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.

Join healthcare innovators for Mayo Clinic's annual AI Research Summit on June 4–5 in Rochester, Minnesota. This premier conference brings together leading experts to explore advances in artificial intelligence (AI) in healthcare, share emerging methods and best practices, and discover new collaborations. A virtual attendance option is also available.

This year's summit will highlight multi-agent modeling and simulation as a new approach for generating real-world evidence. 

"At Mayo Clinic, we are leading the development of AI methods — such as multi‑agent systems and simulation — that allow us to model complex patient scenarios and generate rigorous evidence far faster than traditional approaches," says Dr. Cui Tao, the Nancy Peretsman and Robert Scully Chair of Artificial Intelligence and Informatics at Mayo Clinic.

"These tools are helping us compress what once took years of trials and discovery into months, enabling trustworthy AI solutions that support better decisions and accelerate cures. This year's summit brings together researchers, data scientists, students and clinicians to drive this progress, and we are pleased to partner with our colleagues who help move scientific advances into practice," Dr. Tao says. 

The program 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.

The event's keynote speakers are: 

• Cui Tao, Ph.D., the Nancy Peretsman and Robert Scully Chair of Artificial Intelligence and Informatics 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
• Peter Lee, Ph.D., president of Microsoft Research and Mayo Clinic Trustee
• Micky Tripathi, Ph.D., chief AI implementation officer at Mayo Clinic
• Yi Qian, vice president of Global Real-World Evidence at Johnson & Johnson 
• Matt Redlon, senior administrator, AI Program at Mayo Clinic

Early-bird registration is available through April 30 on the event website.

Submit your work for presentation

Present your work to an audience that includes experts from Mayo Clinic, industry and top academic institutions. Proposals are being accepted for three presentation formats: 

• 10-minute lightning talks
• Poster presentations
• Workshops and tutorials

Abstracts selected for top recognition will be published in Mayo Clinic Proceedings: Digital Health. A subset of presenters will be invited to expand their work into full articles for publication after peer review. 

Proposals may be submitted through the AI Research Summit website as part of the event registration process. Abstract submissions will be accepted through March 6.

Learn more

Learn more and register on the event website.

The post Connect with leading experts at Mayo Clinic’s AI Research Summit appeared first on Mayo Clinic News Network.

This episode of the "Tomorrow's Cure" podcast discusses developments in rheumatoid arthritis research and the emerging technologies shaping what's possible in care. Featuring Dr. John Davis, III, Mayo Clinic rheumatologist and Dr. Kevin Deane, University of Colorado rheumatologist, the episode highlights how early‑stage research and emerging technologies are reshaping what's possible in rheumatoid arthritis care. 

Rheumatoid arthritis is an autoimmune condition that affects far more than joints. Crucially, researchers now know that autoantibodies, such as anti-cyclic citrullinated peptide (anti‑CCP) and rheumatoid factor, often develop years before diagnosis, signaling early immune system disruption. 

Traditional blood tests predict future rheumatoid arthritis only about 30% of the time — too uncertain for preventive treatment. To close this gap, researchers turn to AI and multisource data such as genetic information, lifestyle and environmental exposures, microbiome patterns, imaging and clinical records, and wearable health metrics. AI can piece together complex risk profiles that traditional methods can't, helping identify individuals most likely to develop the disease and when. 

New evidence suggests rheumatoid arthritis may start at mucosal surfaces such as the lungs, gut or gums before affecting joints. Environmental factors such as smoke, pollution and airborne particles may play a role in triggering early immune activation. 

At the same time, the gut microbiome is emerging as a powerful predictor of both rheumatoid arthritis risk and treatment response. Certain bacteria influence inflammation and can even metabolize medications such as methotrexate, affecting how well patients respond. 

Over the next decade, experts anticipate transformative shifts in rheumatology, including more precise biomarkers and antibody panels; AI-guided prediction tools that can lead to personalized, data-driven treatment plans; expanded virtual care options to increase access; and a deeper understanding of environmental and immune triggers.  

