New York, NY [August 28, 2025]—In a groundbreaking development, researchers at the Icahn School of Medicine at Mount Sinai have unveiled a novel approach to predicting genetic disease risk. By leveraging artificial intelligence (AI) and routine lab tests, the team aims to shed light on the often ambiguous results of genetic testing. This innovative method, detailed in the latest issue of Science, marks a significant step forward in the field of personalized medicine.
Traditional genetic studies have long struggled with the concept of penetrance, which refers to the likelihood that a person with a genetic mutation will actually develop the associated disease. The Mount Sinai researchers have addressed this challenge by combining machine learning with electronic health records, offering a more nuanced understanding of genetic risk. The new method moves beyond the binary yes/no diagnosis, which often fails to capture the complexity of diseases such as cancer, diabetes, or high blood pressure.
AI and Lab Tests: A New Frontier in Genetic Risk Assessment
The study’s senior author, Dr. Ron Do, emphasizes the importance of moving past simplistic genetic test interpretations. “We wanted to move beyond black-and-white answers that often leave patients and providers uncertain about what a genetic test result actually means,” he explains. By utilizing AI and real-world lab data, such as cholesterol levels and blood counts, the team can now better estimate the likelihood of disease development in individuals with specific genetic variants.
Using over one million electronic health records, the researchers developed AI models for ten common diseases. These models were then applied to individuals with rare genetic variants, generating a “ML penetrance” score between 0 and 1. A higher score indicates a greater likelihood of disease, while a lower score suggests minimal risk.
Implications for Clinical Practice
The potential impact of this research on clinical practice is profound. Dr. Iain S. Forrest, the study’s lead author, notes that while the AI model is not intended to replace clinical judgment, it can serve as a valuable guide. “Doctors could in the future use the ML penetrance score to decide whether patients should receive earlier screenings or take preventive steps,” he says. This approach could help avoid unnecessary interventions for low-risk variants, while ensuring timely action for high-risk cases.
For example, if a patient has a rare variant associated with Lynch syndrome and scores high on the ML penetrance scale, it could trigger earlier cancer screenings. Conversely, a low score might prevent premature conclusions and overtreatment.
Future Directions and Broader Applications
The Mount Sinai team is already looking ahead, aiming to expand their model to encompass more diseases, a broader range of genetic changes, and more diverse populations. They also plan to monitor the long-term accuracy of their predictions, assessing whether individuals with high-risk variants indeed develop the predicted diseases, and whether early interventions make a difference.
“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,” says Dr. Do. The hope is that this approach will become a scalable solution, enhancing decision-making, communication, and confidence in genetic information.
Support and Collaboration
The research was a collaborative effort involving several experts, including Iain S. Forrest, Ha My T. Vy, Ghislain Rocheleau, and others. The work received support from various grants, including those from the National Institutes of Health (NIH) and the National Institute of Diabetes and Digestive and Kidney Diseases.
This breakthrough represents a significant advancement in the field of precision medicine, offering a more refined tool for understanding genetic risks. As the researchers continue to refine and expand their models, the potential for AI to transform genetic testing and disease prevention grows ever more promising.
