̽��ֱ�� of Cambridge - fitness

Fitness levels accurately predicted using wearable devices – no exercise required

sc604 — Thu, 01 Dec 2022 10:00:18 +0000

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. ̽��ֱ��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.

In what is by far the largest study of its kind, the researchers gathered activity data from more than 11,000 participants in the Fenland Study using wearable sensors, with a subset of participants tested again seven years later. ̽��ֱ��researchers used the data to develop a model to predict VO2max, which was then validated against a third group that carried out a standard lab-based exercise test. ̽��ֱ��model showed a high degree of accuracy compared to lab-based tests, and outperforms other approaches.

Some smartwatches and fitness monitors currently on the market claim to provide an estimate of VO2max, but since the algorithms powering these predictions aren’t published and are subject to change at any time, it’s unclear whether the predictions are accurate, or whether an exercise regime is having any effect on an individual’s VO2max over time.

̽��ֱ��Cambridge-developed model is robust, transparent and provides accurate predictions based on heart rate and accelerometer data only. 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. ̽��ֱ��results are reported in the journal npj Digital Medicine.

A measurement of VO2max is considered the ‘gold standard’ of fitness tests. Professional athletes, for example, test their VO2max by measuring their oxygen consumption while they exercise to the point of exhaustion. There are other ways of measuring fitness in the laboratory, like heart rate response to exercise tests, but these require equipment like a treadmill or exercise bike. Additionally, strenuous exercise can be a risk to some individuals.

“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,” said co-author Dr Soren Brage from Cambridge’s Medical Research Council (MRC) Epidemiology Unit. “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.”

“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,” said co-lead author Dr Dimitris Spathis from Cambridge’s Department of Computer Science and Technology. “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.”

̽��ֱ��study was a collaboration between the two departments: the team from the MRC Epidemiology Unit provided expertise in population health and cardiorespiratory fitness and data from the Fenland Study – a long-running public health study in the East of England – while the team from the Department of Computer Science and Technology provided expertise in machine learning and artificial intelligence for mobile and wearable data.

Participants in the study wore wearable devices continuously for six days. ̽��ֱ��sensors gathered 60 values per second, resulting in an enormous amount of data before processing. “We had to design an algorithm pipeline and appropriate models that could compress this huge amount of data and use it to make an accurate prediction,” said Spathis. “ ̽��ֱ��free-living nature of the data makes this prediction challenging because we’re trying to predict a high-level outcome (fitness) with noisy low-level data (wearable sensors).”

̽��ֱ��researchers used an AI model known as a deep neural network to process and extract meaningful information from the raw sensor data and make predictions of VO2max from it. Beyond predictions, the trained models can be used for the identification of sub-populations in particular need of intervention related to fitness.

̽��ֱ��baseline data from 11,059 participants in the Fenland Study was compared with follow-up data from seven years later, taken from a subset of 2,675 of the original participants. A third group of 181 participants from the UK Biobank Validation Study underwent lab-based VO2max testing to validate the accuracy of the algorithm. ̽��ֱ��machine learning model had strong agreement with the measured VO2max scores at both baseline (82% agreement) and follow-up testing (72% agreement).

“This study is a perfect demonstration of how we can leverage expertise across epidemiology, public health, machine learning and signal processing,” said co-lead author Dr Ignacio Perez-Pozuelo.

̽��ֱ��researchers say that their results demonstrate how wearables can accurately measure fitness, but transparency needs to be improved if measurements from commercially available wearables are to be trusted.

“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,” said Brage. “ ̽��ֱ��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.”

“Everything on your smartwatch related to health and fitness is an estimate,” said Spathis. “We’re transparent about our modelling 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.”

“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,” said senior author Professor Cecilia Mascolo from the Department of Computer Science and Technology. “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).”

̽��ֱ��research was supported in part by Jesus College, Cambridge and the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI). Cecilia Mascolo is a Fellow of Jesus College, Cambridge.

Reference:
Dimitris Spathis et al. ‘Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments.’ npj Digital Medicine (2022). DOI: 10.1038/s41746-022-00719-1

Cambridge researchers have developed a method for measuring overall fitness accurately on wearable devices – and more robustly than current consumer smartwatches and fitness monitors – without the wearer needing to exercise.

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

Cecilia Mascolo

Oscar Wong via Getty Images

Woman checking her smart watch and mobile phone after run

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

When mothers are active so are their children – but many mothers are not

amb206 — Mon, 24 Mar 2014 09:21:01 +0000

Parents are strong influences in the lives of young children, with patterns of behaviour established in the early years laying the foundation for future choices. A new study suggests that, when it comes to levels of physical activity, it is mothers who set (or don’t set) the pace.

An analysis of the physical activity levels of more than 500 mothers and pre-schoolers, assessed using activity monitors to produce accurate data, found that the amount of activity that a mother and her child did each day was closely related. Overall, maternal activity levels were strikingly low: only 53% of mothers engaged in 30 minutes of moderate-to-vigorous physical activity at least once a week. ̽��ֱ��UK Government recommends achieving 150 minutes of at least ‘moderate intensity physical activity’ (such as brisk walking) over the week as one of the ways of achieving its physical activity guidelines.

̽��ֱ��results of the study are published today (24 March 2014) in the journal Pediatrics. ̽��ֱ��paper ‘Activity Levels in Mothers and Their Preschool Children’ suggests that, given the link between mothers and young children, policies to improve children’s health should be directed to whole families and seek to engage mothers in particular.