"I think this is where we need to go … trying to put together a lot of data that we can digitize about an individual, such as health, risk factors, behaviors, even wearable data, and analyze it using AI to identify people who could be at risk long before symptoms appear," Dr. Davis says. The long‑term goal is clear: identify rheumatoid arthritis before joint damage occurs and ultimately prevent the disease altogether. 

Listen to the latest episode of "Tomorrow's Cure" wherever you get your podcasts. You can explore the full library of episodes and guests on the show's page. 

The post Rewriting the future of rheumatoid arthritis: How early detection is transforming prevention  appeared first on Mayo Clinic News Network.

Evenings in the Staal household often carried a delicate unpredictability. After a full school day — and as Ethan's medication began to wear off — the shift from playful to overwhelmed could happen in seconds. Ethan has attention-deficit/hyperactivity disorder (ADHD), a condition that can make emotional regulation especially challenging.  

Ethan's feelings sometimes escalated faster than he could manage. In those difficult moments, his parents say, he became "not accessible" — often needing close to an hour before they could help guide him back to calm. 

Their search for specialized care led them to Mayo Clinic, where child and adolescent psychiatrist Magdalena Romanowicz, M.D., introduced the family to Parent-Child Interaction Therapy. She also invited them to participate in a first-of-its-kind study powered by a smartwatch and artificial intelligence (AI). 

The smartwatch technology was designed to help anticipate when a child was nearing emotional overload, giving parents a chance to step in and defuse the situation before it escalated. For the Staals, the technology offered a clear sense of what was happening inside Ethan just early enough to help him through it. 

"It was a game-changer," Jared Staal says. "We still have challenges, but now we see them coming and we see them through a whole different lens — we didn't always know how to support him in those moments, and now we do." 

A window into the moments before escalation

During the four-month study, Ethan wore a smartwatch that tracked his heart rate, movement and sleep. When the system detected patterns that suggested his stress was building, it sent an alert to Sarah or Jared's phone. 

"It gave us a warning that something was coming," Sarah says. Instead of reacting at the peak of Ethan's distress, they could intervene earlier with calm reassurance, redirection and other techniques they learned in their 12 Parent-Child Interaction Therapy sessions. 

"We could help him recover in 5 to 10 minutes," she says. "And we could have our evenings again as a family." 

What the study revealed 

The Staals' experience reflects the study's overall findings. In the clinical trial, smartwatch alerts prompted parents to respond within four seconds on average to early signs of escalating stress. Their children's severe tantrums were shortened by about 11 minutes — roughly half the duration seen with standard therapy alone. 

The broader context underscores the need for new approaches. Nearly 1 in 5 U.S. children lives with a mental, behavioral or emotional health disorder, yet the number of pediatric mental health specialists has not kept pace with demand. Smartwatch technology represents one possible way to extend support into the home by helping families recognize early changes in a child's stress levels. 

Across a shared wall 

The technology behind the alerts emerged from an unexpected spark. 

Electrical and computer engineer Arjun Athreya, Ph.D., worked just steps from the Children's Hospital Psychiatry Unit at Mayo Clinic — a single shared wall separating his world of algorithms and data from the clinical rooms where children and their families experienced some of their hardest moments.  

Passing conversations with the psychiatrists next door became more formal collaborations as the team began to ask: What happens inside a child's body in the minutes before an outburst? And could those invisible shifts be measured? 

With support from Julia Shekunov, M.D., Medical Director of the inpatient unit, and help from the nursing staff, the team launched a small pilot to explore those questions. 
 
From that work, Dr. Athreya and his team developed an AI model designed to recognize the earliest physiological changes that precede escalating behavior. That work became the foundation for the smartwatch system now being explored with families. 

A family's early role in the research 

One of the first families to try out the smartwatch system was Sawra and Matthew Maurer and their son, Theo.  

For the Maurers, the challenges with Theo were mounting. Calls from kindergarten had become a near-weekly routine: "Theo is having a hard time. Could you come get him?" Around that same time, Theo was diagnosed with ADHD, which helped explain the emotional dysregulation and sudden behavioral shifts they were seeing.  

Theo could slide from being engaged in an activity to overwhelmed in an instant — sweeping crayons off tables or having severe tantrums that sometimes required teachers to guide classmates out of the room. "It was a very difficult year," Sawra recalls. 

