I think many of us would rather not know when and how we’ll meet our end.
The constant worry about a looming 'death date' would just add unnecessary stress to our lives, making us question every decision or stop us from ever leaving our homes again.
But for those curious about your future demise, scientists from Denmark have developed a new AI system that can predict an individual's time of death with some scarily good accuracy.
Advert
The new AI system called 'life2vec' has been trained using data from over one million people in Denmark.
Researchers from the Technical University of Denmark (DTU) collected data from six million Danes between the years of 2008 to 2020.
The data included information on educational background, health (including appointments and diagnoses), and occupation.
Advert
After training the model with this extensive data, the AI bot could identify patterns and predict outcomes, including the likelihood of death - and even the time of death.
The AI model used the algorithm to predict whether people aged 35 to 65 on the Danish national registers had died by 2020, achieving an impressive accuracy of 79%.
The study author Dr. Sune Lehman from DTU said: 'We used the model to address the fundamental question: to what extent can we predict events in your future based on conditions and events in your past?'.
Lehman explained that the 'life2vec' machine system utilises technology that's used in ChatGPT, which analyses sequences of words to statistically determine the probability of what comes next.
'This is usually the type of task for which transformer models in AI are used, but in our experiments, we use them to analyse what we call life sequences, i.e., events that have happened in human life,' Dr. Lehman said.
Advert
'What’s exciting is to consider human life as a long sequence of events, similar to how a sentence in a language consists of a series of words.'
The study, published in the journal Nature Computational Science, found that the model's predictions were 11% more accurate than any other existing AI model or the methods used by life insurance companies.
However, Dr. Lehman stressed the ethical risks of such: '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.'