Abstract: A system and method are disclosed for predicting short term health outcomes based on data collected by a wearable device such as an activity tracker or a smart watch. Artificial Intelligence (AI) algorithms are configured to process an input vector that includes monitored parameter data collected by the wearable device as well as embedding data obtained from health records corresponding to a user account registered to the wearable device. In particular, a framework is defined that includes a random forest model configured to classify a user based on the monitored parameter data and embedding data. Based on a positive health outcome classification, a minimum value is assigned to a health index value for the user or, based on a negative health outcome classification, a gradient boosting machine is configured to generate the health index value. Various operations can be performed based on the assigned health index value for the user.

Abstract: A system and method are disclosed for detecting chronic health conditions based on data collected by a wearable device such as an activity tracker or a smart watch. Deep learning algorithms are configured to process the monitored parameter data collected by the wearable device as well as additional embedding data obtained from health records corresponding to a user account registered to the wearable device. In some examples, the input vector can also include embedding data related to social determinants data and/or demographic data. The output of the deep learning algorithms provides predictions that represent probabilities that the user of the wearable device has an underlying health condition. If any underlying health condition is detected, then the user can be notified directly, via the wearable device or an associated application or technology, or indirectly, via a primary care provider associated with the user.