Saturday, 23 December 2023 04:33

Scientists create AI system that can predict when you die with startling accuracy

Rate this item
(0 votes)

An artificial intelligence model developed by an international team of researchers has demonstrated the ability to predict future events in people’s lives, including the time of their death.

Life2vec, a so-called transformer model trained on a massive volume of data to predict various aspects of a person’s life, was created by scientists in Denmark and the United States. After being fed data from Danish health and demographic records for six million people, like time of birth, schooling, education, salary, housing, and health, the AI model was trained to predict what would come next. According to its creators, Life2vec demonstrated an eerie ability to predict when people would die based on data analysis. For example, when tested on a group of people between the ages of 35 and 65, half of whom died between 2016 and 2020, it was able to predict who would die and who would live, with 78% accuracy.

The research team led by Sune Lehmann Jørgensen at the Technical University of Denmark pointed out that Life2vec was trained exclusively on data from Denmark, so the results may not be quite the same for people in other countries. However, Jørgensen also stressed that models like this one should not fall into the hands of corporations, although they are probably using such technology on us.

“Clearly, our model should not be used by an insurance company, because the whole idea of insurance is that, by sharing the lack of knowledge of who is going to be the unlucky person struck by some incident, or death, or losing your backpack, we can kind of share this burden,” Jørgensen said.

Life2vec is currently not available for use by the public, but its creators suspect that similar models have already been developed and are being used by big tech companies with massive amounts of data to train them on.

Despite the ethical implications of using an AI model capable of estimating how much you have to live with startling accuracy, there is one undeniable upside – such a prediction can help you prevent your untimely death.

“Our framework allows researchers to discover potential mechanisms that impact life outcomes as well as the associated possibilities for personalized interventions, the team behind Life2vec wrote.

 

Oddity Central

June 09, 2025

Nigerian energy firm achieves 200,000 barrels daily output after Shell acquisition

Renaissance Africa Energy Company Limited (RAEC) announced it has successfully increased crude oil production beyond…
June 09, 2025

Northern leaders criticize Tinubu for focusing on 2027 re-election instead of national challenges

The Arewa Consultative Forum (ACF) has criticized President Bola Tinubu and the ruling All Progressives…
June 09, 2025

The two kinds of people in the world - and why it matters for leadership

Robert E. Siegel One provocative assertion I often make when teaching is that there are…
June 07, 2025

‘Nigerians are marrying all our daughters’, Kenya’s President Ruto, cries out

Kenyan President William Ruto has stirred up a storm on social media with his provocative…
June 06, 2025

Gunmen kill two policemen, abduct Chinese in Kwara

The Kwara State Police Command on Thursday confirmed the killing of two policemen and the…
June 09, 2025

Here’s the latest as Israel-Hamas war enters Day 612

Israel reveals tunnel under Gaza hospital, says body of Sinwar's brother found there The Israeli…
June 08, 2025

Let God back into the lab: Why science without God is failing us

David Rives In recent decades, a subtle and sinister revolution has occurred in our scientific…
May 13, 2025

Nigeria's Flying Eagles qualify for World Cup after dramatic win over Senegal

Nigeria's U-20 national football team, the Flying Eagles, have secured their place at the 2025…

NEWSSCROLL TEAM: 'Sina Kawonise: Publisher/Editor-in-Chief; Afolabi Ajibola: IT Manager;
Contact Us: [email protected] Tel/WhatsApp: +234 811 395 4049

Copyright © 2015 - 2025 NewsScroll. All rights reserved.