Click to Skip Ad
Closing in...
  1. Prime Day Deals 2021
    04:05 Deals

    Prime Day deals 2021: See hundreds of Amazon’s best deals right here

  2. Amazon Dash Smart Shelf
    15:16 Deals

    I’m obsessed with this Amazon gadget you’ve never heard of – and it&#821…

  3. Best Prime Day Deals 2021
    13:41 Deals

    Prime Day secrets: All of Amazon’s deepest discounts are on this one hidden page

  4. Prime Day Nintendo Switch Deals
    12:27 Deals

    Anyone with a Nintendo Switch needs to see this one Prime Day deal

  5. Amazon Deals
    07:59 Deals

    10 deals you don’t want to miss on Sunday: Free $25 Amazon credit, $230 Windows 10 l…




Scientists created an AI that can predict when a person will die

March 29th, 2019 at 10:05 PM
ai predicts death

Fears of an AI-controlled robot takeover aside, artificial intelligence has provided mankind with an incredible opportunity to leverage incredible computational power for use in a variety of ways, including things like cancer detection. But can a computer tell us when we’re likely to meet an untimely end?

Researchers from the University of Nottingham decided to find out, and what they discovered was that a machine learning system isn’t merely as good at predicting and individual’s chances of mortality as it is with illnesses, it’s actually better. The system, which digested the data of over 500,000 people, was able to guess which individuals would perish better than the models developed by human doctors.

The algorithm used in the study had to crunch an incredible amount of information, including the lifestyle differences and dietary habits of a massive chunk of the UK population.

“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,” Dr. Stephen Weng, lead author of the work, said in a statement. “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.”

The research team used data from the UK Biobank for over half a million people between the ages of 40 and 69. The data was collected between 2006 and 2016, and the algorithm was then tasked with predicting mortality rates of the group.

“We mapped the resulting predictions to mortality data from the cohort, using Office of National Statistics death records, the UK cancer registry and ‘hospital episodes’ statistics,” Weng says. “We found machine learned algorithms were significantly more accurate in predicting death than the standard prediction models developed by a human expert.”

The study, while impressive, is just one step in a larger effort to build machine learning systems capable of offering customized health outlooks for individuals. At some point in the not-so-distant future, computers may tell each of us what ailments pose the most danger, and how to beat them.

Mike Wehner has reported on technology and video games for the past decade, covering breaking news and trends in VR, wearables, smartphones, and future tech.

Most recently, Mike served as Tech Editor at The Daily Dot, and has been featured in USA Today, Time.com, and countless other web and print outlets. His love of reporting is second only to his gaming addiction.




Popular News