doesn't have a chassis, doesn't have a steering wheel, doesn't have windshield wipers, it doesn't have lights," he said. "We need all of those things."

Speakers emphasized that human oversight remains essential, with clinicians and researchers responsible for evaluating information and making final decisions.

"The momentum is clearly growing," Dr. Tao said. "If AI is going to become a part of real clinical care, we need rigorous validation, a governance framework, workflow integration and translational maintenance. And that translation from innovation to responsible implementation is exactly where the field is heading next."

Other experts, including Yi Qian, vice president of Global Real World Evidence at Johnson & Johnson, highlighted approaches to creating trusted evidence and insights for clinical care.

Related

• Mayo Clinic and Microsoft collaborate to develop a frontier AI model for healthcare 
• How researchers are using AI to accelerate the path to cures (VIDEO)
• How 60 years of health data helped shape modern medicine

The post Mayo Clinic summit explores the next phase of healthcare AI (VIDEO) appeared first on Mayo Clinic News Network.

A routine mammogram may do more than detect breast cancer, it also could help identify early signs of heart disease.

Heart disease is the leading cause of death among women, responsible for 1 in 3 deaths. It often develops without symptoms until a major event occurs. Despite this, there is not a standard for annual heart disease screening, a critical gap in early detection for women.

Doctors typically assess heart disease risk using factors like cholesterol, blood pressure and body weight. These tools don't fully account for how heart disease develops differently in women or what's happening inside the blood vessels themselves.

A missed opportunity in routine mammograms

Mayo Clinic recommends women at average risk begin annual mammogram screening at age 40, and most women do. Researchers say this creates an opportunity to assess heart disease risk during a test many women already receive without additional radiation or testing.

Breast arterial calcification (BAC) is captured during a mammogram. For two decades, studies have demonstrated that it can be used to help identify patients at risk for heart disease. However, the challenge has been measuring it accurately and consistently, and assigning a value to it.

"BAC is difficult to measure because it appears as a very subtle finding on standard 2D mammograms and cannot be consistently quantified by eye, even by experts. As a result, it typically requires specialized computational methods to reliably detect and measure it," explains Dr. Imon Banerjee, scientific director of the Arizona Advanced AI and Innovation Hub at Mayo Clinic. "AI allows us to measure these calcium deposits quickly and more accurately than before."

Large study shows strong link to risk

A retrospective cohort study published in the European Heart Journal included more than 120,000 women who had screening mammograms at two healthcare systems. They evaluated whether AI-derived BAC measurements could help clinicians predict a woman's risk of cardiovascular disease and death, independent of traditional risk factors. Researchers note the study was observational and evaluated associations between BAC and future cardiovascular outcomes.

"Breast arterial calcification occurs when calcium builds up in the walls of the arteries within breast tissue," says Dr. Banerjee. "Calcium seen on mammograms correlates with calcification in other parts of the body. This type of calcium in the breast is different from calcium in the heart. Instead of blocking blood flow, it makes the blood vessels stiffer and less flexible, signaling a higher risk of heart problems because it affects how blood moves."

Using a deep learning model, the team developed a tool that identifies calcium deposits, measures their extent and classifies severity. Researchers then tracked whether higher levels were associated with cardiovascular events or death over time.

The findings were significant. Women with severe BAC had more than 10 times the risk of developing a cardiovascular event within five years compared to those with no or mild BAC. The model was validated across 12 institutions, comparing AI-generated measurements with radiologist assessments. The AI model is now undergoing Food and Drug Administration review.

WATCH: Dr. Imon Banerjee - AI can accurately measure heart disease risk

 Journalists: Broadcast-quality sound bites are available in the downloads at the end of the post. Please courtesy: "Mayo Clinic News Network." Name super/CG: Imon Banerjee, Ph.D./ Radiology /Mayo Clinic.

Moving towards clinical use

"We created an AI algorithm that allows us, with a single click, to measure BAC. It can now easily be added to the radiologist's report," Dr. Banerjee says. "That measurement becomes a new input for the prediction models. This could completely change the screening workflow for women and improve early detection of heart disease."

