AI death prediction tool claims remarkable accuracy

Researchers at the Technical University of Denmark (DTU) have developed an AI-based death predictor, which claims to have high accuracy in predicting the life span of individuals. The AI Life2vec system, tailored to ChatGPT, uses personal information such as health, education, occupation and income for its predictions. Using population data from Denmark, the model refines its accuracy. Analyzing health and labor market data involving 6 million people from 2008 to 2020, the death predictor achieves a 78 percent accuracy rate.
Sune Lehmann, lead author of the December 2023 study, said, “We are using the technology behind ChatGPT (known as the Transformer Model) to analyze human lives by representing each person as a sequence of events occurring in their lives. Let’s use.” Predict human life,” told the New York Post.

“We use the fact that, in a certain sense, human life shares similarities with language,” Mr. Lehmann explained. “Just as words follow each other in sentences, similarly events in human life follow each other.”

“Mortality prediction is a frequently used task within statistical modeling that is closely related to other health prediction tasks and therefore requires the ability to successfully model the progression of individual health sequences as well as labor history to predict the correct outcome. life2vec is required,” the authors of the study wrote.

Unlike ChatGPT, which focuses on producing creative text or overcoming professional obstacles, Life2vec takes a different approach. This AI explores the personal history of individuals, analyzing details such as health, education, career and income. Through this intensive testing, Life2vec aims not only to predict career success or fashion choices, but to predict something much more profound: the outcome of a person’s life. It’s like holding the past in a mirror and trying to glimpse the future reflected in it.