Safety tools for decision support recommendations made to users of continuous glucose monitoring systems
Systems and method are described for determining if a decision support recommendation is to be presented to a user for treatment of a diabetic state, including receiving a plurality of input data items impacting a diabetic state of a user of continuous glucose monitor, the input data items serving as input data to a process for determining a decision support recommendation; assigning a reliability level to each of the input data items; calculating a reliability metric based on the reliability levels assigned to each of the input data items; determining a decision support recommendation based on the process and the input data and presenting the decision support recommendation to the user on a user interface only if the reliability metric exceeds a threshold.
1. A method for determining a decision support recommendation for treatment of a diabetic state, the method comprising:
identifying a current diabetic state of a user based at least in part on a glucose concentration level;
receiving additional data that, along with the current diabetic state, are used for determining the decision support recommendation;
assigning a separate reliability level to each of the current diabetic state and the additional data, wherein the separate reliability level assigned to the additional data is based at least in part on an identity of a source from which the additional data is obtained;
calculating the decision support recommendation using the additional data and the current diabetic state;
assigning an overall reliability level to the decision support recommendation based on the separate reliability levels; and
performing the decision support recommendation to treat the diabetic state of the user based on the overall reliability level exceeding a first threshold, wherein the first threshold is selected based at least in part on a type of the decision support recommendation that is calculated, wherein performing the decision support recommendation comprises sending a command to an insulin pump, the command causing the insulin pump to automatically administer an amount of insulin.
2. The method of claim 1 , wherein the additional data includes an indication of food and drink ingested or to be ingested within a prescribed period of time.
3. The method of claim 2 , wherein the indication includes data manually entered by the user, nutritional data concerning the food or drink that is obtained from a third party, nutritional data automatically entered by an application, or nutritional data that is automatically entered by scanning the nutritional data into the application.
4. The method of claim 1 , wherein the additional data includes information describing past physiological response patterns of the user or an indication of a user activity level that has occurred or is to occur within a prescribed amount of time.
5. The method of claim 1 , wherein assigning the separate reliability level to the additional data includes assigning a higher reliability to additional information obtained through machine-to-machine communication than through manual entry-to-machine communication.
6. The method of claim 1 , wherein the decision support recommendation includes a recommendation to ingest food or drink or a recommendation to inject a calculated amount of insulin.
7. The method of claim 1 , wherein presenting the decision support recommendation only if the overall reliability level exceeds the first threshold further includes determining when to present the decision support recommendation based at least in part on the overall reliability level.
8. The method of claim 1 , wherein receiving the additional data includes receiving a plurality of additional data items of different types and assigning the separate reliability level to the additional data includes independently assigning a separate reliability level to each of the additional data items.
9. The method of claim 8 , wherein presenting the decision support recommendation includes only presenting the decision support recommendation if a weighted average of the separate reliability levels exceeds a second threshold and if none of the separate reliability levels falls below a third threshold.
10. The method of claim 1 , wherein:
receiving the additional data comprises receiving a plurality of additional data items;
assigning the separate reliability level to each of the current diabetic state and the additional data comprises assigning a separate reliability level to each of the plurality of additional data items based at least in part on the identity of the source from which each of the plurality of additional data items is obtained; and
calculating the decision support recommendation comprises calculating the decision support recommendation using the plurality of additional data items and the current diabetic state.
11. The method of claim 1 , wherein presenting the decision support recommendation further comprises presenting the decision support recommendation only if none of the separate reliability levels is below a second threshold.