AI algorithm can predict human life events, including death

Artificial intelligence (AI) has come a long way, and new research has shown that it can now predict events in people’s lives.

A recent study proves that AI transformer models, which are used to analyze written language (like ChatGPT) can be trained with extensive datasets about people’s lives to predict what may occur in their future. These models can even estimate the time of death with a high degree of accuracy.

An AI model to predict human lives

In the study, researchers used a life2vec model to analyze information on health status and labor market attachment of 6 million Danes. Once the AI model is trained, it can learn the patterns in the data to predict outcomes such as personality traits and time of death with exceptional precision.

Sune Lehmann, DTU professor and author of the article, believes that the exciting aspect lies in understanding the data that enables the model to provide such precise predictions.

“We used the model to address the fundamental question: to what extent can AI predict events in your future based on conditions and events in your past? Scientifically, what is exciting for us is not so much the prediction itself, but the aspects of data that enable the model to provide such precise answers,” says Lehmann.

Transformer models: A new approach to AI

The predictions from life2vec cover questions such as “death within four years”? Upon analyzing the model’s responses, the results were found to be consistent with existing findings in social sciences.

The AI model places data on various elements such as time of birth, schooling, education, salary, housing, and health in a large system of vectors, a mathematical structure that organizes the data.

Sune Lehmann comments on the revolutionary use of transformer models in AI. He said, “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. This is usually the type of task for which transformer models in AI are used, but in our experiments we use them to analyze what we call life sequences, i.e., events that have happened in human life.”

Implications of AI predictions

While such advanced technologies are indeed impressive, they come with ethical questions about the model’s data protection, privacy, and the role of bias found within the data.

More information and insight into these challenges of AI predictions is necessary to implement such models to assess an individual’s risk of developing a disease or other preventable life events.

Sune Lehmann believes that further discussions are necessary to consider where technology is taking us and whether this is the direction we want.

“The model opens up important positive and negative perspectives to discuss and address politically. Similar technologies for predicting life events and human behavior are already used today inside tech companies that, for example, track our behavior on social networks, profile us accurately, and use these profiles to predict our behavior and influence us. This discussion needs to be part of the democratic conversation.”

According to experts, the next step will be to include different data types like images, text, or information about our social connections. Such advancements in data analytics and artificial intelligence predictions open up a new relationship between social and health sciences, a cornerstone in designing future public health policies and interventions.

The full study was published in the journal Nature Computational Science.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–