Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Wearables Group December 2023

We develop reproducible methods to analyse time-series wearable sensor data in very large population health studies to better understand the causes and consequences of disease.

Please do get in contact if you are interested in joining, or collaborating with, our research group. We produce open papers, code, and data where our work can be broadly categorised into three major areas:

  1. Machine learning: We develop methods to measure physical activity and sleep status from wearables data in large-scale biobanks that are actively used by researchers worldwide to demonstrate new associations with cardiovascular disease, cancer, depression, mood disorders, and others. These methods generally involve reproducible time-series machine learning methods to robustly identify both behavioural (e.g. walking) and disease-specific (e.g. heart failure) phenotypes. We are actively working on new accelerometer phenotypes and new sensing modalities including cameras, electrocardiograms, and photoplethysmograms.  
  2. Epidemiology: We develop methods to account for the unique nature of wearable phenotypes in relation to health association and risk prediction analyses. This has helped us show a clear inverse association between the amount of total physical activity and cardiovascular disease incidence, with no threshold of effect at low or high levels. Our methods generally involve reproducible compositional data analysis to account for the relative time spent in different behaviours over the 24-hour day. We are actively working to expand our work to include large-scale wearable epidemiology studies across a diverse range of cohorts.
  3. Genomics: The combination of wearables with genomics is important to identify and prioritise which wearable measurements are causally associated with disease and to discover new target mechanisms for disease. This has helped us discover the first genetic variants associated with machine-learned sensor phenotypes, showing the first genetic evidence that physical activity might causally lower blood pressure. We are actively working to expand this work to include more datasets and more detailed genomic information.

Our team

Our Funders

Wellcome

Novo Nordisk

Swiss Re

Health Data Research UK

National Institute for Health Research

British Heart Foundation

Alan Turing Institute

Medical Research Council

Engineering and Physical Sciences Research Council

US National Institute for Health

resources

Data

Capture-24

A human activity recognition dataset with raw accelerometer data and accompanying annotations inferred from wearable cameras.

Associated manuscript.

UK Biobank

Derived physical activity and sleep variables in 100,000 UK Biobank participants.

The main manuscripts associated with this:

Associated manuscript (1)
Associated manuscript (2)

Code

Stepcount

An internally and externally validated software tool to infer step counts from wrist-worn accelerometers.

Associated manuscript.

Actipy

A software tool to ingest multiple activity files into python dataframes with associated calibration, filtering, etc.

Graphic icons of different wearable devices.

Sleepnet

An internally and externally validated (versus polysomnography in ~1700 people) software tool to infer sleep metrics from wrist-worn accelerometers.

Associated manuscript. 

Biobank Accelerometer analysis

Software tool used to generate activity variables for the UK Biobank.

Associated manuscript.  

Wearables biobank accelerometer analysis logo.

SSL Feature Learning

A software tool to extract new movement features (over traditional time and frequency domain features) trained using data from 100,000 UK Biobank participants.

Associated manuscript.

Epicoda

R package designed to support epidemiological analyses using compositional exposure variables.

Associated manuscript. 

Image of a person wearing a wrist watch with some science-themed graphics in the background.