The new AI system can predict very accurately premature deaths

Researchers at the University of Nottingham have developed an artificial intelligence system to accurately predict premature deaths among study participants. According to a university announcement, this system performs better than predictions based on an approach developed by human experts, ultimately proving "very accurate" in its evaluations.

The use of machine learning to predict the risk of premature death of a patient can help improve preventive health care in the future. The system uses risk prediction models that examine a variety of information, including lifestyle factors, biometric data, demographics, and so on.

Many factors could affect the risk of premature death predicted by a given individual, including things apparently as small as the amount of meat, fruit and vegetables consumed per day. Experts used health data from more than half a million people in the United Kingdom aged 40 to 69 between 2006 and 2010. Monitoring data was collected until 2016.

AI predictions were compared to information from the UK cancer registry, death registries, and "hospital episode" statistics to determine their accuracy. Human experts have already developed their own standard prediction models to estimate whether a person is at risk of premature death, but the algorithms proved to be more accurate during the study.

Dr. Stephen Weng, Project Leader, stated the following:

We have taken a big step forward in this area by developing a unique and holistic approach to predicting the risk of premature death of a person through machine learning. This uses computers to build new risk prediction models that take into account a wide range of demographic, biometric, clinical, and lifestyle factors for every person badessed, even their dietary intake of fruits, vegetables, and meat by day.