| Application: | 59070, Statistical machine learning of wearable sensor data to predict disease outcomes |
| Title: | biobank ACCELEROMETER ANALYSIS: Extracting meaningful health information from large accelerometer datasets |
| Size: | 40.9 MB |
| Cost Tier: | 3 |
| Archived: | 5 Oct 2022 |
| Stability: | Complete |
| Personal: | Contains individual-level data |
Return 2040
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Notes
This dataset supplies supplemental data for the derived accelerometer fields in Category 1020. This was generated by a tool to extract meaningful health information from large accelerometer datasets. The software generates time-series and summary metrics useful for answering key questions such as how much time is spent in sleep, sedentary behaviour, or doing physical activity.Application 59070
Statistical machine learning of wearable sensor data to predict disease outcomes
Most common diseases are identified too late. For example, over 50% of major cardiac events are in patients not classified as high-risk using current clinical risk prediction methods. Wearable sensors can continuously, noninvasively, and painlessly measure important markers of health in people's everyday lives. However, much more research is needed to test if these sensors really do help us predict who is at risk of common diseases such as cardiovascular disease, type 2 diabetes, breast cancer, colon cancer, etc. We therefore propose to test if the prediction of future disease can be improved by adding data from wearable sensors to clinical risk prediction models. In particular, we will investigate: 1. Can disease events be predicted from wearable sensors alone? 2. Are wearable sensor measurements causally associated with disease outcomes? 3. Are clinical risk prediction models improved by adding wearable sensor measurements?
| Lead investigator: | Dr Aiden Doherty |
| Lead institution: | University of Oxford |
Enabling scientific discoveries that improve human health