What’s the obsession around AI death calculator: Is it accurate?

Imagine learning about your own death date on your next visit to a hospital. Sounds scary? Or preparative? Everyone’s having mixed feelings right now. Well, this is not something borrowed from a movie plot, this is actually happening.
Hospitals in the UK are planning to use an

AI death calculator

to tell patients the rough date of their death. The program is called AI-ECG risk estimation or

AIRE

.

Developed by researchers at Imperial College London and Imperial College Healthcare NHS Trust and published in Lancet Digital Health, this detects the death date of an individual.

How does an AI death calculator work?

The AI calculator uses electrocardiogram (ECG) records to “accurately predict which patients went on to experience new disease, worse disease, or who subsequently died.” Researchers say the model can see and understand ECG patterns with more complexity and subtlety than a cardiologist can.

“We cardiologists use our experience and standard guidelines when we look at ECGs, sorting them into ‘normal’ and ‘abnormal’ patterns to help us diagnose disease. However, the AI model detects much more subtle detail, so it can ‘spot’ problems in ECGs that would appear normal to us, and potentially long before the disease develops fully,” Dr Arunashis Sau, an academic clinical lecturer at Imperial College London’s National Heart and Lung Institute, and cardiology specialist registrar at Imperial College Healthcare NHS Trust, who also led the research said in an official statement.

The AI death calculator or AIRE was able to correctly identify the risk of death in the ten years following the ECG (from high to low) in 78% of cases. “The system can predict future health risks such as heart rhythm problems, heart attacks and heart failure, as well as when someone would die from a non-heart related cause. The researchers found it could predict these risks with a high level of accuracy,” the researchers have said.

Are AI death calculators reliable?

AI death calculators, which estimate life expectancy based on data inputs like age, lifestyle, health conditions, and demographics, are not entirely reliable. These calculators use algorithms trained on historical data to provide an estimate of how long a person might live. However, they have significant limitations. Life expectancy is influenced by numerous unpredictable factors such as accidents, sudden illnesses, and changes in medical care that AI cannot foresee. Additionally, the accuracy of these predictions depends on the quality and comprehensiveness of the data the AI is trained on.
While AI death calculators may offer a rough estimate or provide insights into health risks, they cannot account for individual variations or future advancements in medicine and technology that could extend life. Moreover, these calculators often overlook emotional, psychological, and social factors, which also play a role in longevity.

AI death calculators should be used with caution and as a general guide rather than an absolute prediction. They can be useful for highlighting health trends or encouraging healthier lifestyles, but they lack the precision to be considered truly reliable for individual life expectancy predictions.