AUTOMATED DETECTION OF A PHYSICAL BEHAVIOR EVENT AND CORRESPONDING ADJUSTMENT OF A MEDICATION DISPENSING SYSTEM BASED ON HISTORICAL EVENTS
An automated medication dispensing system provides for triggering a medication administration message when an inferred event is detected for which a medication administration message is to be sent. The event might be the start, the beginning, or an anticipation of a start, of an eating event, detected by an event detection module from gestures of a user from a set of sensor readings. The message can be a signal to medication dispensing apparatus, and/or a reminder message to the user, an ancillary message to a caregiver, health professional, or others. The medication administration message might comprise a signal to an input of an insulin management system or an input of a meal-aware artificial pancreas. The events might also include a drinking event, a smoking event, a personal hygiene event, and/or a medication related event.
1 . An automated medication dosing and dispensing system comprising:
sensors to detect movement related to a user of the automated medication dosing and dispensing system;
a computer-readable storage medium comprising program code instructions; and
a processor, wherein the program code instructions are configurable to cause the processor to perform a method comprising the steps of:
determining, from sensor readings obtained from the sensors, a start or an anticipated start of a current food intake event of the user;
reviewing historical data collected for previously recorded food intake events of the user;
identifying a correlation between the current food intake event and a number of the previously recorded food intake events; and
adjusting medication dosage, medication dispensing parameters, or both medication dosage and medication dispensing parameters based on the identified correlation.
2 . The system of claim 1 , wherein at least one of the sensor readings measures a movement of a body part of the user.
3 . The system of claim 1 , further comprising an event detection module to determine, from the sensor readings, a physical behavior event of the user.
4 . The system of claim 3 , wherein the event detection module determines gestures of the user that characterize the current food intake event.
5 . The system of claim 1 , wherein the adjusting is based on at least one of the following characteristics of the food intake event: time duration; pace; start time; end time; number of bites; number of sips; eating method; type of utensils used; type of containers used; amount of chewing before swallowing; chewing speed; amount of food consumed; time between bites; time between sips; content of food consumed.
6 . The system of claim 1 , wherein:
the medication managed by the system is insulin; and
the adjusting step calculates a dosage of insulin to be administered and a schedule for delivery of the calculated dosage of insulin.
7 . The system of claim 1 , wherein the sensors comprise an accelerometer that measures movement of an arm of the user and a gyroscope that measures rotation of the arm of the user.
8 . The system of claim 1 , wherein the historical data comprises parameters that are not directly linked to the food intake event.
9 . The system of claim 8 , wherein the parameters include at least one of: location information; time of day the user wakes up; stress level; sleeping behavior patterns; calendar event details; phone call information; email meta-data.
10 . A method of operating an automated medication dosing and dispensing system having sensors to detect movement related to a user, the method comprising the steps of:
determining, from sensor readings obtained from the sensors, a start or an anticipated start of a current food intake event of the user;
reviewing historical data collected for previously recorded food intake events of the user;
identifying a correlation between the current food intake event and a number of the previously recorded food intake events; and
adjusting medication dosage, medication dispensing parameters, or both medication dosage and medication dispensing parameters based on the identified correlation.
11 . The method of claim 10 , wherein at least one of the sensor readings measures a movement of a body part of the user.
12 . The method of claim 10 , further comprising the step of determining, from the sensor readings, physical behavior events of the user.
13 . The method of claim 12 , wherein the physical behavior events determined from the sensor readings include gestures of the user that characterize the current food intake event.
14 . The method of claim 10 , wherein the adjusting is based on at least one of the following characteristics of the food intake event: time duration; pace; start time; end time; number of bites; number of sips; eating method; type of utensils used; type of containers used; amount of chewing before swallowing; chewing speed; amount of food consumed; time between bites; time between sips; content of food consumed.
15 . The method of claim 10 , wherein:
the medication managed by the system is insulin; and
the adjusting step calculates a dosage of insulin to be administered and a schedule for delivery of the calculated dosage of insulin.
16 . The method of claim 10 , wherein the sensors comprise an accelerometer that measures movement of an arm of the user and a gyroscope that measures rotation of the arm of the user.
17 . The method of claim 10 wherein the historical data comprises parameters that are not directly linked to the food intake event.
18 . The method of claim 17 , wherein the parameters include at least one of: location information; time of day the user wakes up; stress level; sleeping behavior patterns; calendar event details; phone call information; email meta-data.
19 . The method of claim 10 , wherein the adjusting is performed upon detection of an actual or imminent start of the current food intake event.
20 . The method of claim 10 , wherein the adjusting is based on characteristics of the current gesture-based physical behavior event.