Enrolling in the early smartwatch feasibility study gave her new insight.  

During the study, Theo wore a watch each day that collected his physiological data — heart rate, movement, sleep patterns — while the family logged episodes in an AI-powered app. 

That data helped researchers understand what Theo's body was doing in the moments before he became dysregulated. By matching those physiological signals with what was happening behaviorally, the team could begin identifying the subtle shifts that happen as a child moves from calm toward distress and then back to calm. 

Theo's data helped teach the system what those early changes look like in real-world settings. 

Sawra didn't receive alerts in that early phase, but she could see the information the watch recorded. "The idea is wonderful," she says. "Being able to detect when a child is heading toward a severe tantrum would be a phenomenal thing for a parent." 

Moving the research forward

Future studies will focus on improving the model, testing the system in larger groups and examining how real-time physiological data can inform care outside the clinic. As that work continues, the experiences of families like the Staals and the Maurers will help guide how the technology evolves and how it can support children in everyday life. 

Related article

Mayo Clinic smartwatch system helps parents shorten, defuse children’s severe tantrums early

Mayo Clinic researchers have developed a smartwatch-based alert system that signals parents at the earliest signs of a tantrum in children with emotional and behavioral disorders — prompting them to intervene before it intensifies. Read more.

The post Families at Mayo Clinic explore how a smartwatch can give early warnings of severe tantrums  appeared first on Mayo Clinic News Network.

PHOENIX — Mayo Clinic researchers have developed and evaluated MedEduChat, an electronic health record (EHR) that works with a large language model to provide accurate, patient-specific prostate cancer education.  

The findings are published in Nature Portfolio Digital Medicine and highlight a new approach to delivering timely, individualized guidance for people navigating a prostate cancer diagnosis.  

Cancer patients often face uncertainty as they process complex information about their diagnosis and treatment options. Limited time with clinicians can make it difficult for patients to receive the detailed answers they need to understand decisions that shape their care.  

This MedEduChat study demonstrates how advanced AI, grounded in Mayo-validated clinical data, can help bridge these gaps by delivering clear, conversational explanations based on each patient's own health record.  

Understanding the patient experience using AI 

Fifteen prostate cancer patients interacted with MedEduChat for 20 to 30 minutes as part of a mixed-method usability study conducted at Mayo Clinic campuses in Arizona and Minnesota. 

Patients reported higher confidence after using the tool, with Health Confidence Scores increasing from 9.9 to 13.9 on a 16-point scale. Usability scores were also high; average survey responses ranked MedEduChat 83.7 out of 100.  

Patients noted that MedEduChat helped them understand their diagnosis in a more accessible way. The tool provided relief by explaining unfamiliar or complex terms in a clear and concise manner.  

The conversational format helped participants replace incorrect assumptions with medically accurate information derived from their own EHR.  

Clinician-evaluated accuracy and safety 

Wei Liu, Ph.D., a radiation oncology medical physicist, and three Mayo Clinic clinicians independently reviewed 85 anonymized question-and-response pairs. They rated MedEduChat's answers as highly correct (2.9 out of 3), complete (2.7 out of 3) and safe (2.7 out of 3). 

Clinicians also noted strong patient-readiness and moderate personalization, reflecting MedEduChat's ability to tailor explanations to each person's age, treatment history and cancer stage.  

Although MedEduChat delivered accurate and clinically aligned information, clinicians emphasized the importance of ongoing monitoring to prevent errors that could arise from incomplete or inconsistently documented EHR data.

The research team incorporated a multilayer approach to address these concerns and guide future system enhancements.

Combining patient-centered education with AI 

MedEduChat was designed with a structured educational model that combines closed-domain clinical data, semi-structured guidance and personalized interaction.

Patients can explore diagnosis details, learn about treatment options and side effects, and review lifestyle considerations and follow-up expectations. The tool draws only from validated sources, such as Mayo Clinic materials and National Comprehensive Cancer Network guidelines.

"This research demonstrates how large language models can be safely and effectively integrated into real clinical systems to improve cancer education," according to Dr. Liu. "By combining advanced AI with Mayo Clinic's electronic health records, MedEduChat delivers personalized, accurate and easy-to-understand explanations tailored to each patient's medical history."

