Newly developed artificial intelligence can predict which diseases specific genetic mutations are likely to cause, not just whether they are harmful.[5] Mount Sinai researchers developed AI models for 10 common diseases based on more than 1 million electronic health records.[1] The models use routine laboratory tests such as cholesterol levels, blood rosettes, and kidney function.[1] For more than 1,600 genetic variants, they calculated an "ML penetrance" score from 0 to 1, where a higher score close to 1 indicates a higher risk of the disease.[1] Some variants previously labeled as uncertain showed clear signs of disease, others considered harmful had little effect.[1] The results were published on August 28 in the journal Science.[1] The team plans to extend the model to more diseases, genetic changes and populations.[1] This approach supports precision medicine for rare or ambiguous findings.[1]