Aside from the fear of AI-controlled robot adoption, artificial intelligence has given humanity an incredible opportunity to leverage incredible computing power for a variety of uses, including cancer detection. But can a computer tell us when it's likely to end untimely?
Researchers from the University of Nottingham decided to find it out, and it turned out that a machine learning system is not only well predictable. The mortality chances of an individual as in disease are actually better. The system, which digested the data of over 500,000 people, was able to guess which individuals would die better than the models developed by physicians.
The algorithm used in the study had to penetrate an incredible amount of information including lifestyle differences and eating habits of a large part of the British population.
"We have taken a big step forward in this area by developing a unique and holistic approach to predict the risk of premature death of a person through machine learning." Stephen Weng, lead author of the work, said in a statement. "Computers are being used to create new risk prediction models that address a variety of demographic, biometric, clinical and lifestyle factors for each individual, even the dietary intake of fruits, vegetables and meat per day."
The research The team used UK biobank data for over half a million people between the ages of 40 and 69 years. The data was collected between 2006 and 201
The resulting predictions on cohort mortality data, using Office of National Statistics death records, the UK Cancer Registry, and statistics on "hospital episodes," says Weng. "We've found that machine-learned algorithms are used in the Predicting death were significantly more accurate than the standard predictive models developed by a human expert. "
While impressive, the study is only one step toward greater efforts to develop machine learning systems that can offer individual health prospects to individuals At some point in the not-too-distant future, computers can tell each of us which complaints represent the greatest danger and how to defeat them.