Event-oriented predictions of glycemic responses

1 . 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:

accessing a prediction model correlating:

a person's glycemic responses to events, and

the person's physiological parameters during the events;

obtaining a glucose level measurement of the person during an event;

determining a physiological parameter of the person during the event based on applying a physiological model to the glucose level measurement, the physiological parameter being derived based on an iterative adjustment of one or more physiological model parameters to minimize a difference measure between at least one simulated glucose level generated by the physiological model and at least one actual glucose level based on the glucose level measurement;

predicting the person's glycemic response to the event based on applying the prediction model to the physiological parameter;

determining, based on the predicted glycemic response, an amount of insulin to deliver to the person; and

causing delivery of the amount of insulin by an insulin delivery device.

2 . The system of claim 1 , wherein the event is a meal event.

3 . The system of claim 1 , wherein the physiological parameter is a metabolic parameter.

4 . The system of claim 3 , wherein the metabolic parameter is a rate of absorption of carbohydrates into the person's body.

5 . The system of claim 3 , wherein the metabolic parameter is a rate of converting carbohydrates into glucose.

6 . The system of claim 1 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:

obtaining carbohydrate content information for the event.

7 . The system of claim 1 , wherein the one or more processor-readable media further store instructions which, when executed by the one or more processors, cause performance of:

obtaining insulin delivery information indicating an amount of insulin delivered to the person during the event.

8 . The system of claim 7 , wherein predicting the person's glycemic response comprises accounting for glucose metabolism caused by the amount of insulin delivered to the person during the event.

9 . The system of claim 1 , wherein communicating the amount of insulin toward the insulin delivery device comprises communicating the amount of insulin to an intermediary computing device that is communicatively coupled to the insulin delivery device.

10 . The system of claim 1 , wherein predicting the person's glycemic response comprises:

obtaining a value indicative of a cumulative total amount of glucose predicted to have appeared in the person's blood after a particular amount of time has elapsed since a start time for the event; and

generating, based on the value, a curve representing the person's glucose levels during the particular amount of time.

11 . The system of claim 10 , wherein the value corresponds to a fractional area under a curve representative of a rate at which glucose appears in the person's blood as a function of time.

12 . The system of claim 1 , wherein the prediction model is configured to output a value corresponding to a cumulative total amount of glucose predicted to have appeared in the person's blood after a particular amount of time has elapsed since a start time for the event.

13 . The system of claim 1 , wherein the prediction model is generated based on a set of past events identified as eliciting similar glycemic responses from the person if the person's physiological parameters are identical during each past event of the set of past events.

14 . The system of claim 13 , wherein the set of past events includes a first event and a second event, the person's actual glycemic response to the first event being identified as similar to the person's hypothetical glycemic response to the second event, the hypothetical glycemic response to the second event being determined based on applying the person's physiological model to the person's physiological parameters during the first event.

15 . The system of claim 13 , wherein one or more of the person's physiological parameters during each past event, of the set of past events, are used to generate a graphical representation, and wherein a hyper-surface is fitted to the graphical representation to generate the prediction model.

16 . The system of claim 1 , wherein the prediction model is specific to the person.

17 . The system of claim 1 , wherein the physiological model comprises a glucose increasing model configured to simulate an increase in glucose levels of the person over time and a glucose decreasing model configured to simulate a decrease in glucose levels of the person over time, and wherein the at least one simulated glucose level is generated based on combining the simulated glucose increase from the glucose increasing model and the simulated glucose decrease from the glucose decreasing model applied to a starting bodily glucose level of the person.

18 . The system of claim 1 , wherein the iterative adjustment of the one or more physiological model parameters is subject to physiological constraints for values of the one or more physiological model parameters.

19 . A processor-implemented method comprising:

accessing a prediction model correlating:

a person's glycemic responses to events, and

the person's physiological parameters during the events;

obtaining a glucose level measurement of the person during an event;

determining a physiological parameter of the person during the event based on applying a physiological model to the glucose level measurement, the physiological parameter being derived based on an iterative adjustment of one or more physiological model parameters to minimize a difference measure between at least one simulated glucose level generated by the physiological model and at least one actual glucose level based on the glucose level measurement;

predicting the person's glycemic response to the event based on applying the prediction model to the physiological parameter;

determining, based on the predicted glycemic response, an amount of insulin to deliver to the person; and

causing delivery of the amount of insulin by an insulin delivery device.

20 . One or more non-transitory processor-readable media storing instructions which, when executed by one or more processors, cause performance of:

accessing a prediction model correlating:

a person's glycemic responses to events, and

the person's physiological parameters during the events;

obtaining a glucose level measurement of the person during an event;

determining a physiological parameter of the person during the event based on applying a physiological model to the glucose level measurement, the physiological parameter being derived based on an iterative adjustment of one or more physiological model parameters to minimize a difference measure between at least one simulated glucose level generated by the physiological model and at least one actual glucose level based on the glucose level measurement;

predicting the person's glycemic response to the event based on applying the prediction model to the physiological parameter;

determining, based on the predicted glycemic response, an amount of insulin to deliver to the person; and

causing delivery of the amount of insulin by an insulin delivery device.