Abstract: Data describing glucose measurements is received from a continuous glucose monitoring (CGM) system worn by a user and predicted glucose values during a future time period are generated for the user based on the data. A determination is made that at least one of the predicted glucose values satisfies a threshold value for an alert, which is associated with a prediction horizon that defines an amount of time prior to satisfaction of the threshold value for communicating the alert to the user. Output of the alert is caused responsive to determining that the at least one predicted glucose value satisfies the threshold value for the alert within the prediction horizon, relative to a current time. The prediction horizon is modified based on a user response to the alert. Output of a subsequent instance of the alert is caused based on the modified prediction horizon.

Abstract: Data-stream bridging for sensor transitions is described. A first data stream of glucose measurements is received from a first glucose sensor worn by a user. A termination event for the first glucose sensor is detected when production and/or communication of the first glucose measurements via the first data stream ceases. Next, a second data stream of glucose measurements is received from a second glucose sensor worn by the user that replaces the first glucose sensor. During a warmup period for the second glucose sensor, estimated glucose values are output for the user based on both the first data stream of glucose measurements received from the first glucose sensor prior to the termination event and the second data stream of glucose measurements received from the second glucose sensor.

Abstract: Data describing glucose measurements is received from a continuous glucose monitoring (CGM) system worn by a user and predicted glucose values during a future time period are generated for the user based on the data. A determination is made that at least one of the predicted glucose values satisfies a threshold value for an alert, which is associated with a prediction horizon that defines an amount of time prior to satisfaction of the threshold value for communicating the alert to the user. Output of the alert is caused responsive to determining that the at least one predicted glucose value satisfies the threshold value for the alert within the prediction horizon, relative to a current time. The prediction horizon is modified based on a user response to the alert. Output of a subsequent instance of the alert is caused based on the modified prediction horizon.

Abstract: Data describing glucose measurements is received from a continuous glucose monitoring (CGM) system worn by a user and predicted glucose values during a future time period are generated for the user based on the data. A determination is made that at least one of the predicted glucose values satisfies a threshold value for an alert, which is associated with a prediction horizon that defines an amount of time prior to satisfaction of the threshold value for communicating the alert to the user. Output of the alert is caused responsive to determining that the at least one predicted glucose value satisfies the threshold value for the alert within the prediction horizon, relative to a current time. The prediction horizon is modified based on a user response to the alert. Output of a subsequent instance of the alert is caused based on the modified prediction horizon.

Abstract: Data describing glucose measurements is received from a continuous glucose monitoring (CGM) system worn by a user and predicted glucose values during a future time period are generated for the user based on the data. A determination is made that at least one of the predicted glucose values satisfies a threshold value for an alert, which is associated with a prediction horizon that defines an amount of time prior to satisfaction of the threshold value for communicating the alert to the user. Output of the alert is caused responsive to determining that the at least one predicted glucose value satisfies the threshold value for the alert within the prediction horizon, relative to a current time. The prediction horizon is modified based on a user response to the alert. Output of a subsequent instance of the alert is caused based on the modified prediction horizon.

Abstract: Population malady identification with a wearable glucose monitoring device is described. A malady identification system obtains temperature measurements that are produced by wearable glucose monitoring devices worn by users of a user population. The malady identification system further obtains location data describing locations of the users and associates each of the temperature measurements with a respective location. The malady identification system utilizes identification logic (e.g., one or more machine learning models) to identify presence of a malady in the users at one or more of the locations based on the temperature measurements and the location data. The malady identification system generates a communication for notifying at least one of the users about the presence of the malady.

Abstract: Glucose measurement and glucose-impacting event prediction using a stack of machine learning models is described. A CGM platform includes stacked machine learning models, such that an output generated by one of the machine learning models can be provided as input to another one of the machine learning models. The multiple machine learning models include at least one model trained to generate a glucose measurement prediction and another model trained to generate an event prediction, for an upcoming time interval. Each of the stacked machine learning models is configured to generate its respective output when provided as input at least one of glucose measurements provided by a CGM system worn by the user or additional data describing user behavior or other aspects that impact a person's glucose in the future. Predictions may then be output, such as via communication and/or display of a notification about the corresponding prediction.