Smartphones are now nearly ubiquitous; their numerous built-in sensors enable continuous measurement of activities of daily living, making them especially well-suited for health research.
Progress in science has always been driven by data. More than 5 billion mobile devices were in use in 2020 (Association, G. The mobile economy 2020), with multiple sensors (e.g. accelerometer and GPS) that can capture detailed, continuous and objective measurements on various aspects of our lives, including physical activity. This surge in smartphone adoption around the world presents unprecedented opportunities for data collection to study human behaviour and health.
Today these devices can collect an enormous amount of data on large cohorts of individuals over long periods of time without the need for additional hardware or instruments. They are instruments with great potential in data collection for objective and reproducible quantification of population risk factors. Behavioural risk factors, including but not limited to sedentary behaviour, sleep and physical activity, can be monitored by smartphones in an individual’s day-to-day life.
The adoption of smartphones in health research is supported by encouraging findings such as wearable accelerometers, which have demonstrated strong associations between physical activity and health outcomes such as obesity, diabetes, various cardiovascular diseases, mental health and mortality.
To improve results and achieve population-level impact, future studies should focus on improving the quality of the data collected, addressing missing data, incorporating greater diversity of participants and activities, providing more complete documentation, and sharing the source code of the methods and algorithms implemented.
Source: A systematic review of smartphone-based human activity recognition methods for health research. (Nature)