In this longitudinal study we propose to recruit a very large cohort of subjects from various demographics that we can equip with wearable devices and collect fine grained spatio temporal data on heart rates, sleep, and activity levels, as well location and movement. These will be integrated with their electronic health records (including diagnostic tests, treatments, chronic conditions and image datasets), vaccination dates and records, post vaccination symptoms, antibody testing and covid -19 test results. Using deep learning methods we will develop models to predict early onset of infections and understand the long term effects of previous infection as well as effects of specific vaccines.
Activity and Physiological Trackers To Detect And Monitor Pandemic Effects
Pillar 1
Pillar 2
Digital aging, gerosciene and latent COVID-19 effects
Latent psycho-socio-behavioral effects
Public health responses
Sentinel alert system/waste water
Virus & immune response
Need
Wearable devices are increasingly used in the USA and globally to monitor individual health. Data collected from personal sensors can improve remote patient monitoring, enhance our pandemic response, and track secondary and long-term effects of COVID-19.
Proposed Solution
While there are existing studies that are currently conducting a subset of these analyses, our goal is to transform the prediction and monitoring of pandemic effects. We propose a comprehensive study that combines data from personal wearable sensors, COVID -19 tests and EHR datasets, antibody testing results, as well as COVID -19 vaccination records to not only proactively predict potential COVID -19 infection (or reinfections) but also long-term effects of COVID-19 and the effect of vaccines and other preventive measures.