Methods and systems for real-time sensor measurement simulation

Patent metadata

Field	Value
Publication number	US-12119119-B2
Application number	US-202016848695-A
Country	US
Kind code	B2
Filing date	Apr 14, 2020
Priority date	Dec 9, 2019
Publication date	Oct 15, 2024
Grant date	Oct 15, 2024

Abstract

Medical devices and related systems and methods are provided. A method of estimating a physiological condition using a first sensing arrangement involves obtaining a sensor translation model associated with a relationship between the first sensing arrangement and a second sensing arrangement, wherein the second sensing arrangement is different from the first sensing arrangement, obtaining one or more measurements from a sensing element coupled to the processing system of the first sensing arrangement, determining simulated measurement data for the second sensing arrangement by applying the sensor translation model to the one or more measurements from the sensing element of the first sensing arrangement, and determining an estimated value for the physiological condition by applying an estimation model associated with the second sensing arrangement to the simulated measurement data.

First claim

What is claimed is:

1. A method of estimating a physiological condition using data associated with different sensing arrangements, the method comprising:
obtaining, by a processing system, a sensor translation model associated with a relationship between a first sensing arrangement and a second sensing arrangement, wherein:
the first sensing arrangement comprises a first sensing element configured to measure the physiological condition,
the second sensing arrangement comprises a second sensing element configured to measure the same physiological condition, and
the sensor translation model is based on measurements from the first sensing element and corresponding measurements from the second sensing element;

obtaining, by the processing system, one or more measurements from the first sensing element in a first instance of the first sensing arrangement;
determining, by the processing system, simulated measurement data for the second sensing arrangement by applying the sensor translation model to the one or more measurements from the first sensing element in the first instance of the first sensing arrangement, wherein the simulated measurement data represents one or more measurements that the second sensing element of the second sensing arrangement would output in response to a value of the physiological condition that resulted in the one or more measurements from the first sensing element in the first instance of the first sensing arrangement; and
determining, by the processing system, an estimated value of the physiological condition by applying an estimation model associated with the second sensing arrangement to the simulated measurement data, wherein the estimation model is different from the sensor translation model.

2. The method of claim 1 , wherein obtaining the sensor translation model comprises:
obtaining first measurement data from different instances of the first sensing arrangement;
obtaining second measurement data from different instances of the second sensing arrangement concurrent to the first measurement data; and
determining the sensor translation model based on relationships between the first measurement data and the second measurement data.

3. The method of claim 2 , wherein determining the sensor translation model comprises training the sensor translation model using the first measurement data and the second measurement data as inputs to the sensor translation model.

4. The method of claim 2 , wherein determining the sensor translation model comprises determining the sensor translation model based on relationships between the first measurement data and the second measurement data, using a series of invertible, memory-less transforms to shift sensing signals between a first domain associated with the first sensing arrangement and a second domain associated with the second sensing arrangement.

5. The method of claim 2 , wherein determining the sensor translation model comprises determining the sensor translation model based on relationships between the first measurement data and the second measurement data using a concatenative modeling technique.

6. The method of claim 1 , further comprising downloading, by the processing system, the estimation model associated with the second sensing arrangement from a remote server via a network.

7. The method of claim 6 , wherein obtaining the sensor translation model comprises downloading, by the processing system, the sensor translation model from the remote server via the network.

8. The method of claim 1 , further comprising outputting, by the processing system, the estimated value of the physiological condition.

9. The method of claim 1 , wherein the first sensing arrangement comprises a new sensing arrangement influenced by the physiological condition and the second sensing arrangement comprises a legacy sensing arrangement influenced by the physiological condition.

10. The method of claim 9 , wherein:
the physiological condition comprises a glucose level;
the new sensing arrangement comprises a new glucose sensor;
the legacy sensing arrangement comprises a legacy glucose sensor; and
the estimation model comprises a sensor glucose estimation model associated with the legacy glucose sensor.

11. The method of claim 1 , wherein the first sensing arrangement comprises a template sensing device influenced by the physiological condition and the second sensing arrangement comprises a target sensing device influenced by the physiological condition, and wherein the method further comprises:
obtaining first measurement data from different instances of the template sensing device;
obtaining second measurement data from different instances of the target sensing device concurrent to the first measurement data, wherein respective sets of the first measurement data and the second measurement data are concurrently obtained from a respective common patient using respective instances of the template sensing device and the target sensing device; and
determining the sensor translation model based at least in part on relationships between the first measurement data and the second measurement data.

12. The method of claim 11 , further comprising:
obtaining reference values for the physiological condition together with third measurement data associated with the reference values, wherein the third measurement data comprises historical measurements from additional instances of the target sensing device; and
training the estimation model using the third measurement data as an input to the estimation model and the reference values as an output of the estimation model.

13. The method of claim 11 , wherein determining the sensor translation model comprises training the sensor translation model using the first measurement data as an input to the sensor translation model and using the second measurement data as an output of the sensor translation model.

14. The method of claim 11 , wherein determining the sensor translation model comprises determining the sensor translation model based on relationships between the first measurement data and the second measurement data, using a series of invertible, memory-less transforms to shift sensing signals from a first domain associated with the first sensing arrangement to a second domain associated with the second sensing arrangement.

15. The method of claim 11 , wherein determining the sensor translation model comprises determining the sensor translation model based on relationships between the first measurement data and the second measurement data using a concatenative modeling technique.

16. The method of claim 1 , wherein the first sensing arrangement comprises a legacy sensing arrangement influenced by the physiological condition and the second sensing arrangement comprises a new sensing arrangement influenced by the physiological condition.

17. The method of claim 16 , wherein:
the physiological condition comprises a glucose level;
the new sensing arrangement comprises a new glucose sensor;
the legacy sensing arrangement comprises a legacy glucose sensor; and
the estimation model comprises a sensor glucose estimation model associated with the new glucose sensor.

18. The method of claim 1 , further comprising determining a delivery command for operating an actuation arrangement of an infusion device based at least in part on the estimated value of the physiological condition.

19. The method of claim 1 , wherein the one or more measurements from the first sensing element in the first instance of the first sensing arrangement comprise at

Assignees

• Medtronic Minimed Inc

Inventors

• Gee Elaine
• Ajemba Peter
• Engheta Bahman
• Nishida Jeffrey
• Varsavsky Andrea
• Nogueira Keith

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/0475

  Generative networks · CPC title

• G06N3/094

  Adversarial learning · CPC title

• A61B5/1495

  Calibrating or testing of in-vivo probes · CPC title