Mayo Clinic is the leading force in efforts to improve the patient experience through artificial intelligence (AI)-supported innovation.
Physicians and researchers across Mayo Clinic are developing and using AI-driven tools that accelerate new knowledge, solutions and technologies. Mayo Clinic is also partnering with other leading institutions worldwide to better leverage resources and advance responsible, effective and trustworthy AI practices.
Discover how AI is making an impact on patient care at Mayo Clinic.
Drug-resistant epilepsy often requires surgery to remove seizure-causing brain tissue.
First, though, patients must typically undergo a different surgery to implant electrodes in their brain, followed by weeks of monitoring neural activity to identify where the seizures are located.
It’s challenging for physicians to accurately detect high-frequency brain waves because of their short duration and low amplitude, as well as environmental noise. Physicians currently use a labor-intensive manual data analysis process to remove unwanted or corrupted data points.
Mayo Clinic researchers have developed new AI tools to more rapidly and accurately pinpoint seizure hot spots in patients with drug-resistant epilepsy. Nuri Ince, Ph.D., a consultant in the Mayo Clinic Department of Neurologic Surgery, is the senior author of the study, which was published in the journal Nature Communications Medicine.
Enhancing the identification process means patients can more quickly undergo targeted tissue removal surgery, which is critical for achieving seizure freedom. Faster identification also reduces the need for prolonged monitoring after electrode implantation, minimizing risks like infection — which is five times more likely to occur in children than in adults during prolonged stays in epilepsy monitoring units.
The group's future work will focus on transforming the framework into a fully digital, real-time system that can interpret the brain waves during electrode implantation surgery and provide feedback to the clinical team regarding the location of the epileptic brain tissue.
To learn more, visit Mayo Clinic News Network.
In early 2025, Mayo Clinic launched Mayo Clinic Digital Pathology, a platform that will accelerate diagnostic speed and accuracy, leading to faster, more personalized treatments and cures.
This new platform involves collaborations with NVIDIA, a world leader in accelerated computing, and Aignostics, an industry leader in building AI models for digital solutions.
Mayo Clinic Digital Pathology takes advantage of unique Mayo Clinic assets:
Mayo Clinic Digital Pathology uses large, diverse datasets to build powerful artificial intelligence models in pathology, which addresses a major challenge in the field: the widespread use of analog processes. This hinders access to critical diagnostic data that could be used to expand diagnostics and treatments and speed the development of new therapies to benefit patients.
The early results of this collaborative, multidisciplinary effort are promising. As of mid-January 2025, Mayo Clinic Digital Pathology has leveraged 20 million digital slide images linked to 10 million patient records that incorporate treatments, medications, imaging, clinical notes, genomic data and more.
To learn more, visit Mayo Clinic News Network.
Two Mayo Clinic Ph.D. candidates, Caroline Grant and Jean Marrero-Polanco, are exploring how AI can provide clinicians with predictive alerts about their patients’ potential response to specific medications in a study published in the journal Clinical and Translational Science.
Grant and Marrero-Polanco, under the mentorship of senior study author Arjun Athreya, Ph.D., a computer scientist in the Mayo Clinic Department of Molecular Pharmacology and Experimental Therapeutics, surveyed 305 clinicians across Mayo Clinic sites in Arizona, Florida and Minnesota, as well as Mayo Clinic Health System, about their communication preferences.
The researchers used AI to process large volumes of survey data and uncover insights that are hard to detect with traditional methods. They found that clinicians generally prefer concise, individualized alerts that use patient-specific genomic data to help personalize their care, rather than more generic or detailed alerts. Concise, individualized alerts are more actionable and less intrusive for clinicians.
The next phase of this research will involve testing these refined alerts in actual clinical settings to determine their effect on clinician burnout and patient outcomes.
To learn more, visit Mayo Clinic News Network.
Bahman and Becky Hoveida believe in a future of healthcare where cancers are diagnosed earlier.
Cancer Care Beyond Walls has made life a lot easier for patients with cancer and their families.
"Oliver's life was a brief gift, but he left a mark deeper than his time with us."