Researchers at the Icahn School of Medicine at Mount Sinai have developed a new method to assess the risk that individuals with rare genetic mutations will develop disease. This approach uses artificial intelligence (AI) and standard laboratory tests, such as cholesterol levels and blood counts, to estimate what is known in genetics as penetrance—the likelihood that a person carrying a mutation will actually experience related health problems.
The study, published in Science on August 28, describes how machine learning models were trained using more than one million electronic health records to predict risk for ten common diseases. The models generate a score between 0 and 1 for each genetic variant, indicating the probability of disease development. The researchers calculated these “ML penetrance” scores for over 1,600 genetic variants.
Ron Do, PhD, senior study author and Charles Bronfman Professor in Personalized Medicine at Icahn School of Medicine at Mount Sinai, said: “We wanted to move beyond black-and-white answers that often leave patients and providers uncertain about what a genetic test result actually means. By using artificial intelligence and real-world lab data, such as cholesterol levels or blood counts that are already part of most medical records, we can now better estimate how likely disease will develop in an individual with a specific genetic variant. It’s a much more nuanced, scalable, and accessible way to support precision medicine, especially when dealing with rare or ambiguous findings.”
The AI models revealed some unexpected results; certain variants previously labeled as “uncertain” showed clear links to disease while others thought to be harmful had little impact according to real-world data.
Lead study author Iain S. Forrest, MD, PhD explained: “While our AI model is not meant to replace clinical judgment, it can potentially serve as an important guide, especially when test results are unclear. Doctors could in the future use the ML penetrance score to decide whether patients should receive earlier screenings or take preventive steps, or to avoid unnecessary worry or intervention if the variant is low-risk. If a patient has a rare variant associated with Lynch syndrome, for instance, and it scores high, that could trigger earlier cancer screening, but if the risk appears low, jumping to conclusions or overtreatment might be avoided.”
The research team plans further work expanding their model across additional diseases and diverse populations while tracking outcomes over time.
Dr. Do added: “Ultimately, our study points to a potential future where AI and routine clinical data work hand in hand to provide more personalized, actionable insights for patients and families navigating genetic test results. Our hope is that this becomes a scalable way to support better decisions, clearer communication, and more confidence in what genetic information really means.”
The paper’s authors include Iain S. Forrest; Ha My T. Vy; Ghislain Rocheleau; Daniel M. Jordan; Ben O. Petrazzini; Girish N. Nadkarni; Judy H. Cho; Mythily Ganapathi; Kuan-Lin Huang; Wendy K. Chung; and Ron Do.
This research received support from several National Institutes of Health grants including those from the National Institute of General Medical Sciences (T32-GM007280), National Institute of Diabetes and Digestive and Kidney Diseases (U24-DK062429), National Human Genome Research Institute (R01-HG010365), among others.
Mount Sinai’s Windreich Department of AI and Human Health is led by Dr. Girish N. Nadkarni and focuses on responsible use of AI in healthcare settings by integrating expertise across disciplines within Mount Sinai Health System (https://ai.mssm.edu). The department collaborates closely with institutions like the Hasso Plattner Institute for Digital Health at Mount Sinai—a partnership between Mount Sinai Health System in New York City and Hasso Plattner Institute for Digital Engineering in Potsdam—which aims to advance patient care through data-driven approaches.
In 2024 the department’s NutriScan application was recognized with the Hearst Health Prize for its use of machine learning technology aimed at improving malnutrition diagnosis rates among hospitalized patients (https://ai.mssm.edu).
The Icahn School of Medicine serves as an academic partner for seven hospitals within Mount Sinai Health System—one of New York City’s largest health networks—and offers education programs along with extensive research initiatives funded by major grants.
