Digital Medicine refers to gathering useful information from the data acquired through digital means. This includes data from wearable devices (Fitbit, Apple Watch, etc.). Sensors on these devices can be tailored to capture numerous measurements within the domains of health, mobility, and lifestyle. By looking at prognostic models through multi-scale, multimodal data collection via a wearable device, real-time data can provide crucial health-related insights and may help deliver better care.

Wearable technology uses an interactive user interface and various sensors for tracking activity, recommending and motivating users to attain their fitness goals, potentially generating a change in daily or routine habits. The detail and continuous data streaming from wearable devices make them an ideal source to identify measurements that may be useful in clinical care. Changes in physiological data due to infections or diseases can be effectively detected, often even before the onset of symptoms. To computationally detect such abnormalities, we can either rely on statistical methods or on machine learning and deep learning models.

We are focused on capturing and connecting information from wearables to clinical outcomes. This can only be possible by connecting patients' medical information to the data stream from the wearables. Patients enrolled in this study will be asked to wear a wearable device for a specific duration.