SYSTEM AND METHOD FOR IDENTIFYING AUTOREGULATION ZONES

• US 20170105672A1
• Filed: 10/14/2016
• Published: 04/20/2017
• Est. Priority Date: 10/16/2015
• Status: Active Grant

• Current Assignee: Covidien LP (Medtronic Plc)
• Original Assignee: Covidien LP (Medtronic Plc)
• Inventors: Addison, Paul Stanley, Watson, James N., Montgomery, Dean
• Granted Patent: US 10,463,292 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/02028 Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/0261 using optical means, e.g. infrared light
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/14553 specially adapted for cerebral tissue
• CPC Class Codes: A61B 5/4064 Evaluating the brain A61B5/031, A61B5/369, A61B5/14553 take precedence
• CPC Class Codes: A61B 5/4076 Diagnosing or monitoring particular conditions of the nervous system A61B5/4821, A61B5/4824 take precedence
• CPC Class Codes: A61B 5/6801 specially adapted to be attached to or worn on the body surface
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G16H 20/40 relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
• 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 50/30 for calculating health indices; for individual health risk assessment

Abstract

A system configured to monitor autoregulation includes a medical sensor configured to be applied to a patient and to generate a regional oxygen saturation signal. The system includes a controller having a processor configured to receive the regional oxygen saturation signal and a blood pressure signal and to determine a cerebral oximetry index (COx) based on the blood pressure signal and the regional oxygen saturation signal. The processor is also configured to apply a data clustering algorithm to cluster COx data points over a range of blood pressures, identify a first cluster of COx data points that corresponds to an intact autoregulation zone for the patient, and provide a first output indicative of the intact autoregulation zone for the patient.

Claims

1. A system configured to monitor autoregulation comprising:

a medical sensor configured to be applied to a patient and to generate a regional oxygen saturation signal;

a controller comprising a processor configured to;

receive the regional oxygen saturation signal and a blood pressure signal;

determine a cerebral oximetry index (COx) based on the blood pressure signal and the regional oxygen saturation signal;

apply a data clustering algorithm to cluster COx data points over a range of blood pressures;

identify a first cluster of COx data points that corresponds to an intact autoregulation zone for the patient; and

provide a first output indicative of the intact autoregulation zone for the patient.

2. The system of claim 1, wherein the processor is configured to identify a second cluster of COx data points that corresponds to an impaired autoregulation zone for the patient and to provide a second output indicative of the impaired autoregulation zone for the patient.

3. The system of claim 1, wherein the processor is configured to identify a boundary between the first cluster and a second cluster and to provide a second output indicative of the boundary.

4. The system of claim 1, wherein the processor is configured to apply the data clustering algorithm in response to determination of a threshold number of COx data points.

5. The system of claim 1, wherein the data clustering algorithm comprises a k-means clustering algorithm.

6. The system of claim 1, wherein the data clustering algorithm comprises a Gaussian mixture model.

7. The system of claim 1, wherein the data clustering algorithm comprises one or more of a density-based spatial clustering of applications with noise (DB SCAN) clustering algorithm, principal component analysis (PCA), independent component analysis (ICA), linear discriminant analysis (LDA), learning vector quantization (LVQ), a self-organizing map (SOM or Kohonen net), or any combination thereof.

8. The system of claim 1, wherein the processor is configured to determine a target blood pressure based on a centroid of the first cluster.

9. The system of claim 1, comprising a blood pressure monitoring device configured to obtain the blood pressure signal from the patient.

10. A system configured to monitor autoregulation comprising:

a controller comprising a processor configured to;

receive a regional oxygen saturation signal and a blood pressure signal from one or more medical sensors;

determine a cerebral oximetry index (COx) based on the blood pressure signal and the regional oxygen saturation signal;

evaluate COx data points over a range of blood pressures; and

identify a first cluster of COx data points that corresponds to an intact autoregulation zone for the patient using a data clustering algorithm configured to cluster the COx data points over the range of blood pressures.

11. The system of claim 10, wherein the processor is configured to determine a target blood pressure based on a centroid of the first cluster.

12. The system of claim 10, wherein the data clustering algorithm comprises one or more of a k-means clustering algorithm, a Gaussian mixture model, a density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm, principal component analysis (PCA), independent component analysis (ICA), linear discriminant analysis (LDA), learning vector quantization (LVQ), a self-organizing map (SOM or Kohonen net), or any combination thereof

13. The system of claim 10, wherein the processor is configured to provide an output indicative of the intact autoregulation zone for the patient.

14. A method of monitoring autoregulation comprising:

receiving, at a processor, a regional oxygen saturation signal and a blood pressure signal from one or more medical sensors;

determining, using the processor, a cerebral oximetry index (COx) based on the blood pressure signal and the regional oxygen saturation signal;

evaluating, using the processor, COx data points over a range of blood pressures; and

identifying, using the processor, a first cluster of COx data points that corresponds to an intact autoregulation zone for the patient using a data clustering algorithm configured to cluster the COx data points over the range of blood pressures.

15. The method of claim 14, comprising providing a first output indicative of the intact autoregulation zone for the patient, using the processor.

16. The method of claim 14, comprising identifying a second cluster of COx data points that corresponds to an impaired autoregulation zone for the patient and providing a second output indicative of the impaired autoregulation zone for the patient, using the processor.

17. The method of claim 14, comprising identifying the first cluster of COx data points using the data clustering algorithm in response to determination of a threshold number of COx data points.

18. The method of claim 14, wherein the data clustering algorithm comprises one or more of a k-means clustering algorithm, a Gaussian mixture model, a density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm, principal component analysis (PCA), independent component analysis (ICA), linear discriminant analysis (LDA), learning vector quantization (LVQ), a self-organizing map (SOM or Kohonen net), or any combination thereof

19. The method of claim 14, comprising determining a target blood pressure based on a centroid of the first cluster, using the processor.

20. The method of claim 19, comprising providing a second output indicative of the target blood pressure, using the processor.