Research Fellow, Stanford University
1 active project
Fitbit heart rate signals for validation of infectious disease alerting system
Scientific Questions Being Studied
We plan to use the All of Us study population to identify a similar cohort (to the outside studies defined in the next section) for pattern validation of heart rate signals to predict infection from Covid-19 and other infectious diseases. A primary goal is to validate our smartwatch-based Covid-19 alerting algorithms, as well as refine ways to exclude false alarms such as those driven by other lifestyle factors (travel, exercise...).
- Methods Development
- Control Set
In our (Stanford) collaboration with Fitbit and the PAC-12 sports conference, 925 student athletes at PAC-12 universities have been wearing Fitbit watches for 1-2 years to aid in the prediction of COVID-19 and other infectious diseases. We also have wearable data from our phase I (N=6,187) and phase II (N=5,285) studies where we developed algorithms attempting to predict Covid-19 and other infectious diseases, but also predicted elevated physiological signals from other lifestyle factors. Comparing algorithms across studies will help us to identify factors that lead to "false" alarms, such as exercise, other health conditions, or travel.
We hope to better refine our ability to predict infectious disease, and to distinguish other factors that create elevated or outlying signals in wearable data. This would complement our previous publications in Nature Medicine and Nature Biomedical Engineering by improving the alerts we are sending to study participants about elevated physiological signals.
Demographic Categories of Interest
This study will not center on underrepresented populations.
Data Set UsedControlled Tier
- Andrew Brooks - Research Fellow, Stanford University
You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.