̽��ֱ��research was overseen by Dr Esther van Sluijs at the MRC Epidemiology Unit and the Centre for Diet and Activity Research, ̽��ֱ�� of Cambridge, and led by Kathryn Hesketh (formerly of Cambridge and now UCL), in collaboration with researchers at the MRC Lifecourse Epidemiology Unit, ̽��ֱ�� of Southampton.

̽��ֱ��study is the first to show a direct association in a large sample of mothers and children, both fitted with activity monitors at the same time. It shows that young children are not ‘just naturally active’ and that parents have an important role to play in the development of healthy activity habits early on in life. ̽��ֱ��research also provides important evidence for policy makers to inform programmes that promote physical activity in families with young children. Its findings suggest that all family members can benefit from such efforts.

It is well established that physical activity is closely linked to health and disease prevention. Research shows that active mothers appear to have active school-aged children, who are in turn more likely than their less active peers to have good health outcomes. However, there has been little large-scale research into the association between the activity of mothers and that of preschool-aged children or about the demographic and temporal factors that influence activity levels in mothers of young children.

̽��ֱ��research published in the Pediatrics paper drew on data obtained from 554 women and their four-year-old children who are participants in the Southampton Women’s Survey, devised and run by the MRC Lifecourse Epidemiology Unit. A major longitudinal study initiated in the late 1990s, the project is following women who were first interviewed in their 20s and 30s, many of whom subsequently gave birth. From confirmation of pregnancy, the programme assesses the health and development of the children born to women in the survey.

Of the 554 mothers whose data was analysed in the Cambridge-led study, many were working and many of the children attended day-care facilities – factors that influenced activity levels of both mothers and children, as well as the association between the two. Other potential influences on maternal activity examined in the study included maternal education, whether the child had siblings, and whether his or her father was present at home.

While previous studies have used a self-report approach to measure activity, in the Southampton Women’s Survey both mothers and youngsters were fitted with Actiheart monitors (combined accelerometer and heart rate monitor) to record with a high degree of accuracy their physical activity levels for up to a week with a high degree of accuracy. “We used an activity monitor that was attached to participants and worn continuously, even during sleep and water-based activity,” said van Sluijs.

“This approach allowed us to capture accurately both mothers’ and children’s physical activity levels for the whole of the measurement period, matching hour for hour maternal-child activity levels. This comparison provided us with detailed information about how the association between mothers and children’s activity changed throughout the day, and how factors such as childcare attendance and maternal education influenced this relationship.”

̽��ֱ��activity levels of parent and child were, for the first time, recorded over whole daytime periods for up to seven days. ̽��ֱ��resulting data allowed the researchers to plot physical activity throughout the day and over the course of an entire week to see how activities varied across the day and how weekday activity levels compared with weekend activity levels.

̽��ֱ��data from mother and child were matched up to see if and how the activity patterns of adults and children correlated. “We saw a direct, positive association between physical activity in children and their mothers – the more activity a mother did, the more active her child. Although it is not possible to tell from this study whether active children were making their mothers run around after them, it is likely that activity in one of the pair influences activity in the other,” said Hesketh.

“For every minute of moderate-to-vigorous activity a mother engaged in, her child was more likely to engage in 10% more of the same level of activity. If a mother was one hour less sedentary per day, her child may have spent 10 minutes less sedentary per day. Such small minute-by-minute differences may therefore represent a non-trivial amount of activity over the course of a week, month and year.”

̽��ֱ��direct positive association between mothers and their four-year-old children was apparent for overall daily activity levels and activity segmented over the day (morning, afternoon and evening). This finding suggests that mothers and their children are active concurrently. However, the association differed by child’s weight status, time spent at preschool, duration of mother’s schooling and by time of day and week.

“Our study shows that the relationship between mother and child activity is moderated by demographic and time factors – for example, for moderate-to-vigorous activity, the relationship was stronger for mothers who left school aged 16 compared to those who left aged 18 or more. ̽��ֱ��association also differed by time of week, with light activity, such as walking, most strongly associated at weekends than on weekdays. ̽��ֱ��opposite was observed for moderate-to-vigorous activity which was more strongly associated on weekdays,” said van Sluijs.

̽��ֱ��research adds a further dimension to what is already known about levels of physical activity in children and adults. Despite strong evidence of the benefits of exercise, activity levels decrease through childhood and into adulthood. This decline extends into the childbearing years. New parents tend to be less active than peers without children and more likely to fail to meet recommended guidelines.

Once women become mothers their activity levels frequently fail to return to pre-parenthood levels and their relative lack of activity may influence that of their small children. “There are many competing priorities for new parents and making time to be active may not always be top of the list. However, small increases in maternal activity levels may lead to benefits for mothers and children. And if activity in mothers and children can be encouraged or incorporated into daily activities, so that more time is spent moving, activity levels are likely to increase in both. In return, this is likely to have long-term health benefits for both,” said Hesketh.

A study of physical activity patterns of women and their four-year-olds reveals a strong association between the two. It also shows that only 53% of mothers engaged in 30 minutes of moderate-to-vigorous activity at least once a week. Taken together, these results provide valuable pointers for policy makers.

Our study shows that the relationship between mother and child activity is moderated by demographic and time factors.

Esther van Sluijs

Mikey Phillips via Flickr

Wellies

This work is licensed under a Creative Commons Licence. If you use this content on your site please link back to this page.

Yes