With the help of artificial intelligence, researchers may one day be able to predict from medical records who is more likely to develop Alzheimer’s disease later in life. This may be possible by training certain self-educating programs — also known as machine learning algorithms — to spot risks via electronic health records.
Led by NIA-funded scientists at the University of California, San Francisco, researchers trained computers on the disease diagnosis, blood test results, and other important information stored in the electronic health records of 749 people with Alzheimer’s and 250,545 control individuals.
The study found that the programs were about 70% accurate at predicting Alzheimer’s based solely on electronic health records seven years before a diagnosis. The programs were about 80% accurate at predicting a diagnosis one year in advance.
These findings provide a blueprint for how researchers may use machine learning algorithms and other advanced computer programs to mine clinical and biological data to better understand each person’s risk for Alzheimer’s.
Learn more about how AI can be used to spot signs of Alzheimer’s.
