Now AI Calculator That Can Predict Your Death

Predicting the course of one's life and anticipating the inevitability of mortality has long captivated the human imagination. Now, scientists have come up with a technology that has predicted your death.

An AI tool has been developed that leverages the intricacies of an individual's life story to unveil glimpses of their future, demonstrating an impressive accuracy rate of approximately 78 per cent. Distinguishing itself from its counterparts, this technological marvel operates as a conversational companion, resembling a chatbot. By employing existing details, it delicately unveils predictions about what lies ahead. In a recent study, this model, aptly named "life2vec," stands shoulder to shoulder with other counterparts designed to forecast analogous life trajectories.

"We use the technology behind ChatGPT (something called transformer models) to analyze human lives by representing each person as the sequence of events that happens in their life," New York Post quoted Sune Lehmann, lead author of the December 2023 study 'Using sequence of life-events to predict human lives' as saying.

"We use the fact that in a certain sense, human lives share a similarity with language," Lehmann said. "Just like words follow each other in sentences, events follow each other in human lives,"

Diverging from ChatGPT, the buzzworthy bot embraced by tech enthusiasts to secure coveted positions or fashion impeccable ensembles, life2vec distinguishes itself by calculating the future trajectories of individuals through a meticulous analysis of their personal histories. "This model can predict almost anything," Lehmann told The Post, who noted that his research team also used the specialized program to foretell people's personalities and decisions to make international moves.

"We predicted death because it's something people have worked on for many years (for example, insurance companies)," he added, "so we had a good sense of what was possible."

From 2008 to 2020, Lehmann and his team studied a diverse group of 6 million Danish individuals, spanning different genders and age groups. Utilizing life2vec, the researchers employed the tool to identify individuals within the sample who were likely to live for a minimum of four years beyond January 1, 2016. "The scale of our dataset allows us to construct sequence-level representations of individual human life trajectories, which detail how each person moves through time," the report said. "We can observe how individual lives evolve in a space of diverse event types (information about a heart attack is mixed with salary increases or information about moving from an urban to a rural area)."

The researchers inputted AI-specific details for each study participant, employing straightforward language like "In September 2012, Francisco received 20,000 Danish kroner as a guard at a castle in Elsinore" or "During her third year at secondary boarding school, Hermione followed five elective classes."

Subsequently, distinct digital tokens were allocated to each specific piece of information, all meticulously categorized. As examples, a forearm fracture was denoted as S52, working in a tobacco shop was coded as IND4726, income was represented by a set of 100 unique digital tokens, and "postpartum hemorrhage" was abbreviated as O72.

Through the provided data, life2vec accurately predicted the individuals who had passed away by 2020 with an accuracy rate exceeding 75 per cent.