The algorithm builds predictors for traits such as height, bone density and even the level of education a person might achieve, purely based on one's genome. Further applications have the potential to dramatically advance the practice of precision health
The research, carried out by a team from Michigan State University, examined the whole genetic makeup of nearly 500,000 adults in the United Kingdom using machine learning.
In confirmation tests, the computer precisely predicted everyone's height within approximately an inch. While bone density and educational accomplishment predictors were not as accurate, they were precise enough to identify outlying individuals who were at risk of having very low bone density related with osteoporosis, or were at risk of struggling in school.
Traditional genetic testing usually looks for a detailed change in a person's genes or chromosomes that can indicate a higher risk for diseases such as breast cancer. This model considers numerous genomic variances and builds a predictor built on the tens of thousands of deviations.