Adoption remains the next challenge

"The challenge with BAC is that we have the algorithm, we have the validation, we know that it works. Now, how do the institutions adopt it?" acknowledges Dr. Banerjee. "There are currently no clinical regulations of BAC. Mayo Clinic physicians are translating this research into practice."

Teams across Cardiovascular Medicine, Primary Care, Women's Health and Radiology at Mayo Clinic's Arizona and Florida campuses are working to integrate the technology into clinical practice and develop a framework for broader use before expanding to all Mayo Clinic sites.

Related article: How researchers are using AI to accelerate the path to cures (VIDEO)

The post Mammograms may help identify heart disease risk (VIDEO) appeared first on Mayo Clinic News Network.

The Rochester Epidemiology Project (REP) has served as a cornerstone for population health research for six decades, providing the longitudinal data essential for predicting health outcomes. Today, the REP functions as a resource in helping to study medical conditions, including heart failure, dementia, cancer and bone health.  

Because it maintains decades of history on a stable population, the REP allows investigators to identify long-term trends such as early warnings of rising disease incidence that would be difficult to capture in shorter, isolated studies. 

This year, as the REP celebrates its 60th anniversary, Mayo Clinic is highlighting how this historic medical records linkage system remains a powerful tool that helps scientists study population health over many decades. 

"The REP is a unique collaboration between health care providers, patients and scientists to use medical record information to study health and health outcomes," says Jennifer St. Sauver, Ph.D., co-principal investigator of the Rochester Epidemiology Project. 

"Since 1966, the REP has supported research on virtually every health condition, including studies of what causes different diseases, how patients respond to surgeries and therapies, and how diseases change over time." 

Dr. St. Sauver notes that the REP has been instrumental in understanding the pathogenesis of so many different conditions that it is difficult to name only a few. 

"The REP has supported major research programs to understand bone and joint conditions; Alzheimer's disease and related dementias; lupus; rheumatoid arthritis; kidney stones; heart failure; (and) breast, prostate, blood and pancreatic cancers," says Dr. St. Sauver.  

The next phase: AI-driven research 

By combining 60 years of history with tomorrow's technology, the REP continues to find new ways to help people live longer, healthier lives.  

Today, the integration of artificial intelligence (AI) has the potential to accelerate these discoveries even further.  

"The REP is uniquely positioned to evolve into a next-generation, AI-enabled population health platform," says Cui Tao, Ph.D., the Nancy Peretsman and Robert Scully Chair of Artificial Intelligence and Informatics at Mayo Clinic. 

"Key opportunities include leveraging linked longitudinal data to simulate interventions, accelerate clinical research and support real-world evidence generation." 

Dr. Tao notes that the REP can also help bridge population-level insights with individualized risk prediction and precision intervention strategies. 

"As AI methods continue to mature, the REP provides an exceptional foundation for integrating multimodal data and enabling scalable translational research," says Dr. Tao.  

"With nearly 2.9 million patient records and decades of follow-up data, the REP represents a rare scientific resource with the potential to help shape the future of precision medicine and AI-driven healthcare discovery." 

Dr. Tao shares that Mayo Clinic Epidemiology and REP collaborators will participate in workshops and lightning talks at the upcoming AI Research Summit taking place June 4-5, which will include an evening commemorating the program's 60th anniversary.  

The post How 60 years of health data helped shape modern medicine appeared first on Mayo Clinic News Network.

Artificial intelligence (AI) and automation are enabling researchers to advance discoveries into patient care faster and with greater precision, opening new ways to address complex needs in medicine.

"With AI, they're now able to ask and answer questions that they were not able to answer before," says Cui Tao, Ph.D., a professor of Biomedical Informatics and the Nancy Peretsman and Robert Scully Chair of Artificial Intelligence and Informatics at Mayo Clinic.  

Researchers are also using AI to identify clinical trials for patients and to accelerate the research process — from early ideas to new treatments in patient care.   

Watch: Dr. Cui Tao explains how researchers are using AI tools to accelerate their work

Journalists: Broadcast-quality soundbites are available for downloads at the end of the post. Please courtesy: "Mayo Clinic News Network." 

