Free app claims to predict end of life based on current levels of physical activity
Predicting death has long been a fascination for mankind, and now a new app promises to narrow the end of your life down to the nearest 36.5 days.
Experts in Russia designed a free app dubbed Gero, which uses Artificial Intelligence (AI) to analyse activity data from your phone accelerometer to estimate your lifespan within a tenth of a year.
When combined with information recorded by wearable fitness monitors, this prediction becomes even more precise.
The estimate will even be revised downwards if you don’t keep up with your healthy living routines, hopefully adding an incentive to stick to them.
The app is the work of researchers at the Moscow Institute of Physics and Technology.
The full findings of the study were published in the journal Scientific Reports.
They analysed physical activity records and clinical data from the 2003 to 2006 United States (US) National Health and Nutrition Examination Survey (NHANES).
A neural network was then trained with the results to predict the biological age and mortality risk of volunteers using a week-long stream of activity measurements.
The recent introduction of affordable fitness wearables means individuals now have access to their own measurements.
This tracking is already done without interfering with the daily routines of hundreds of millions of people all over the world.
Using the AI’s knowledge from NHANES, the app is able to analyse activity data from such wearables or a smatphone’s built-in accelerometer.
In a written statement, Dr. Peter Fedichev, said: “Artificial intelligence is a powerful tool in pattern recognition and has demonstrated outstanding performance in visual object identification, speech recognition and other fields.
“Inspired by these examples, we explored AI potential for Health Risks Assessment based on human physical activity.
“Life and health insurance programs have already begun to provide discounts to their users based on physical activity monitored by fitness wristbands. We report that AI can be used to further refine the risks models.”