Expanding AI cancer research 

The study team plans to translate this work into clinical use across all three Mayo Clinic campuses in Arizona, Florida and Minnesota. Next steps include expanding MedEduChat beyond radiation oncology to additional cancer specialties. These efforts aim to make personalized AI-assisted education a routine part of cancer care.

This research was funded by the National Cancer Institute, the Eric and Wendy Schmidt Fund for AI Research and Innovation, the Fred C. and Katherine B. Andersen Foundation, and The Kemper and Ethel Marley Fund in Cancer Research.

### 

About Mayo Clinic Comprehensive Cancer Center 
Designated as a comprehensive cancer center by the National Cancer Institute, Mayo Clinic Comprehensive Cancer Center is defining the cancer center of the future, focused on delivering the world's most exceptional patient-centered cancer care for everyone. At Mayo Clinic Comprehensive Cancer Center, a culture of innovation and collaboration is driving research breakthroughs in cancer detection, prevention and treatment to change lives.  

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 New Mayo Clinic study advances personalized prostate cancer education with an EHR-integrated AI agent  appeared first on Mayo Clinic News Network.

These discoveries reflect progress across three major innovation efforts at Mayo Clinic. Mayo Clinic clinicians and scientists are working together to develop tools to predict and intercept biological processes before they evolve into disease or progress into complex, hard-to-treat conditions through the Precure initiative. They are advancing new cures for end-organ failure beyond traditional transplantation as part of the Genesis initiative. They are also uniting clinical insight with cutting-edge engineering to deliver novel neurological diagnostics and therapies through the Bioelectronics Neuromodulation Innovation to Cure (BIONIC) initiative. 
 

1. 'Virtual clinical trials' may predict success of heart failure drugs 

Mayo Clinic researchers have created "virtual clinical trials" that advance the discovery of therapies while reducing time, cost and the risk of failed studies by combining advanced computer modeling with real-world patient data as part of the Precure and Genesis initiatives. Through one virtual clinical trial, they have developed a new way to predict whether existing drugs could be repurposed to treat heart failure, one of the world's most pressing health challenges. 

"Clinical trials will always remain essential," says Cui Tao, Ph.D., the Nancy Peretsman and Robert Scully Chair of Artificial Intelligence and Informatics and vice president of Mayo Clinic Platform Informatics. "But this innovation demonstrates how AI can make research more efficient, affordable and broadly accessible. Integrating trial emulation, simulation, synthetic trials and biomedical knowledge modeling opens the door to a new paradigm in translational science." 

2. New discovery may unlock regenerative therapies for lung disease

Mayo Clinic researchers have uncovered the molecular "switch" that directs a small but powerful set of cells that choose whether to repair tissue or fight infection, a discovery that could inform regenerative therapies for chronic lung diseases, which is part of Mayo Clinic's Genesis initiative.
 
"We were surprised to find that these specialized cells cannot do both jobs at once," says Douglas Brownfield, Ph.D., senior author of the study. "Some commit to rebuilding, while others focus on defense. That division of labor is essential — and by uncovering the switch that controls it, we can start thinking about how to restore balance when it breaks down in disease." 

3. Stem cells may offer new hope for end-stage kidney disease treatment

Mayo Clinic researchers found that injecting patients' own stem cells from fat cells into the vein before hemodialysis, a treatment for end-stage kidney disease, often helped prevent inflammation and vein narrowing. This could help millions of people tolerate dialysis longer, extending the time before they require a kidney transplant as part of the Mayo Clinic Genesis initiative. 

"This approach has the potential to improve outcomes for millions of patients with kidney failure, reduce healthcare costs and inform new clinical guidelines for dialysis access management if validated in larger clinical trials," says Sanjay Misra, M.D., a Mayo Clinic interventional radiologist. 

4. Mayo Clinic physicians map patients' brain waves to personalize epilepsy treatment

Using detailed maps of each patient's unique brain wave patterns, Mayo Clinic physicians can now pinpoint where stimulation is most effective, moving beyond the traditional one-size-fits-all approach to epilepsy treatment. This research is part of the BIONIC initiative.

