VO2 max is a crucial measurement of overall fitness and an important predictor of heart disease and mortality risk. Generally, tests that measure VO2max require expensive laboratory equipment and are mostly limited to elite athletes.
Now, Scientists from the University of Cambridge have developed a method to measure overall fitness accurately on wearable devices. It uses machine learning to predict VO2max during everyday activity without needing contextual information such as GPS measurements. The method is more robust than current consumer smartwatches and fitness monitors.
The newly developed model is more transparent and provides accurate predictions based on heart rate and accelerometer data only. The model’s ability to track changes over time makes it valuable for measuring population-wide fitness levels and determining how changing lifestyles affect it.
Co-author Dr. Soren Brage from Cambridge’s MRC Epidemiology Unit 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.”
Co-lead author Dr. Dimitris Spathis from Cambridge’s Department of Computer Science and Technology said, “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.”
The study was a collaboration between the two departments: the team from the Department of Computer Science and Technology contributed expertise in machine learning and artificial intelligence for mobile and wearable data, while the team from the MRC Epidemiology Unit contributed knowledge of population health, cardiorespiratory fitness, and data from the Fenland Study, a long-running public health study in the East of England.
For six days, study participants wore wearable technology nonstop. The sensors collected 60 values every second, producing a massive amount of data that needed to be processed.
Spathis said, “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. The 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).”
To analyze and extract useful information from the unprocessed sensor data and construct predictions of VO2max from it, scientists employed an AI model known as a deep neural network. Beyond making predictions, the trained models can be utilized to identify subpopulations that especially require fitness-related intervention.
The Fenland Study’s baseline data from 11,059 participants were compared to follow-up data collected from a subset of 2,675 of the original participants seven years later. To verify the correctness of the algorithm, the third group of 181 UK Biobank Validation Study participants undertook lab-based VO2max testing. Both at the baseline (82% agreement) and follow-up testing (72% agreement), the machine learning model and the measured VO2max scores had an excellent agreement.
Co-lead author Dr. Ignacio Perez-Pozuelo said, “This study is a perfect demonstration of how we can leverage expertise across epidemiology, public health, machine learning, and signal processing.”
“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.”
Brage said, “It’s true in principle that many fitness monitors and smartwatches provide a measurement of VO2 max, but it’s very difficult to assess the validity of those claims. The models aren’t usually published, and the algorithms can change regularly, making it difficult for people to determine if their fitness has improved or is just being estimated by a different algorithm.”
Spathis said, “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 can achieve better results using noisy data and traditional biomarkers. Also, all our algorithms and models are open-sourced, and everyone can use them.”
Senior author Professor Cecilia Mascolo from the Department of Computer Science and Technology said, “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 that we can move beyond weaker health proxies such as the Body Mass Index (BMI).”