Using AI to accelerate cures  

Dr. Cui Tao shares her perspective on how researchers are using AI to reshape scientific discovery and accelerate the path to patient care: 

What does it mean to use AI to accelerate research?  
Using AI to accelerate research discovery is more than just using AI as a downstream analytics tool. It's about being able to embed AI into the whole procedure.  

Traditionally, when we conduct research, it's more of a linear procedure — from hypothesis generation to study design to collecting data and, finally, getting the result and interpreting the result. That's a linear process. But with AI, we're able to accelerate the whole process and iteratively test each step at the same time. 

How does using AI change the way studies and clinical trials are designed?
We can actually develop different AI agents for cohort matching, for clinical design, to refine how we conduct clinical trials in the traditional way.  

Our teams can also use AI to help patients understand the complex informed consent forms and to help identify those patients who are likely to be eligible for certain trials, from recruiting to data analysis to long-term follow-up. 

What do researchers tell you excites them most about these approaches? 
With AI, now we're able to accelerate everything, so it actually saves critical time for our researchers so that they can focus more fully on innovation, creativity and research.  

How is Mayo Clinic ensuring discovery is focused on the right things for patients?  
Whatever AI tools we design, they need to fulfill the needs of our patients and clinicians. We also emphasize AI regulation — the AI tools need to be safe, need to be trustworthy, before we can put them into actual patient care. 

Why is a multidisciplinary approach across biomedical, computational and social sciences important? From physicians to clinicians to data scientists to AI scientists and engineers ... We need to all work together to make sure that whatever we're building is impactful.  

And we need to ensure a bidirectional translational path: First, we need to be able to understand the clinical or biomedical question and translate that into an AI problem; and second, we need to be able to translate the AI solutions back into practice so that people can use them. 

Join leading experts at Mayo Clinic's AI Research Summit 

Join Dr. Tao and other experts at Mayo Clinic's AI Research Summit on June 4–5 in Rochester, Minnesota, and online. This conference brings together leaders and innovators to share advances in healthcare AI research, explore emerging methods and build collaborations.  

This year's summit will explore topics such as multi-agent clinical intelligence, simulation, virtual twins and multimodal foundation models. Sessions will also focus on translating AI research into clinical practice and building trustworthy, governable systems. 

In addition to Dr. Tao, the keynote speakers are:  

• Peter Lee, Ph.D., president of Microsoft Research and Mayo Clinic trustee 
• Micky Tripathi, Ph.D., chief AI implementation officer at Mayo Clinic 
• Yong Chen, Ph.D., director of the Center for Health AI and Synthesis of Evidence at the Perelman School of Medicine, University of Pennsylvania 
• Yi Qian, vice president of Global Real-World Evidence at Johnson & Johnson  
• Matt Redlon, chair, AI Program, and vice president, Digital Biology, Mayo Clinic Digital Pathology   

Register by May 30 on the event website. 

The post How researchers are using AI to accelerate the path to cures (VIDEO) appeared first on Mayo Clinic News Network.

A new era of medicine is emerging at Mayo Clinic — one that finds disease before symptoms appear 

ROCHESTER, Minn. — When Mayo Clinic researchers sequenced the genomes of 484 seemingly healthy adults, they found that about 13% carried a serious, previously unrecognized genomic risk — conditions those patients did not know about and that standard care would likely miss.

Nearly all participants, 98.6%, had at least one genetic finding, and for most, the results called for monitoring. The study, published in Genetics in Medicine, also takes a closer look at what it takes to turn those findings into the proper follow-up care.

Among the 13%, the actionable findings pointed to serious risks, including hereditary breast and ovarian cancer; Lynch syndrome, linked to colorectal cancer; cardiomyopathy; long QT syndrome; and amyloidosis.

"These are people traditional testing based on symptoms or family history would not identify," says Dr. Konstantinos Lazaridis, the Carlson and Nelson Endowed Executive Director of the Center for Individualized Medicine and senior author of the study. "This study helps define the blueprint for integrating genomic insight into care at scale — turning information into decisions that can change the trajectory of disease."