"The long-term goal is to quiet the seizure network, so it is eventually forgotten. Reorganizing the neuronal network could move us beyond controlling seizures to actually curing epilepsy," says Nick Gregg, M.D., a Mayo Clinic neurologist. 

5. New genetic biomarker flags aggressive brain tumors

Mayo Clinic researchers found when meningiomas — the most common type of brain tumor — show activity in a gene called telomerase reverse transcriptase (TERT), it tends to recur more quickly, even if it looks low grade under the microscope. This is part of the Mayo Clinic Precure initiative. 

"High TERT expression is strongly linked to faster disease progression," says Gelareh Zadeh, M.D., Ph.D., a neurosurgeon at Mayo Clinic and senior author of the study. "This makes it a promising new biomarker for identifying patients who may be at greater risk of developing aggressive disease."

6. Mayo Clinic researchers discover the immune system's 'fountain of youth'

Mayo Clinic researchers have found that some older people maintain "immune youth" – a new term coined by Mayo researchers to explain a young immune system in someone over age 60.  
 
"We observed that these patients have very young immune systems despite being in their 60s and 70s. But the price they pay for that is autoimmunity," says Cornelia Weyand, M.D., Ph.D., a Mayo Clinic rheumatologist and clinician-scientist. This is part of the Mayo Clinic Precure initiative.

7. Mayo Clinic tools predict, identify and diagnose Alzheimer's, dementia quicker

Mayo Clinic researchers have developed new tools to estimate a person's risk of developing Alzheimer's disease years before symptoms appear as part of the Precure initiative and to help clinicians identify brain activity patterns linked to nine types of dementia, including Alzheimer's disease, using one scan. They also confirmed the accuracy of an FDA-approved blood test that can be used at outpatient memory clinics to diagnose the disease in patients with a range of cognitive impairment. 

"Every patient who walks into my clinic carries a unique story shaped by the brain's complexity," says David T. Jones, M.D., a Mayo Clinic neurologist. "That complexity drew me to neurology and continues to drive my commitment to clearer answers."

8. Mayo Clinic research improves dense breast cancer screening and early detection

Nearly half of all women in the U.S. have dense breast tissue, which can make detecting breast cancer difficult with a mammogram. Mayo Clinic researchers found that adding another test, called molecular breast imaging, or MBI, to a 3D mammogram, improved the ability to find cancer in dense tissue by more than double. 
 
"Our research focuses on detecting the most lethal cancers, which can include invasive tumors that grow quickly. If these are detected earlier, we likely can save more lives," says Carrie Hruska, Ph.D., a Mayo Clinic professor of medical physics and lead author of the study. 

9. Mayo Clinic researchers find 'sugar coating' cells can protect those typically destroyed in type 1 diabetes

After identifying a sugar molecule that cancer cells use on their surfaces to hide from the immune system, Mayo Clinic researchers have found the same molecule may eventually help in the treatment of type 1 diabetes, once known as juvenile diabetes. 

"A goal would be to provide transplantable cells without the need for immunosuppression," says Virginia Shapiro, Ph.D., a Mayo Clinic immunology researcher. "Though we're still in the early stages, this study may be one step toward improving care."

10. New study calculates autoimmune disease prevalence

Mayo Clinic researchers and collaborators have described — for the first time — the prevalence of autoimmune diseases in the U.S. Their research 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 it 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 DeLisa Fairweather, Ph.D., vice-chair of translational research for the Department of Cardiovascular Medicine at Mayo Clinic in Florida and corresponding author of 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 A Year of Discovery: 10 Mayo Clinic research breakthroughs moving medicine forward  appeared first on Mayo Clinic News Network.

At Mayo Clinic, biomedical engineer Benjamin Brinkmann, Ph.D., is developing tools and technologies that help reveal brain patterns — making epileptic seizures more predictable and, one day, preventable. 

In a neurology lab at Mayo Clinic, Dr. Benjamin Brinkmann studies the brain's electrical rhythms across days, weeks and months — searching for patterns that reveal when seizures are most likely to occur. Working with neuroscientists and clinicians, he combines data from brain waves, vital signs and imaging to develop tools that interpret those signals and help guide patient care. 

