Meal detection devices and methods
First Claim
1. A meal detection system, comprising:
- a plurality of sensors, each configured to sense a different physiological parameter of a user, the plurality of sensors being disposed external to the user;
a processor in communication with the plurality of sensors and configured to analyze outputs of the plurality of sensors to detect meal intake by the user, the processor being further configured to trigger a controlled device to deliver a therapy to the user in response to meal intake detected by the processor;
wherein, for each of the plurality of sensors, the processor is configured to calculate an index based on the output of the sensor and to determine that meal intake occurred when the index exceeds a threshold value; and
wherein the processor is configured to calculate the threshold value by processing a set of training data usin an average harmonic mean algorithm, the training data including sensor data for at least one user and ground truth data for the at least one user.
4 Assignments
0 Petitions
Accused Products
Abstract
Devices and methods for detecting meal intake are disclosed herein. In some embodiments, one or more sensors can be used to detect or monitor physiological parameters of a user (e.g., heart rate, body movements, temperature, pH, impedance, gastric stretch, sound emissions, and the like). The outputs of the sensors can be received by a computer system configured to analyze the sensor data and make a determination as to whether meal intake has occurred or is presently occurring. The computer system'"'"'s determination can be used to trigger, modulate, or otherwise control one or more therapeutic devices. Other types of devices can also be controlled using this determination, such as monitoring or logging devices.
100 Citations
18 Claims
-
1. A meal detection system, comprising:
-
a plurality of sensors, each configured to sense a different physiological parameter of a user, the plurality of sensors being disposed external to the user; a processor in communication with the plurality of sensors and configured to analyze outputs of the plurality of sensors to detect meal intake by the user, the processor being further configured to trigger a controlled device to deliver a therapy to the user in response to meal intake detected by the processor; wherein, for each of the plurality of sensors, the processor is configured to calculate an index based on the output of the sensor and to determine that meal intake occurred when the index exceeds a threshold value; and wherein the processor is configured to calculate the threshold value by processing a set of training data usin an average harmonic mean algorithm, the training data including sensor data for at least one user and ground truth data for the at least one user. - View Dependent Claims (2, 3, 5, 6, 8, 9, 10)
-
-
4. The system of 1, wherein the plurality of sensors includes a microphone configured to detect sounds emitted by the user and wherein the processor is configured to calculate a microphone index based on frequency matching and temporal matching of the microphone output to a predetermined pattern.
-
7. The system of 1, wherein the plurality of sensors includes an accelerometer configured to detect motion of the user and wherein the processor is configured to calculate an accelerometer index based on the total energy of the accelerometer output in a frequency band of interest.
-
11. A meal detection system, comprising:
-
a plurality of sensors, each configured to sense a different physiological parameter of a user, the plurality of sensors being disposed external to the user; and a processor in communication with the plurality of sensors and configured to analyze outputs of the plurality of sensors to detect meal intake by the user, the processor being further configured to trigger a controlled device to deliver a therapy to the user in response to meal intake detected by the processor, wherein the plurality of sensors includes an electromyograph and an accelerometer, and wherein the processor is configured to calculate an electromyograph index, an electromyograph threshold value, an accelerometer index, and an accelerometer threshold value, and to determine that; solid meal intake occurred when the electromyograph index exceeds the electromyograph threshold value; liquid meal intake occurred when the electromyograph index does not exceed the electromyograph threshold value and the accelerometer index exceeds the accelerometer threshold value; and no meal intake occurred when the electromyograph index does not exceed the electromyograph threshold value and the accelerometer index does not exceed the accelerometer threshold value.
-
-
12. A meal detection system, comprising:
-
a plurality of sensors, each configured to sense a different physiological parameter of a user, the plurality of sensors being disposed external to the user; and a processor in communication with the plurality of sensors and configured to analyze outputs of the plurality of sensors to detect meal intake by the user, the processor being further configured to trigger a controlled device to deliver a therapy to the user in response to meal intake detected by the processor, wherein the plurality of sensors includes an impedance sensor and an accelerometer, and wherein the processor is configured to calculate an impedance sensor index, an impedance sensor threshold value, an accelerometer index, and an accelerometer threshold value, and to determine that; solid meal intake occurred when the impedance sensor index exceeds the impedance sensor threshold value; liquid meal intake occurred when the impedance sensor index does not exceed the impedance sensor threshold value and the accelerometer index exceeds the accelerometer threshold value; and no meal intake occurred when the impedance sensor index does not exceed the impedance sensor threshold value and the accelerometer index does not exceed the accelerometer threshold value.
-
-
13. A meal detection system, comprising:
-
a plurality of sensors, each configured to sense a different physiological parameter of a user, the plurality of sensors being disposed external to the user; and a processor in communication with the plurality of sensors and configured to analyze outputs of the plurality of sensors to detect meal intake by the user, the processor being further configured to trigger a controlled device to deliver a therapy to the user in response to meal intake detected by the processor, wherein the plurality of sensors includes an electromyograph and a microphone, and wherein the processor is configured to calculate an electromyograph index, an electromyograph threshold value, a microphone index, and a microphone threshold value, and to determine that; solid meal intake occurred when the electromyograph index exceeds the electromyograph threshold value; liquid meal intake occurred when the electromyograph index does not exceed the electromyograph threshold value and the microphone index exceeds the microphone threshold value; and no meal intake occurred when the electromyograph index does not exceed the electromyograph threshold value and the microphone index does not exceed the microphone threshold value.
-
-
14. A meal detection system, comprising:
-
a plurality of sensors, each configured to sense a different physiological parameter of a user, the plurality of sensors being disposed external to the user; and a processor in communication with the plurality of sensors and configured to analyze outputs of the plurality of sensors to detect meal intake by the user, the processor being further configured to trigger a controlled device to deliver a therapy to the user in response to meal intake detected by the processor, wherein the plurality of sensors includes an impedance sensor and a microphone, and wherein the processor is configured to calculate an impedance sensor index, an impedance sensor threshold value, a microphone index, and a microphone threshold value, and to determine that; solid meal intake occurred when the impedance sensor index exceeds the impedance sensor threshold value and the microphone index exceeds the microphone threshold value; liquid meal intake occurred when the impedance sensor index does not exceed the impedance sensor threshold value and the microphone index exceeds the microphone threshold value; and no meal intake occurred when the impedance sensor index does not exceed the impedance sensor threshold value and the microphone index does not exceed the microphone threshold value.
-
-
15. A medical method, comprising:
-
sensing a plurality of physiological parameters of a user using a plurality of sensors disposed externally to the user; using a processor in communication with the plurality of sensors, analyzing outputs of the plurality of sensors to detect meal intake by the user; and automatically triggering a controlled device to deliver a therapy to the user in response to meal intake detected by the processor; for each of the plurality of sensors, using the processor o calculate an index based on the output of the sensor and using the processor to determine that meal intake occurred when the index exceeds a threshold value; and using the processor to calculate the threshold value by processing a set of training data using an average harmonic mean algorithm, the training data including sensor data for at least one user and ground truth data for the at least one user. - View Dependent Claims (16, 17, 18)
-
Specification