From discovery to care

Identifying the risk, it turns out, is the easiest part. Acting on it is far more complex. Nearly every case required clinical interpretation, documentation and communication. This work fell largely to genetic counselors, who reviewed results, prepared individualized summaries and helped guide next steps for patients and care teams.

"Genetic counselors are often the first people to share this kind of information with patients," says Jessa Bidwell, a certified research genetic counselor and first author of the study. "There can be surprise, anxiety, devastation, and at times relief at finally having an explanation. Our role is to meet people in that moment and help them understand what their health risks might be, based on the genetic finding, and their personal and family history."

Most participants with actionable findings followed through, completing referrals and connecting with primary care specialists. Yet fewer than half had a documented conversation with a primary care professional after receiving results — underscoring how difficult it remains to integrate genomic findings into routine care.

The study positions predictive genomic screening as both a clinical opportunity and a systems challenge. The science exists. Researchers and clinicians are still building the infrastructure to act on it consistently.

At Mayo Clinic, that infrastructure is beginning to take shape through an initiative called Precure. Genomic screening is one part of that initiative, which aims to detect disease earlier by combining genetic data with other biological signals.

"Precure is one example of a moonshot for human health at Mayo Clinic," says Dr. Lazaridis, who leads the initiative. "It reflects Mayo Clinic's commitment to move medicine beyond treatment and toward lasting wellness." - Dr. Lazaridis

Predicting disease before it begins 

Most diseases don't arrive without warning. They begin with small shifts in genes, molecules, proteins and immune signals that develop over time, often years before symptoms appear.

Precure is Mayo Clinic's enterprise-wide effort to detect those early signals and intervene sooner. Powered by advanced computing and artificial intelligence (AI), the initiative currently focuses on five organ systems — the brain, heart, kidneys, liver and lungs — studying conditions such as Alzheimer's disease, heart failure and chronic liver disease to better understand how they emerge and progress.

The work draws on expertise from across Mayo Clinic and is supported by Mayo Clinic Platform, which brings together large-scale patient data and advanced computing to enable scientists to study disease across populations.

"Precure is one example of a moonshot for human health at Mayo Clinic," says Dr. Lazaridis, who leads the initiative. "It reflects Mayo Clinic's commitment to move medicine beyond treatment and toward lasting wellness."

Precure is part of Mayo Clinic's Bold. Forward. strategy to Cure, Connect and Transform healthcare. The genomic screening study is an early demonstration of what that looks like in practice: science that doesn't wait for disease to announce itself, and a system already being built to act on what it finds.

For a complete list of authors, disclosures and funding information, review the study. 

###

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:

• Julie Ferris-Tillman, Ph.D., Mayo Clinic Communications, newsbureau@mayo.edu

The post Mayo Clinic study finds 1 in 8 adults carries hidden genetic risk — and reveals what it takes to act on it  appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Mayo Clinic research identified a powerful new way to improve the prediction of a patient's long-term cardiovascular disease risk by enhancing a routinely performed imaging test with artificial intelligence (AI). Heart disease develops over time and remains the leading cause of death worldwide, so identifying risk early is critical to preventing heart attack, stroke and other serious outcomes.

The study highlights the growing role of AI in helping experts uncover new insights from existing medical data. Findings were presented at the 2026 American College of Cardiology Scientific Session with simultaneous publication in the American Journal of Preventive Cardiology.

The study followed nearly 12,000 adults for approximately 16 years. Investigators applied AI to participants' standard coronary artery calcium scans to measure fat surrounding the heart. They compared the predictive value of this measurement with and in combination with two standard risk assessment approaches: the American Heart Association PREVENT equation, which incorporates traditional factors such as age, sex, blood pressure, cholesterol, diabetes and other variables, and the coronary artery calcium score, which measures calcified plaque in coronary arteries.

The findings show that the volume of heart fat could be used independently to predict cardiovascular events. It significantly improved the overall accuracy of long-term risk prediction when combined with the coronary artery calcium score and the PREVENT equation, especially among patients in low-risk categories.