Epilepsy is a brain disorder that causes recurring seizures — sudden bursts of electrical activity that can interrupt movement, speech or awareness. About 3.4 million people in the U.S. live with the condition. For many, medication keeps seizures under control. But for those with drug-resistant epilepsy, the episodes can occur without warning — disrupting routines and independence. 

Dr. Brinkmann, a biomedical engineer, has dedicated his career to improving care for people with epilepsy. Working with Mayo Clinic's epilepsy team, he helps identify where seizures begin in the brain — essential information for those whose epilepsy is difficult to control. His long-term goal is to move from forecasting seizures to stopping them before they start. 

A clearer picture of epilepsy, one signal at a time

One example of that work is a study Dr. Brinkmann led with international collaborators. They tested a small implant that sits just under the skin behind the ear, recording brain activity as people go about their day. The device helps provide a more accurate picture than seizure diaries, which can miss or misclassify episodes. Accurate and continuous monitoring helps doctors track seizure patterns and adjust treatment.

Over 15 months, the team collected more than 72,000 hours of brainwave data from people with epilepsy. They recorded 754 seizures — nearly twice as many as were reported in diaries. About half of the study participants wore the device more than 20 hours a day and reported it did not interfere with daily life. The findings suggest that long-term, at-home brain monitoring can uncover seizure patterns missed in short clinic visits. 

Smartwatch uses AI to forecast seizures 

Dr. Brinkmann also led a study on wearable technology — a smartwatch that uses artificial intelligence to help forecast seizures before they happen. 

The watch tracks heart rate, movement, skin conductance and temperature, using machine learning to help clinicians find patterns that may signal a seizure. In findings published in Epilepsia, the team correctly predicted about 75% of seizures, with few false alarms. 

Dr. Brinkmann says the idea is simple: to give people a warning. A few minutes' notice can mean calling a caregiver, sitting down or avoiding a risky activity. In the future, those alerts could even trigger treatments automatically, using medication or gentle brain stimulation when seizure risk is high. 

Building the future of epilepsy care

Together, the implant and smartwatch studies show what's possible when brain activity can be tracked continuously. The research is opening a new window into how seizures develop and helping shape the next generation of neurotechnology at Mayo Clinic. 

Dr. Brinkmann's work contributes to Mayo's BIONIC program — short for Bioelectronics Neuromodulation Innovation to Cure — which unites scientists and clinicians to develop smarter, more responsive technologies and therapeutics for the brain, spine and nervous system. The goal is ambitious: systems that can sense trouble and respond instantly to stop it. 

In Dr. Brinkmann's lab, every signal adds to that future — each one bringing a clearer picture of epilepsy and what care might look like in the years ahead. 

The post Mayo Clinic scientist uses AI, wearables and implants to decode brain rhythms and forecast seizures  appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — At Mayo Clinic, cardiologists Peter Noseworthy, M.D., and John Giudicessi, M.D., Ph.D., are uncovering the earliest signs of a genetic heart condition that often strikes without warning. Their work shows that early detection, and even prevention, may be possible long before symptoms appear. 

The condition, arrhythmogenic right ventricular cardiomyopathy, weakens the molecules that hold heart cells together. As those bonds deteriorate, healthy muscle is replaced with scar tissue and fat, leaving the heart weaker.  

The disease often advances silently. Sometimes the first sign is when a person suddenly collapses during exercise. For many, a diagnosis comes only after the heart is already damaged. Detecting it earlier could spare patients from heart failure, the need for a transplant or sudden death. 

"We spend so much time managing the consequences of this disease — ablations, transplants, repeated hospitalizations. It's a much better paradigm to ask: What can we do to prevent this in the first place?" 

"We spend so much time managing the consequences of this disease — ablations, transplants, repeated hospitalizations," Dr. Noseworthy says. "It's a much better paradigm to ask: What can we do to prevent this in the first place?" 

Leading a new era of heart care 

Dr. Noseworthy leads Mayo Clinic's Division of Heart Rhythm Services, where he cares for patients with heart rhythm disorders and helps guide innovation strategies across the institution. Much of his research centers on using digital tools and artificial intelligence (AI) to detect problems earlier and improve patient care. 

