Vision beyond time: robot predicts death with 78% accuracy, scientists say

A artificial intelligence is advancing significantly. The novelty is a system that acts as a kind of calculator, capable of predicting the moment of a person’s death. The most surprising aspect is its high degree of precision.

According to the scientists involved, the ‘life2vec’ model can predict a person’s death with 78% accuracy. Everything happens based on an algorithm that uses the person’s life history to predict when death will occur.

The ‘seer’ robot, created by developers from Denmarkworks as a chatbot and feeds on data and information about more than 6 million people.

These data include, for example, income, profession, place of residence, injuries and pregnancy history.

Can AI decipher each person’s remaining lifespan? – Photo: Reproduction

The researchers developed a system that can process simple language, the end result of which is impressive.

It is capable of predicting not only the probability of a person dying early, but the evolution of their personal income throughout their life.

The robot was trained with data from 2008 to 2016. From this, it is able to provide an answer about how long each person will last on Earth. The results caught the attention of those involved in the research.

According to the report published in the magazine Nature Computational Sciencethe bot correctly predicted who had died by 2020 in more than three-quarters of cases.

“We are actively working on ways to share some of the results more openly, but this requires more research to be done in a way that can guarantee the privacy of people in the study,” study author Sune Lehmann explained in an interview with the Daily Mail. .

Personality aspects

Another ability of the bot, according to the networking professor and former student at the Technical University of Denmark, is linked to people’s personalities. He would also be able to predict aspects of individual behavior.

One element that needs to be clear, however, is that the researchers used data from quality of life from Denmark. This suggests that results elsewhere in the world or the degree of accuracy may vary.

The trend towards using digital and robotic tools, which anticipate human issues, has become increasingly present.

Lehmann cites, for example, the use of algorithms to trace profiles and behaviors in social media and, simultaneously, influence people.

“This discussion needs to be part of the democratic conversation so that we can consider where technology is taking us and whether this is a development we want,” says the scientist.