A recent study unveiled the unprecedented skill of a ChatGPT-like artificial intelligence model trained with life stories of over a million people has predicted highly accurate lives of individuals as well as the risk of their early death.

The scientist from Denmark Technical University (DTU) believes that the AI model was trained on the personal data of over a million people in Denmark. So far It had predicted the chances of death of people more accurately than any existing system.

Data including the individuals’ education, their visits to doctors and hospitals, resulting diagnoses, income, and occupation, of six million people collected from the health and labour market from 2008 to 2020 was analyzed by the researchers converted into words to train a large language model dubbed “life2vec”, it is the similar technology behind apps like ChatGPT.

According to a study published in the journal Nature Computational Science on Tuesday, the AI model could beat other sophisticated systems and predict outcomes like personality and time of death with high accuracy once it learned the patterns in the data.

Researchers asked the AI system to forecast who would live and who would die based on data on a group of individuals from the set who were between the ages of 35 and 65, half of whom passed away between 2016 and 2020.

They discovered that its forecasts were 11% more accurate than those of any other AI model in use or the technique life insurance firms employ to determine policy prices.

Study first author 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?”

He added that they found the existing did not predict so much but the aspect of data that enabled the model to provide such precise answers.

“Our framework allows researchers to identify new potential mechanisms that impact life outcomes and associated possibilities for personalized interventions,” researchers wrote in the study.