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 non-transitory medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
identifying a potential instance of a glycemic event by
applying, to a series of explicit values representative of discrete measurements of blood glucose of an individual, a model that produces a series of imputed values for the blood glucose of the individual, and
parsing the series of explicit values and/or the series of imputed values to discover one or more values that are determined to be representative of the potential instance of the glycemic event; and
altering, in response to said identifying, a measurement schedule of a sensor by increasing a frequency at which the sensor measures a physiological parameter other than blood glucose, so as to increase insight into the physiological parameter over an interval of time that corresponds to the potential instance of the glycemic event while conserving power during intervals of time that are less relevant to glycemic health of the individual.
2. The non-transitory medium of claim 1 , wherein the series of explicit values is provided to the model as input, such that the series of imputed values is produced as output based on a statistical analysis of the series of explicit values.
3. The non-transitory medium of claim 1 , wherein the one or more values are imputed values that are representative of an excursion that exceeds a predetermined amount.
4. The non-transitory medium of claim 1 , wherein the operations further comprise:
generating a notification for presentation to the individual for whom the potential instance of the glycemic event is identified.
5. The non-transitory medium of claim 4 , wherein the notification specifies the measurement schedule, the execution of which requires at least some manual interaction by the individual.
6. The non-transitory medium of claim 1 , wherein the processor is part of a computing device that is communicatively connected, via separate wireless communication channels, to the sensor and a glucose monitoring device that generates the series of explicit data values.
7. A method comprising:
obtaining, by a processor,
(i) a series of explicit values that are representative of actual measurements of a blood glucose level of an individual, and
(ii) a series of imputed values that are represented of predicted measurements of the blood glucose level of the individual;
detecting, by the processor, an instance of a glycemic event by examining the series of explicit values and the series of imputed values to discover one or more values that are determined to be representative of the instance of the glycemic event; and
modulating, by the processor, a frequency with which a sensor generates one or more physical measurements for the individual in a measurement dimension other than blood glucose over an interval of time that corresponds to the instance of the glycemic event, so as to increase insight into the measurement dimension while conserving power during intervals of time that are less relevant to glycemic health of the individual.
8. The method of claim 7 , wherein by modifying the frequency over the interval of time corresponding to the instance of the glycemic event, further insight is gained into the measurement dimension other than blood glucose before, during, or after the instance of the glycemic event.
9. The method of claim 7 , wherein the one or more values are explicit values that are determined to be representative of the instance of the glycemic event.
10. The method of claim 7 , wherein the one or more values are imputed values that are determined to be representative of the instance of the glycemic event.
11. The method of claim 7 , wherein said modulating results in a gradual increase in the frequency before the interval of time corresponding to the glycemic event and a gradual decrease in the frequency after the interval of time.
12. The method of claim 7 , wherein the sensor is configured to measure temperature, humidity, light, movement, position, heart rate, blood pressure, or any combination thereof.
13. The method of claim 7 , further comprising:
generating, by the processor, a report based on (i) the series of explicit values, (ii) the series of imputed values, and (iii) the one or more physical measurements, so as to convey whether a relationship exists between blood glucose and the measurement dimension other than blood glucose.
14. A non-transitory medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
examining a signal that is representative of discrete, digitally-represented measurements that are generated by a first sensor for a first physiological parameter and that are arranged in temporal order, so as to identify a variation in the first physiological parameter that corresponds to a change in health of an individual; and
modulating a frequency with which a second sensor generates one or more measurements of a second physiological parameter over an interval of time corresponding to the variation, so as to increase insight into the second physiological parameter as the individual experiences the change in health while conserving power when the individual is not experiencing variations in the first physiological parameter.
15. The non-transitory medium of claim 14 , wherein the operations further comprise:
generating a report that specifies a relationship, if any, that exists between the first and second physiological parameters, as determined based on an analysis of the one or more measurements corresponding to the interval of time.
16. The non-transitory medium of claim 15 , wherein the report is accessible to a person other than the individual.
17. The non-transitory medium of claim 14 , wherein the variation is identified by:
applying, to the measurements, an algorithm that identifies at least one measurement that matches a pattern in accordance with a pattern-defining parameter; and
characterizing the at least one measurement as being indicative of the variation.
18. The non-transitory medium of claim 14 , wherein the variation is identified by:
applying, to the measurements, patterns that correspond to different types of physiological events; and
characterizing the variation as representative of a given type of physiological event by identifying a matching one of the patterns.
19. The non-transitory medium of claim 14 , wherein the operations further comprise:
modulating a frequency with which the first sensor generates one or more measurements for the first physiological parameter over the interval of time corresponding to the variation, so as to also increase insight into the first physiological parameter as the individual experiences the change in health.
20. The non-transitory medium of claim 1 , wherein said altering causes a resolution and/or a polling frequency of the sensor to be highest within the interval of time that includes, or is expected to include, the potential instance of the glycemic event.