Researchers with the University of Nottingham have developed an artificial intelligence system that accurately predicted premature death in study participants. According to an announcement from the university, this system offered better performance than predictions made based on an approach developed by human experts, ultimately proving ‘very accurate’ in its assessments.
The use of machine learning to predict a patient’s risk of premature death may help improve preventative health care in the future. The system utilizes risk prediction models that look at a variety of information, including the person’s lifestyle factors, biometrics, demographics, and more.
Many factors could influence any given individual’s predicted risk of premature death, including things as seemingly small as the quantity of meat, fruit, and vegetables eaten per day. The experts used the health data of more than half a million people in the UK who were between the ages of 40 and 69 in the years 2006 to 2010. Follow-up data was gathered until 2016.
Predictions by the AI were compared against information from the UK cancer registry, death records, and statistics on ‘hospital episodes’ to determine its accuracy. Human experts already have developed their own standard prediction models for estimating whether someone is at risk of premature death, but the algorithms proved more accurate during the study.
Talking about the work was project lead Dr. Stephen Weng, who said:
We have taken a major step forward in this field by developing a unique and holistic approach to predicting a person’s risk of premature death by 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 each individual assessed, even their dietary consumption of fruit, vegetables and meat per day.