Artificial intelligence can predict death. This is what researchers from Great Britain are currently reporting. But the approach is not without controversy.
When does life end? This question concerns many people and so far no one has been able to give a precise answer. But for many years now, scientists around the world have been researching methods to predict lifespan – with the help of artificial intelligence.
Researchers at Imperial College London have developed an AI-based model that is said to be able to use electrocardiograms (ECGs) to predict with relative precision a person’s health risks. The model, called AIRE (AI-ECG risk estimator), was fed data from over 1.1 million ECGs from almost 190,000 patients.
According to a press release from the university, the AI system should now be able to calculate, among other things, the risk of imminent heart disease, but also when someone would die from a non-heart-related cause – with an accuracy of 78 percent.
“ECGs record a variety of information from throughout the body, because diseases such as diabetes, which affect organs such as the kidneys or liver, also affect the heart in some way,” said the study authors. The analysis therefore shows that AI can tell a lot not only about the heart, but also about what is going on elsewhere in the body, and that it could be able to detect accelerated aging.
The British health authority NHS (National Health Service) is already planning to use the technology in individual clinics from mid-2025. The aim is to identify patients who could benefit from palliative care or preventative treatments. The aim is to be able to assess individual risks faster and better and to intervene in a timely manner.
The use of AI models to predict life events or assess disease risks is being actively discussed in medicine. The researchers also admit that it is definitely a question of ethics to use such sensitive data. Regulations are still needed for this.