Study Shows Early Death can be Predicted Using AI

Alicia Farmer
April 1, 2019

"We mapped the resulting predictions to mortality data from the cohort using Office of National Statistics death records, the United Kingdom cancer registry, and "hospital episodes" statistics", explains the study's lead investigator.

A team of scientists and doctors at the University of Nottingham in the United Kingdom developed and tested an AI system that continually crunches data about a large pool of middle-aged people to predict someone's risk of dying early because of chronic disease.

To evaluate likelihood of mortality two types of AI were tested: 1) deep learning in which layered information processing networks help the computer to learn for examples; and 2) random forest which is a simpler type of AI that combines tree like models to consider possible outcomes.

Researchers at the University of Nottingham in the United Kingdom used health data from over half a million people aged between 40 and 69 for the study.

Dodgers romp with Opening Day-record 8 home runs
After doubling and scoring in the first inning, he hit one of Greinke's curveballs 420 feet to straightaway center in the second. Seager was back in the Dodgers' lineup for the first time since missing almost all of last season due to Tommy John surgery.

Canadians Felix Auger-Aliassime, Denis Shapovalov done at Miami Open
After reaching the third Masters 1000 semifinal of his burgeoning career, Shapovalov draws the legendary Roger Federer on Friday. Start in Monte Carlo and - yeah, obviously my goals and my expectations, maybe not my expectations, but I'm aiming high.

'You are Titanic - you will sink,' protesters shout as million march
Algerian shouts as he holds the national flag during a protest in Algiers, Algeria, Friday, March 15. The powerful military has stayed in the barracks throughout the unrest.

The predictions of early death made by the AI algorithm were "significantly more accurate" than the predictions delivered by a model that did not use machine learning, said study's lead author Stephen Weng. 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.

'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.

"Preventative healthcare is a growing priority in the fight against serious diseases so we have been working for a number of years to improve the accuracy of computerised health risk assessment in the general population", said Weng.

It appears as if with careful tuning AI deep learning algorithms can be used to predict a range of outcomes. However, the techniques can be hard to use and new to a number of health research professionals. Using artificial intelligence in this manner may be unfamiliar to many in the healthcare field, methods such as those used in this study may help with scientific verification and future development of this field, explains Professor Joe Kai. However, it tends to over-predict risk.

Other reports by

Discuss This Article

FOLLOW OUR NEWSPAPER