Revolutionary discovery: an algorithm that can predict a person's death

History was “written” by researchers from Denmark.

a Revolutionary technologywhich may constitute the origin of the universe for the human race, researchers at Denmark. Specifically, these are powerful Machine learning algorithmsin order to accurately predict important events in a person's life, including his death.

In the study published in the magazine Computational natural sciencesthe researchers detailed how the model was named Life2vec– Predicting the outcome of a person's life when fed with very specific data about that person.

“With this data, we can make all kinds of predictions,” Mr. Hans stressed. Sonny Lyman, lead author of the study and a professor at the Technical University of Denmark. However, he noted that this is a “research prototype” and cannot perform “real-world tasks” in its current state.

the Researchers Data from the Danish National Register, which included records of 6 million people, were used. They studied data from 2008 to 2016 on important aspects of these individuals' lives, such as education, health, income, and occupation.

Researchers have created vocabulary for life events using language processing techniques so that it is… Life2vec Interpreting sentences based on data. After training them on this data, it was done model He was able to predict certain aspects of people's lives, such as how they would think, how they would feel, how they would act, and whether they would die in the next few years.

To predict how early someone might die, the team used data from 1^the January 2008 reach to 31^the December 2015 To a group of more than 2.3 million people between the ages of 35 and 65. This group was chosen because it is difficult to predict deaths in this age group, according to Lehman.

the Life2vec The data was used to infer a person's probability of being alive four years after 2016. Life2vec“We chose a group of 100,000 people, half of whom survived and the other half died,” Lehman noted.

although Researchers They knew people who died after 2016, but the algorithm didn't. They then asked the algorithm to make individual predictions about whether or not someone lived after 2016. The results were impressive: the algorithm correctly predicted 78% of cases.

the Life2vec It also outperformed other contemporary models by at least 11%, I would expect Greater accuracy Mortality rates according to the study.

Men were more likely to die after 2016, according to the results. some ProfessionsLike engineers, as well as those diagnosed with a mental health problem, such as depression or anxiety, were at risk of early death. In contrast, highly paid managers or executives lived longer.

But the survey had several DeterminantsThe researchers noted. The trials were not randomized, the study duration was relatively short and some people residing in Denmark may not be registered in the national registry. “If someone does not have a salary – or chooses not to use healthcare systems – we cannot access their data,” they stressed.

the Stady It was conducted in a wealthy country with strong infrastructure and a strong health care system, according to the authors. It is not clear whether these results can be applied to other countries given their economic and social differences.

Mr. Lehman indicated that he knew that Mr Algorithm It sounds “ominous and crazy, but it's actually something that's already been worked on, mostly with insurance companies in mind.”