MODEL MOSAIC FRAMEWORK FOR MODELING GLUCOSE SENSITIVITY
Techniques for determining glucose sensitivity are provided. In some embodiments, the techniques may involve receiving sensor data relating to a sensor electrical property. The techniques may further involve determining a subspace of a plurality of subspaces of an input signal feature space based on a respective range of values associated with the sensor electrical property. The techniques may further involve selecting a machine learning model from a plurality of machine learning models associated with the subspace. The techniques may further involve determining a glucose sensitivity of a glucose sensor device based on the sensor data and the selected machine learning model. The techniques may further involve determining whether to inhibit or utilize glucose readings of the glucose sensor device based on the glucose sensitivity. The techniques may further involve operating the glucose sensor device based on the determination.
1 . A method comprising:
receiving sensor data relating to a sensor electrical property;
determining a subspace of a plurality of subspaces of an input signal feature space based on a respective range of values associated with the sensor electrical property;
selecting a machine learning model from a plurality of machine learning models associated with the subspace;
determining a glucose sensitivity of a glucose sensor device based on the sensor data and the selected machine learning model;
determining whether to inhibit or utilize glucose readings of the glucose sensor device based on the glucose sensitivity; and
operating the glucose sensor device based on the determination.
2 . The method of claim 1 , wherein operating the glucose sensor device comprises determining a glucose level based on sensor data, and further comprising controlling delivery of insulin by an insulin delivery device based on the determined glucose level.
3 . The method of claim 1 , wherein operating the glucose sensor device based on the determination comprises determining that the glucose readings are to be inhibited based on the sensor data being non-compliant with one or more criteria.
4 . The method of claim 3 , wherein inhibiting the glucose readings comprises inhibiting transmission of data associated with the glucose readings from the glucose sensor device to a second device.
5 . The method of claim 1 , wherein the sensor electrical property comprises one or more of: a wear time of the glucose sensor device; a battery life of the glucose sensor device; or calibration information associated with the glucose sensor device.
6 . The method of claim 1 , wherein at least two subspaces of the plurality of subspaces are associated with overlapping machine learning models.
7 . The method of claim 1 , wherein the input signal feature space has been partitioned into the plurality of subspaces based on behavior of glucose sensitivity values for a corresponding range of sensor electrical property values within each subspace.
8 . The method of claim 7 , wherein each subspace is associated with different sensor operating conditions determined based on the range of sensor electrical property values corresponding to the subspace.
9 . The method of claim 8 , wherein a first subspace is associated with typical analyte diffusion, and wherein a second subspace is associated with reduced analyte diffusion.
10 . A system comprising:
one or more processors; and
one or more processor-readable media storing instructions which, when executed by the one or more processors, cause performance of:
receiving sensor data relating to a sensor electrical property;
determining a subspace of a plurality of subspaces of an input signal feature space based on a respective range of values associated with the sensor electrical property;
selecting a machine learning model from a plurality of machine learning models associated with the subspace;
determining a glucose sensitivity of a glucose sensor device based on the sensor data and the selected machine learning model;
determining whether to inhibit or utilize glucose readings of the glucose sensor device based on the glucose sensitivity; and
operating the glucose sensor device based on the determination.
11 . The system of claim 10 , wherein operating the glucose sensor device comprises determining a glucose level based on sensor data, and wherein the instructions further comprise controlling delivery of insulin by an insulin delivery device based on the determined glucose level.
12 . The system of claim 10 , wherein operating the glucose sensor device based on the determination comprises determining that the glucose readings are to be inhibited based on the sensor data being non-compliant with one or more criteria.
13 . The system of claim 12 , wherein inhibiting the glucose readings comprises inhibiting transmission of data associated with the glucose readings from the glucose sensor device to a second device.
14 . The system of claim 10 , wherein the sensor electrical property comprises one or more of:
a wear time of the glucose sensor device; a battery life of the glucose sensor device; or calibration information associated with the glucose sensor device.
15 . The system of claim 10 , wherein at least two subspaces of the plurality of subspaces are associated with overlapping machine learning models.
16 . The system of claim 10 , wherein the input signal feature space has been partitioned into the plurality of subspaces based on behavior of glucose sensitivity values for a corresponding range of sensor electrical property values within each subspace.
17 . The system of claim 16 , wherein each subspace is associated with different sensor operating conditions determined based on the range of sensor electrical property values corresponding to the subspace.
18 . The system of claim 17 , wherein a first subspace is associated with typical analyte diffusion, and wherein a second subspace is associated with reduced analyte diffusion.
19 . A method comprising:
receiving sensor data relating to a sensor electrical property;
determining a subspace of a plurality of subspaces of an input signal feature space based on a respective range of values associated with the sensor electrical property;
providing the sensor data as input to a trained machine learning model associated with the determined subspace and determining a glucose sensitivity of the glucose sensor device based on an output of the trained machine learning model;
determining whether to inhibit or utilize glucose readings of the glucose sensor device based on the glucose sensitivity; and
operating the glucose sensor device based on the determination.
20 . The method of claim 19 , wherein each subspace is associated with a different trained machine learning model.