New York City-based Icahn School of Medicine at Mount Sinai has developed a machine learning model to estimate disease risk from rare genetic variants using routine clinical data.
The model was trained on more than 1 million EHRs to quantify risk for 10 common diseases, according to an Aug. 28 news release. Researchers applied it to people with rare DNA mutations and generated a 0-to-1 score reflecting how likely an individual is to develop a specific disease, where a score closer to 1 indicates a greater likelihood.
Mount Sinai researchers analyzed more than 1,600 variants and found that some previously labeled “uncertain” were tied to clear disease patterns, while others believed to be high-risk showed little impact in real-world data.
The team said the tool is not meant to replace clinical judgment, but could help guide screening decisions or reduce unnecessary intervention when genetic test results are ambiguous.