Dr. Giudicessi, a genetic cardiologist, focuses on inherited heart rhythm conditions and how genetic changes influence who develops disease. His work bridges patient care and laboratory research, including first-in-human clinical trials that explore the potential of gene therapy. 

Together, they turned to two powerful data sources: the genetic code that shapes the heart and the electrical signals that guide its rhythm. 

"So much of medicine is reactionary — we wait for something bad to happen. This work is ushering in the tools to push against disease and to identify it early." 

Pinpointing risk in genes and rhythm  

Their search for answers started in Mayo Clinic's new Research Data Atlas, which unites decades of genetic, clinical and biospecimen data. Within it, they identified people carrying disease-causing mutations in PKP2, the gene most often linked to this disease.  

About 1 in 2,000 people carry a mutation in the PKP2 gene, but many never develop the disease. The challenge is knowing who will — and stepping in early enough to change the outcome. That question drives Dr. Giudicessi's work. 

"So much of medicine is reactionary — we wait for something bad to happen," Dr. Giudicessi says. "This work is ushering in the tools to push against disease and to identify it early." 

To spot those early rhythm changes, the team drew on an AI model developed by Mayo Clinic cardiologist Ammar Killu, M.B.B.S., and his team.  

Analyzing electrocardiograms from patients with a PKP2 mutation, the AI helped the researchers identify faint patterns that marked the first signs of disease.  

"This research shows how AI can help us identify really subtle changes that may facilitate earlier diagnosis and then allow us to move beyond individual cases to understand patterns across populations."

"This research shows how AI can help us identify really subtle changes that may facilitate earlier diagnosis and then allow us to move beyond individual cases to understand patterns across populations," Dr. Killu says. "It's a powerful example of how we can scale early detection to reach more patients before disease takes hold." 

Those insights led to a next step. Guided by the AI findings, Dr. Noseworthy and Dr. Giudicessi provided smartwatches to people who were showing early signs of disease. The devices help track daily activity levels — important data, since strenuous exercise can accelerate the disease, while even small adjustments may help slow it. 

The researchers are also exploring gene therapy for PKP2. Still in early testing, the approach may one day restore the missing gene and keep the disease from advancing. 

Building medicine's next chapter 

Their work is part of a larger shift at Mayo Clinic: predicting and preventing disease before it takes hold. That vision drives Precure, an initiative to intercept serious conditions early enough to alter their course. With tools like the Research Data Atlas, investigators can study health patterns across large populations, detect risk sooner and potentially guide people to care before disease advances. 

For Dr. Noseworthy, Dr. Giudicessi and Dr. Killu, the vision is bigger than a single study. They are helping build the infrastructure to move medicine earlier in the course of disease, where illness can be intercepted at scale. 

###

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 use AI and genetics to identify early signs of a rare, life-threatening heart condition appeared first on Mayo Clinic News Network.

ROCHESTER, Minn. — Mayo Clinic researchers have developed an artificial intelligence (AI) algorithm that can identify obstructive sleep apnea (OSA) using the results from an electrocardiogram (ECG) – a common heart test. The innovation could make it faster, cheaper, and easier to spot sleep apnea, particularly in women, who are often underdiagnosed.

A common but underrecognized condition

OSA affects more than 936 million adults ages 30-69 worldwide and poses significant cardiovascular risks. People with OSA experience repeated episodes of upper airway collapse or blockage during sleep. This collapse causes breathing to stop or become shallow repeatedly, which often leads to loud snoring and gasping. Despite its prevalence, it often goes undiagnosed.

"Obstructive sleep apnea or OSA is a highly prevalent disease with important cardiovascular consequences," says Virend Somers, M.D., Ph.D., Alice Sheets Marriott Professor of Cardiovascular Medicine and senior author of the study published in JACC: Advances. "OSA affects the heart to the point where AI algorithms can detect the OSA signature from the ECG, which in essence is a representation of the electrical activity of the heart muscle cells," Dr. Somers adds.

AI model shows strong performance — especially for women

In the study, the researchers used AI algorithms to review the 12-lead electrocardiogram (ECG) test results of 11,299 patients at Mayo Clinic who had undergone the test along with sleep evaluations. More than 7,000 of them had a known diagnosis of OSA, and 4,000 were controls.

