Personalized parameter modeling with signal calibration based on historical data

• US 10,543,314 B2
• Filed: 08/18/2016
• Issued: 01/28/2020
• Est. Priority Date: 08/21/2015
• Status: Active Grant

• Current Assignee: Medtronic Minimed Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Minimed Incorporated (Medtronic Plc)
• Inventors: Varsavsky, Andrea, Lu, Yunfeng, Nogueira, Keith, Nishida, Jeffrey
• Primary Examiner(s): Vanni, G Steven
• Application Number:
  US15/240,733
• Publication Number:
  US 20170049964A1
• Time in Patent Office: 1,258 Days
• Field of Search: None
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/4839 combined with drug delivery
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• CPC Class Codes: A61B 5/7242 using integration
• CPC Class Codes: A61M 2205/3569 sublocal, e.g. between console and disposable
• CPC Class Codes: A61M 2205/502 User interfaces, e.g. screens or keyboards
• CPC Class Codes: A61M 2205/52 with memories providing a history of measured variating parameters of apparatus or patient
• CPC Class Codes: A61M 2205/70 with testing or calibration facilities
• CPC Class Codes: A61M 2230/005 Parameter used as control input for the apparatus
• CPC Class Codes: A61M 2230/06 Heartbeat rate only
• CPC Class Codes: A61M 2230/201 Glucose concentration
• CPC Class Codes: A61M 5/14244 adapted to be carried by the patient, e.g. portable on the body
• CPC Class Codes: A61M 5/1723 using feedback of body parameters, e.g. blood-sugar, pressure measurement of body parameters A61B5/00
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 40/40 : for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
• CPC Class Codes: G16H 40/63 : for local operation
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 : for simulation or modelling of medical disorders

Abstract

Medical devices and related patient management systems and parameter modeling methods are provided. An exemplary method involves obtaining, by a computing device, historical measurements of a condition in a body of the patient previously provided by a sensing device, obtaining, by the computing device, historical operational context information associated with preceding operation of one or more of an infusion device and the sensing device, obtaining, by the computing device, historical values for a parameter from one or more of the infusion device and the sensing device, determining, by the computing device a patient-specific model of the parameter based on relationships between the historical measurements, the historical operational context information and the historical values, and providing, by the computing device via a network, the patient-specific model to one of the infusion device, the sensing device or a client device.

Claims

1. A method comprising:

obtaining, by a remote server from a database, historical measurements of a physiological condition in a body of a patient previously provided by a sensing device including a sensing element configured to provide electrical signals having a signal characteristic indicative of the physiological condition in the body of the patient;

obtaining, by the remote server from the database, historical operational context information associated with preceding operation of the sensing device;

obtaining, by the remote server from the database, historical calibration factor values;

determining, by the remote server, a patient-specific calibration factor model based on relationships between the historical measurements, the historical operational context information and the historical calibration factor values; and

providing, by the remote server via a network, the patient-specific calibration factor model to the sensing device, wherein the sensing device calculates an expected calibration factor value using the patient-specific calibration factor model, converts subsequent electrical signals from the sensing element into calibrated measurement values for the physiological condition in the body of the patient using the expected calibration factor value, and outputs the calibrated measurement values.

2. The method of claim 1, further comprising obtaining, by the remote server, historical delivery information for fluid influencing the physiological condition previously delivered to the body of the patient by an infusion device, wherein determining the patient-specific calibration factor model comprises determining the patient-specific calibration factor model based on relationships between the historical measurements, the historical delivery information, the historical operational context information and the historical calibration factor values.

3. The method of claim 1, wherein determining the patient-specific calibration factor model comprises:

identifying a subset of predictive variables for a calibration factor from among the historical measurements and the historical operational context information based on correlations between the subset of predictive variables and the historical calibration factor values; and

determining the patient-specific calibration factor model as a function of the subset of predictive variables based on historical values for the subset of predictive variables and the historical calibration factor values.

4. A non-transitory computer-readable medium having instructions stored thereon that are executable by a processing system of the remote server to perform the method of claim 1.

5. The method of claim 1, further comprising obtaining, by the remote server from the database, historical reference measurements corresponding to the historical calibration factor values, wherein determining the patient-specific calibration factor model comprises determining the patient-specific calibration factor model based at least in part on the historical reference measurements corresponding to the historical calibration factor values.

6. The method of claim 5, wherein the historical measurements comprise measurement signal values corresponding to the historical reference measurements used to calculate the historical calibration factor values.

7. The method of claim 1, wherein the patient-specific calibration factor model indicates predictive variables for calculating the expected calibration factor value for the patient.

8. The method of claim 7, wherein the predictive variables include at least one of a current sensor site location, a current body mass index of the patient, a gender of the patient, and a current time of day.

9. The method of claim 7, wherein the patient-specific calibration factor model indicates relative weightings associated with the predictive variables.

10. The method of claim 9, wherein determining the patient-specific calibration factor model comprises the remote server utilizing machine learning to determine the predictive variables correlative to or predictive of the historical calibration factor values and determining an equation for calculating the expected calibration factor value based on the predictive variables using the relative weightings.

11. The method of claim 1, wherein determining the patient-specific calibration factor model comprises the remote server utilizing machine learning to determine an equation for calculating the expected calibration factor value.

12. A system comprising:

a database configured to store historical measurements of a physiological condition in a body of a patient, historical delivery information for fluid influencing the physiological condition previously delivered to the body of the patient, historical operational context information associated with the patient, and historical calibration factor values associated with the patient; and

a remote server coupled to the database and a network and programmed to determine a patient-specific calibration factor model based on relationships between the historical measurements, the historical delivery information, the historical operational context information and the historical calibration factor values and provide the patient-specific calibration factor model to a sensing device via the network, wherein the sensing device is configured to calculate an expected calibration factor value using the patient-specific calibration factor model, convert electrical signals having a signal characteristic indicative of the physiological condition in the body of the patient into calibrated measurement values using the expected calibration factor value, and outputs the calibrated measurement values.

13. The system of claim 12, wherein the historical measurements comprise measurement signal values and corresponding historical reference measurements used to calculate the historical calibration factor values.

14. The system of claim 12, wherein the patient-specific calibration factor model indicates predictive variables for calculating the expected calibration factor value for the patient.

15. The system of claim 14, wherein the predictive variables include at least one of a current sensor site location, a current body mass index of the patient, a gender of the patient, and a current time of day.

16. The system of claim 14, wherein the patient-specific calibration factor model indicates relative weightings associated with the predictive variables.

17. A system comprising:

a sensing device communicatively coupled to a network, the sensing device including a sensing element configured to provide electrical signals having a signal characteristic indicative of a physiological condition in a body of a patient;

a database configured to store historical measurements of the physiological condition in the body of the patient from the sensing device, historical operational context information associated with the patient, and historical calibration factor values associated with the patient; and

a remote server coupled to the database and the network and programmed to determine a patient-specific calibration factor model based on relationships between the historical measurements, the historical operational context information and the historical calibration factor values and provide the patient-specific calibration factor model to the sensing device via the network, wherein subsequent output from the sensing device comprises a calibrated measurement value determined based on one or more electrical signals provided by the sensing element and an expected calibration factor determined using the patient-specific calibration factor model.

18. The system of claim 17, wherein the historical measurements comprise measurement signal values and corresponding historical reference measurements used to calculate the historical calibration factor values.

19. The system of claim 17, wherein the patient-specific calibration factor model indicates predictive variables for calculating the expected calibration factor value for the patient.