A new study from Mount Sinai School of Medicine has taken to AI to predict the likelihood of rare genetic mutations that cause disease. They have created a machine that can assign a ‘penetrance score’ to genetic variants that foresee the probability of a mutation inside the genome that can lead to disease.
The AI machinery was programed by using data from over 1 million health records that contained information on common diseases and everyday lab tests. This allowed the model to assess the real-world impact of genetic variants, providing a ‘spectrum of risk’ rather than a 100% yes or 100% no determination of the mutation. According to the MSSM the models scores offer a more accurate prediction of disease risks associated with specific genetic variant. It can qualitatively and quantitatively assess the likelihood of premature disease and health care workers can provide patients with a preventative outlook on their health and make patients aware of any preventative measures necessary to get ahead of any diseases.
Looking in the future with a machine such as this, it expands the knowledge and broadens the range of different outcomes individualized to specific genetic profiles. The MSSM also plans to expand the AI model to broaden its range of disease and genetic variants to help ‘diverse populations’ as well as being a better tool across all the different genetic backgrounds there are in the world. In a world where AI has perhaps become a bad thing, this is what the future needs it for.
No comments:
Post a Comment