Investigation of glycemic events in blood glucose data
To better understand the impact of glycemic events, some entities have begun examining the relationship between the blood glucose level and another physiological parameter. However, this relationship can be difficult to understand. Introduced here are computer programs and associated computer-implemented techniques for discovering glycemic events in a series of data values representative of blood glucose measurements and then altering the measurement schedule of a sensor capable of generating measurements in a dimension other than blood glucose based on the glycemic events. By altering the measurement schedule of the sensor, a diabetes management platform can better understand how, if at all, dimensions other than blood glucose are related to the glycemic health state of a subject whose blood glucose level is being monitored.
1. A method comprising:
receiving, by a processor, a substantially real-time data stream of estimated blood glucose values;
identifying, by the processor, a glycemic event by analyzing the estimated blood glucose values;
configuring, by the processor responsive to said identifying, a measurement schedule of a sensor based on the glycemic event by modulating a frequency with which the sensor generates one or more physical measurements in a measurement dimension other than blood glucose; and
generating, by the processor, a post-glycemic event report based on the estimated blood glucose values and the one or more physical measurements.
2. The method of claim 1 , wherein said configuring is performed so as to gain further insight into the measurement dimension other than blood glucose during a time interval corresponding to the glycemic event.
3. The method of claim 1 , wherein said configuring results in an increase in the frequency over a time interval corresponding to the glycemic event.
4. The method of claim 1 , wherein said identifying comprises:
detecting a signal feature that is indicative of the glycemic event,
wherein the signal feature is defined by a pair of dynamically-determined, semi-global minima values and a peak value in the estimated blood glucose values.
5. The method of claim 4 , wherein said configuring causes the frequency of the sensor to be highest within a time interval corresponding to the peak value.
6. The method of claim 5 , wherein said configuring causes the frequency of the sensor to gradually increase before the time interval and gradually decrease after the time interval.
7. The method of claim 1 , wherein the sensor is configured to measure temperature, humidity, light, movement, position, heart rate, blood pressure, or any combination thereof.
8. The method of claim 1 , further comprising:
configuring, by the processor responsive to said identifying, a second measurement schedule of a second sensor based on the glycemic event by modulating a second frequency with which the second sensor generates one or more physical measurements in a second measurement dimension other than blood glucose.
9. The method of claim 8 , wherein the measurement dimension is different than the second measurement dimension.
10. The method of claim 8 , wherein the measurement schedule of the sensor is configured independently of the second measurement schedule of the second sensor.
11. A method comprising:
acquiring, by a processor, historical estimated blood glucose values;
discovering, by the processor, a pattern of glycemic events from the historical estimated blood glucose values to predict onsets of glycemic events;
receiving, by the processor, a substantially real-time data stream of estimated blood glucose values;
identifying, by the processor, a potential onset of a glycemic event by analyzing the estimated blood glucose values; and
altering, by the processor responsive to said identifying, a measurement schedule of a sensor based on a pattern of estimated blood glucose values supporting the potential onset so as to gain further insight into a measurement dimension other than blood glucose,
wherein the sensor is capable of determining one or more physical measurements in the measurement dimension other than blood glucose over a time interval corresponding to the potential onset.
12. The method of claim 11 , further comprising:
generating, by the processor, a post-glycemic event report based on the estimated blood glucose values and the one or more physical measurements.
13. The method of claim 11 , wherein the historical estimated blood glucose values are associated with a single individual.
14. The method of claim 11 , wherein the historical estimated blood glucose values are associated with a population of multiple individuals.
15. The method of claim 11 , further comprising:
altering, by the processor responsive to said identifying, a second measurement schedule of a second sensor based on the pattern of estimated blood glucose values supporting the potential onset so as to gain further insight into a second measurement dimension other than blood glucose,
wherein the second sensor is capable of determining one or more physical measurements in the second measurement dimension other than blood glucose over the time interval corresponding to the potential onset.
16. The method of claim 15 , wherein the measurement dimension is different than the second measurement dimension.
17. The method of claim 15 , wherein the measurement dimension is the same as the second measurement dimension.
18. The method of claim 11 , wherein said altering results in a change to a resolution of the sensor, a polling frequency of the sensor, or any combination thereof.
19. The method of claim 11 , wherein said altering causes the sensor to automatically adjust a frequency with which the sensor generates physical measurements.
20. The method of claim 11 , wherein the further comprising:
generating, by the processor, a notification for presentation on an electronic device associated with an individual for whom the potential onset is identified,
wherein the notification specifies the altered measurement schedule, the execution of which requires at least some manual interaction.
21. A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
receiving a stream of estimated blood glucose values for an individual;
parsing the stream of estimated blood glucose values to identify a signal feature that is indicative of a glycemic event,
wherein the signal feature is defined by a pair of dynamically-determined, semi-global minima values and a peak value; and
configuring, responsive to said parsing, a measurement schedule of a sensor based on the glycemic event,
wherein the sensor is capable of generating physiological measurements in a measurement dimension other than blood glucose.
22. The non-transitory computer-readable medium of claim 21 , wherein the operations further comprise:
generating a notification for presentation on an electronic device associated with the individual,
wherein the notification specifies the configured measurement schedule, the execution of which requires at least some manual interaction.
23. The non-transitory computer-readable medium of claim 21 , wherein the operations further comprise:
automatically implementing the configured measurement schedule on behalf of the individual without requiring user input.