Fitness levels can be accurately predicted using wearable devices – no exercise required

Using machine learning, a team of researchers has developed a new method of measuring overall fitness on wearable devices. It is highly accurate and outperforms current consumer smartwatches and fitness monitors – even though it does not require the device wearers to exercise.

Normally, tests to accurately measure VO2max – a key measurement of overall fitness and an important predictor of heart disease and mortality risk – require expensive laboratory equipment and are mostly limited to elite athletes. The new method uses machine learning to predict VO2max (the capacity of the body to carry out aerobic work) during everyday activity, without the need for contextual information such as GPS measurements.

The work has just been published in npj Digital Medicine. Read the full story about it on the Cambridge University website.