METHOD FOR IMPROVED OXYGEN SATURATION ESTIMATION IN THE PRESENCE OF NOISE

• US 20090326348A1
• Filed: 06/30/2008
• Published: 12/31/2009
• Est. Priority Date: 06/30/2008
• Status: Active Grant

• Current Assignee: Covidien LP (Medtronic Plc)
• Original Assignee: Covidien LP (Medtronic Plc)
• Inventors: Baker, Clark R. JR.
• Granted Patent: US 8,862,194 B2
• Time in Patent Office: Days
• US Class Current: 600/323
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• 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 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/7405 using sound
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/7455 characterised by tactile indication, e.g. vibration or electrical stimulation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The present disclosure relates, according to some embodiments, to devices, systems, and methods for estimating a physiological parameter in the presence of noise. For example, the disclosure relates, in some embodiments, to devices, systems, and methods for assessing (erg., estimating, measuring, calculating) oxygen saturation (SpO2). Methods of assessing SpO2 may include assessing a noise metric associated with motion artifact. In some embodiments, a percentage (e.g., an empirically determined percentage) of a noise metric may be simply added to the SpO2 estimate to produce a corrected SpO2 estimate. An oximetry algorithm may include, according to some embodiments, combining multiple internal SpO2 estimates and associated noise and/or signal quality metrics (e.g., using a radial basis neural network) to produce a modified (e.g., corrected) SpO2 estimate (e.g., rather than merely selecting the estimate from a finite number of candidates). A modified SpO2 estimate may include little or no movement-based error.

Claims

1. A device for estimating oxygen saturation in the presence of noise, the device comprising:

a processor in communication with a radial basis neural network, wherein the processor is configured to receive optical oximetry data, process the optical oximetry data to produce at least one oxygen saturation estimate, communicate the at least one oxygen saturation estimate to the radial basis neural network, and receive a modified oxygen saturation estimate comprising less noise bias than the at least one oxygen saturation estimate from the radial basis neural network, wherein the radial basis neural network is configured to define the modified oxygen saturation estimate based at least in part on combining the at least one oxygen saturation estimate with corresponding signal quality metrics; and

a display in communication with the processor, wherein the display is operable to display a representation of the modified oxygen saturation estimate.

2. The device of claim 1, wherein the radial basis neural network comprises a single-hidden-layer network.

3. The device of claim 1, comprising a pulse oximeter.

4. The device of claim 1, wherein the radial basis neural network is configured to define the modified oxygen saturation estimate based at least in part on combining the at least one oxygen saturation estimate with one or more additional oxygen saturation estimates.

5. The device of claim 4, wherein the modified oxygen saturation estimate has a value that is not between the values of the at least one oxygen saturation estimate and the one or more additional oxygen saturation estimates.

6. A method for estimating oxygen saturation in the presence of noise) the method comprising:

determining a change in estimated oxygen saturation comprising calculating a difference between a first estimated oxygen saturation value at a first time and a second estimated oxygen saturation value at a second time;

.

determining a change in a saturation noise estimate between a first saturation noise estimate and a second saturation noise estimate, wherein the change in the saturation noise estimate attends the change in estimated oxygen saturation;

displaying either the first estimated oxygen saturation value or the second oxygen saturation value based at least in part on a comparison between the change in the estimated oxygen saturation and the change in the saturation noise estimate.

7. The method of claim 6, wherein the comparison between the change in the estimated oxygen saturation and the change in the saturation noise estimate comprises determining whether the change in the estimated oxygen saturation is at least a certain percentage larger than the change in the saturation noise estimate.

8. The method of claim 7, wherein the comparison between the change in the estimated oxygen saturation and the change in the saturation noise estimate comprises determining whether the change in the estimated oxygen saturation is at least one hundred percent larger than the change in the saturation noise estimate.

9. The method of claim 8, comprising displaying the first estimated oxygen saturation value if the change in the estimated oxygen saturation is less than one hundred percent larger than the change in the saturation noise estimate.

10. The method of claim 8, comprising displaying the second estimated oxygen saturation value if the change in the estimated oxygen saturation is equal to or greater than one hundred percent larger than the change in the saturation noise estimate.

11. A method for reducing affects of noise in an oxygen saturation estimate, the method comprising:

solving a computer-implemented radial basis neural network using a training set of oxygen saturation estimates, wherein the training set of oxygen saturation estimates include a target saturation estimate from noise-free data, a noise-perturbed saturation estimate, and metrics associated with calculating the noise-perturbed saturation estimate; and

processing at least one test oxygen saturation estimate that is biased by noise using the computer-implemented radial basis neural network to produce a modified test oxygen saturation estimate comprising less noise bias than the at least one test oxygen saturation estimate.

12. The method of claim I1, wherein the computer-implemented radial basis neural network comprises a single-hidden-layer network with n unique inputs, m nodes in a hidden layer, and a single linear node in an output layer.

13. The method of claim 12, wherein the m nodes include an output defined by:

y=F(b*distance(x₁ . . . x_n, w₁ . . . w_n)),

where x₁. . . x_n denotes the n unique inputs,

w₁ . . . w_n denotes weights of each of the n unique inputs, respectively,

b is bias,

distance ( ) is the distance between the x and it, vectors in an n-dimensional space, and F(X)=e<sup>−

x2</sup>.

14. The method of claim 13, comprising setting b to a value of from about 5% oxygen saturation to about 10% oxygen saturation.

15. The method of claim 13, comprising setting h to a value of from about 1% oxygen saturation to about 5% oxygen saturation.

16. A method of detecting hypoxia in a subject, the method comprising:

collecting optical oximetry data from a subject;

processing the optical oximetry data to produce at least one oxygen saturation estimate;

processing the at least one oxygen saturation estimate using a solved, computer-implemented radial basis neural network to produce at least one modified oxygen saturation estimate; and

comparing the at least one modified oxygen saturation estimate with a hypoxia oxygen saturation threshold.

17. The method of claim 16, comprising initiating an alarm if the at least one modified oxygen saturation estimate is less than or equal to the hypoxia oxygen saturation threshold.

18. The method of claim 17, wherein the alarm comprises a visible alert.

19. The method of claim 17, wherein the alarm comprises an audible alert.

20. The method of claim 17, wherein the alarm comprises a tactile alert.

21. The method of claim 16, wherein the solved, computer-implemented radial basis neural network comprises a single-hidden-layer network.