Researchers at the Icahn School of Medicine at Mount Sinai have developed a new AI tool to accurately predict a person’s risk for common hereditary diseases.
Artificial intelligence (AI) tool is specifically designed to predict whether rare genetic mutations will lead to disease and to speed up early detection in real time.
The current genetic testing can identify DNA variants that may be linked to diseases, but these tests often fail to provide a complete picture of a person's health risks.
A simple genetic variant rarely determines the complete picture, as most common diseases like heart and cancer are influenced by a combination of genes and various environmental factors.
A New York research team developed a tool that uses AI and electronic medical records. It contains a patient's comprehensive health history to predict the likelihood that people will develop diseases based on their genetic risks.
The study author and a professor of personalized medicine at the Icahn School of Medicine at Mount Sinai said in an official statement, “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.”
Researchers used a dataset of over one million electronic health records to train an AI model to predict the risk for 10 different inherited diseases including breast cancer and polycystic kidney disease (PKD).
The AI tool analyzes patients with rare genetic variants and assigns them a score between 0 and 1 to determine their chances of developing this disease.
The researchers publish the findings in the journal Science to determine a risk score of more than 16,000 genetic variants.
The model has already provided insights about the health risks associated with certain genetic mutations.
This risk score will help doctors to decide whether patients should undergo additional screenings.
The researchers are fully committed to expanding the model to include more genetic variants and a more diverse group of patients simultaneously.
