Doctors Can Now Predict When You Will Die Based On The Way You Walk?

The UK Biobank project says it's found that a study of humans walking can predict when someone will die within a five-year timeframe.

By Charlene Badasie | Published

Nothing is more certain in life than death. But what if it was possible to know when you will die, based only on the way you walk? A new study says that measurements from wrist-worn motion sensors can be used to estimate a person’s death day up to five years before it happens. The research also raises the possibility of using the system to survey patient health via smart devices without the need for in-person visits to the doctor’s office.

Published in the PLOS Digital Health Journal, the study into when you will die was carried out using data from over 100,000 Britons from the UK Biobank project. The system, which began collecting health and biometric information from participants in 2006, will follow them for 14 years. Using a week’s worth of wrist sensor data, researchers at the University of Illinois at Urbana-Champaign designed a model that pares down a person’s acceleration and the distance they traveled into six-minute chunks.

According to study author Bruce Schatz, the scientists incorporated this timeframe into their research on when you will die, to mimic the six-minute walk test. This is a measurement of heart and lung function commonly taken during a medical appointment that asks patients to walk at a normal pace for six minutes. Their total distance traveled is then compared to benchmarks according to their age.

Speaking to The Daily Beast, Schatz said the test is a very good external measure of what’s going on internally. And could easily be replicated using the accelerometer present in a wrist sensor or a cheap smartphone. “I know for a fact that these kinds of models will work with cheap phones,” he told the publication. Predictions of when you will die made by the model were correct 76% of the time after one year.

Estimating when you will die also gave a 73% accuracy rate after five years, according to a study published last year that analyzed the same data set but used hours instead of minutes as a unit of measurement. But Schatz said the new research is a more promising demonstration of passive monitoring technology like phone and wrist sensors as his model requires less data and offers more privacy to the user.

“If you record all the data, it’s true that people have characteristic walks and you can tell who the individual is,” Schatz explained. But he said it’s also possible to take part of the signal, which is good enough to record vitals and completely disguise the person’s identity. However, using everyday technology to passively predict when you will die could raise issues if users can’t give continuous informed consent.

This could be further complicated by degenerative illnesses or a lack of technological literacy. These ethical issues around knowing when you will die are still speculative, but deserve coordinated thought from scientists as the research moves forward. “If you want to raise the general health of the entire population, this kind of research project is really important,” Schatz told The Daily Beast.