"The most surprising finding was the increased visibility on the ECG of OSA in the females compared to the males, even though the OSA severity was less in the females," says Dr. Somers.

"This is relevant since emerging data consistently suggest that females have a greater relative likelihood of suffering the cardiovascular consequences of OSA, even if their OSA may be considered 'milder' by standard diagnostic criteria," he adds.

The test also strongly suggests women may suffer more damage to their heart muscle cells from OSA, Dr. Somers says.

Dr. Somers underscores that this approach may have the potential to evaluate whether a given OSA treatment may be able to reduce a patient's cardiovascular risk.

Review the study for a complete list of authors, disclosures and 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 How Mayo Clinic experts are using AI to better detect sleep apnea, especially in women appeared first on Mayo Clinic News Network.

The needs of patients are at the forefront of healthcare transformation through artificial intelligence (AI). This was the overarching theme at Mayo Clinic's AI Summit, held recently in Rochester, Minnesota.  

Dr. Cui Tao, chair of Mayo Clinic's Department of Artificial Intelligence and Informatics and the Nancy Peretsman and Robert Scully Chair of AI and Informatics, opened the summit by sharing that the goal of the event was to explore how AI can be used to potentially revolutionize healthcare and biomedicine.  

The summit, which brought together clinicians, scientists, engineers and innovators, was chaired by Dr. Hamid Tizhoosh and Dr. Fred Fan, both from the Department of Artificial Intelligence and Informatics. 

These were some key takeaways from the event:  

Patient needs drive AI innovation 

Dr. Clark Otley, chief medical officer of Mayo Clinic Platform, emphasized that Mayo Clinic's leadership in AI is rooted in its responsibility to best serve the needs of patients. He said patients want to see improved, accessible, personalized and affordable care, along with trusted information and privacy protection.  

Dr. Matthew Callstrom, medical director of Mayo Clinic's Generative Artificial Intelligence Program, added, "When you start talking to patients about how important AI will be for their healthcare, they start to raise their hand and say, 'Please include me. I want to have the best possible outcomes.'" 

Transforming medicine from reactive to proactive care 

Summit speakers highlighted the need for a shift from reactive, symptom-based healthcare to proactive, preemptive care.  

Dr. Callstrom shared the story of a patient with rheumatoid arthritis whose disease had progressed to joint destruction and chronic symptoms, due to the need to trial different treatments with the current standard of care. He said AI may have the potential to improve outcomes for such patients.  

"If we use the data in a different way — if we start to be able to predict outcomes for patients for methotrexate, for targeted therapies — maybe we can get onto the right therapy sooner," he said.  

Mayo Clinic Platform: A foundation for innovation 

Mayo Clinic Platform, a key initiative in Mayo's Bold. Forward. strategy, is building a rich dataset of de-identified patient data to drive innovation that will help realize this vision. 

Dr. Otley outlined Mayo Clinic Platform's strategy for responsible AI implementation, including ethical development and deployment, human-centered design, and scientific evidence. He highlighted the importance of supporting healthcare teams in using AI to augment patient care.  

AI applications across specialties offer practical solutions 

Dr. Otley shared AI's promise in specialties such as radiology, mammography, personalized medicine and mental health, emphasizing its potential to help healthcare professionals improve diagnostic accuracy, efficiency and access to care.  

Dr. Callstrom highlighted AI-powered tools for reducing administrative burden by streamlining medical records review and clinical decision-making, improving diagnostic accuracy through voice analysis and digital pathology, and ongoing research in genomics and cancer care.  

He emphasized the need for practical solutions that help healthcare professionals, such as an application that can remotely monitor patients and alert their care team to assist and prevent patient falls if necessary. 

Other featured speakers were Dr. Jeroen van der Laak, Radboud University Medical Center; Dr. Yifan Peng, Weill Cornell Medicine; and Dr. Greg Corrado, Google Research.   

Watch the AI Summit keynotes and panel discussions. 

Related post:

• Advancing AI in healthcare: Highlights from Mayo Clinic's 2024 AI Summit 

The post AI Summit highlights patient-centric approach to transform healthcare  appeared first on Mayo Clinic News Network.