"Pericardial fat has been recognized as a marker of cardiovascular risk, but this study shows how we can now measure it automatically and use it to meaningfully improve risk prediction, especially in patients at borderline or intermediate risk where clinical decisions are often less clear," says Zahra Esmaeili, first author and researcher in the Department of Cardiovascular Medicine at Mayo Clinic. "This opens the door to more personalized prevention strategies."

Key findings:

• Nearly 10% of participants developed cardiovascular disease during follow-up.
• Higher fat volume around the heart was independently associated with increased risk of cardiovascular events, even after accounting for traditional risk factors and coronary calcium scores.
• Participants with the highest coronary fat volume had elevated risk across all coronary calcium levels.
• Adding coronary fat measurements improved the accuracy of predicting cardiovascular events beyond established models.

Coronary artery calcium scoring is widely used to assess cardiovascular risk. This study shows that additional information can be extracted from the same scan without extra testing or cost.

"Because this measurement comes from imaging that many patients are already receiving, it represents a practical and scalable way to enhance cardiovascular risk assessment," says senior author Francisco Lopez-Jimenez, M.D., a preventive cardiologist and co-director of the AI in Cardiology program at Mayo Clinic. "It could help clinicians intervene earlier and more effectively."

Researchers note that further studies will help determine how best to incorporate coronary fat measurement into routine clinical care and whether it can guide treatment decisions.

The manuscript, Deep Learning–Derived Pericardial Adipose Tissue by ECG-Gated Computed Tomography Predicts Cardiovascular Events Beyond Coronary Calcium, and a complete list of authors is published in the American Journal of Preventive Cardiology.

###

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 Including AI-derived heart fat measurement improves accuracy of cardiovascular disease risk prediction appeared first on Mayo Clinic News Network.

When Karen Koellner reached for her phone charger while in bed one night, she felt pain. Curious, she got up and went to her bathroom mirror to check — and her instinct told her something was definitely wrong. She found a lump in her armpit and knew it might be cancer.

The next day, she called her doctor, who referred her to Mayo Clinic's Arizona campus. Fear set in as she expected to wait days before getting an appointment.

Instead, she received a call within two hours.

Manual processes and paperwork are often part of healthcare, but these tasks can take valuable time away from patient care. They can also delay care for patients who need it most.

That is beginning to change.

Intelligent automation helps Mayo Clinic move faster and smarter. A new automation initiative is already improving the experience for patients like Karen, who was diagnosed with stage 3 breast cancer. An intelligent referral processing system flagged her case as urgent based on clinical patterns, prompting staff to reach out right away. Her appointments were scheduled across multiple specialties the next day, with care teams coordinating across states, disciplines and workflows.

"Being seen by an oncologist quickly was important to me," Karen says. "I was able to move forward with a treatment plan rather than waiting and worrying about the unknown."

The automated document referral system was developed at Mayo Clinic to triage incoming patient referrals using generative artificial intelligence (AI) in place of faxes, which had to be processed by hand. By eliminating one of the most time-consuming administrative workflows, the system shortens referral timelines and strengthens coordination across care teams. That means staff can spend more time focused on patients — and anxious patients like Karen experience less of a wait during the critical time between diagnosis and their first appointment.

"That is a crucial time period for patients with serious and complex medical conditions, when every moment truly matters," says Erin Layman, operations manager for Hematology and Medical Oncology at Mayo Clinic in Arizona. "It's important to have an intelligent system that can pull information from multiple documents, summarize it and allow staff to quickly review for accuracy. That helps move high-risk patients through the process much faster."

Karen calls it a game-changer in healthcare.

"Automation for patients with time-sensitive, critical diseases such as cancer has the potential to save lives by getting treatment plans started as soon as possible," she says.

The system, used in multiple departments across Mayo Clinic, worked to Karen’s advantage. Now finished with her treatment, she says she's feeling much better and is grateful to be cancer-free.

The post From fear to a phone call in 2 hours, breast cancer patient gets care faster with the help of intelligent automation appeared first on Mayo Clinic News Network.