BUSINESS

The AI-Powered Death Prediction Tool Promises Amazing Accuracy. Understand the Specifics

An AI-based death predictor has been created by researchers at the Technical University of Denmark (DTU), and it is said to have a high degree of accuracy in predicting people’s lifespans. The AI Life2vec system, which is based on ChatGPT, makes predictions using individual data such as income, employment, education, and health.

By including demographic data from Denmark, the model improves its accuracy. The death predictor attains a 78 percent accuracy rate via the analysis of 6 million individuals’ health and labor market data from 2008 to 2020.
As stated by lead author Sune Lehmann in the December 2023 study “Using a sequence of life events to predict human lives,” “We use the technology behind ChatGPT (something called transformer models) to analyze human lives by representing each person as the sequence of events that happen in their life,” to The New York Post.

“We use the fact that, in a certain sense, human lives share a similarity with language,” said Lehmann. “Just like words follow each other in sentences, events follow each other in human lives.”
“Mortality prediction is an often-used task within statistical modeling that is closely related to other health prediction tasks and therefore requires life2vec to model the progression of individual health sequences as well as labor history to predict the correct outcome successfully,” the study’s authors wrote.

Life2vec adopts a different strategy than ChatGPT, which focuses on writing imaginative language or overcoming obstacles in the workplace. This AI explores people’s personal histories, examining information about their income, profession, education, and health. With this in-depth analysis, Life2vec hopes to forecast something far more significant than fashion choices or professional success: a person’s life’s ultimate result. It’s similar to trying to get a glimpse of the future reflected in a mirror held to the past.

Related Articles

Back to top button