New smart watch can measure fitness without exercise

By Gwyn Wright via SWNS

A new way of measuring fitness on smart watches and monitors which doesn’t need you to do any exercise has been developed by Cambridge scientists.

The gadgets, which use machine learning technology, can predict the body’s capacity to do cardiovascular exercise and how vulnerable it is to heart disease and other mortality risks.

They measure VO2max, a “gold standard” measure of overall fitness used by professional athletes, more accurately than conventional smart watches and monitors, the team say.

Existing tests used to measure fitness are mainly used by top athletes because they need expensive lab equipment in order to work.

The new method, developed by University of Cambridge scientists, can measure the body’s capacity for exercise during everyday activity.

They also do not require contextual information such as GPS measurements.

The model was found to be more accurate than lab-based tests.

The team say some smart watches currently on the market claim to measure VO2max but it is unclear whether they are accurate because the algorithms change and are not published.

It is also unclear whether existing smart watches assess the effect an exercise regime has on someone’s VO2max over time.

In contrast, they say their model is robust, transparent and provides accurate predictions based on heart rate and accelerometer data.

Since the model can also detect fitness changes over time, it could also be useful in estimating fitness levels for entire populations and identifying the effects of lifestyle trends.

For the study, the team gathered data on 11,059 people who used wearable sensors and took part in the Fenland Study.

A group of them were tested again seven years later.

The researchers used the data to develop a model that could predict VO2max, which was then validated against a third group who took part in a standard lab exercise test.

Participants wore wearable devices all day and night for six days and sensors gathered 60 data values per second.

The models had to compress a huge amount of data so they could make an accurate prediction.

They used an artificial intelligence model called deep neural network to extract meaningful information from the raw data and accurately predict VO2max based on it.

These models can be used to identify groups of the population who particularly need help to become fitter.

The data was compared with findings on 2,675 of the original participants and a third group of 181 participants from another study did lab-based VO2max tests to measure the accuracy of the algorithm.

Study author Dr. Søren Brage said: “VO2max isn’t the only measurement of fitness, but it’s an important one for endurance, and is a strong predictor of diabetes, heart disease, and other mortality risks.

“However, since most VO2max tests are done on people who are reasonably fit, it’s hard to get measurements from those who are not as fit and might be at risk of cardiovascular disease.”

Lead study author Dr. Dimitris Spathis added: “We wanted to know whether it was possible to accurately predict VO2max using data from a wearable device, so that there would be no need for an exercise test.

“Our central question was whether wearable devices can measure fitness in the wild.

“Most wearables provide metrics like heart rate, steps or sleeping time, which are proxies for health, but aren’t directly linked to health outcomes.”

Brage added: “It’s true in principle that many fitness monitors and smartwatches provide a measurement of VO2max, but it’s very difficult to assess the validity of those claims.

“The models aren’t usually published, and the algorithms can change on a regular basis, making it difficult for people to determine if their fitness has actually improved or if it’s just being estimated by a different algorithm.”

Spathis added: “Everything on your smartwatch related to health and fitness is an estimate.

“We’re transparent about our modeling and we did it at scale. We show that we can achieve better results with the combination of noisy data and traditional biomarkers.

“Also, all our algorithms and models are open-sourced and everyone can use them.”

Study author Professor Cecilia Mascolo added: “We’ve shown that you don’t need an expensive test in a lab to get a real measurement of fitness – the wearables we use every day can be just as powerful, if they have the right algorithm behind them.

“Cardio-fitness is such an important health marker, but until now we did not have the means to measure it at scale.

“These findings could have significant implications for population health policies, so we can move beyond weaker health proxies such as the Body Mass Index (BMI).”

The findings were published in the journal npj Digital Medicine.