Determination Of A Physiological Parameter

• US 20110071376A1
• Filed: 08/16/2010
• Published: 03/24/2011
• Est. Priority Date: 09/24/2009
• Status: Active Grant

• Current Assignee: Covidien LP (Medtronic Plc)
• Original Assignee: Nellcor Puritan Bennett LLC (Medtronic Plc)
• Inventors: McKenna, Edward M.
• Granted Patent: US 8,855,749 B2
• Time in Patent Office: Days
• US Class Current: 600/336
• CPC Class Codes: A61B 5/0015 characterised by features of the telemetry system
• CPC Class Codes: A61B 5/1455 using optical sensors, e.g. spectral photometrical oximeters
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 2218/18 by plotting the signal segments against each other, e.g. analysing scattergrams
• CPC Class Codes: G16B 40/00 ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
• CPC Class Codes: G16B 40/10 Signal processing, e.g. from mass spectrometry [MS] or from PCR
• CPC Class Codes: G16B 40/20 Supervised data analysis
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/40 for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Methods and systems are provided for analyzing a physiological signal by applying a continuous wavelet transform on the signal and comparing the wavelet transformation to a library of wavelet signatures corresponding to one or more physiological conditions and/or patient conditions. A pulse oximeter system may relate the wavelet transformation with one or more of the wavelet signatures based on filters and/or thresholds, and may determine that the wavelet transformation indicates that the patient of the physiological signal has a physiological condition indicated by the related wavelet signature. In some embodiments, the pulse oximeter system may use previous analyses in a neural network to update the library. Further, non-physiological components of the wavelet transformation may also be identified and removed.

Claims

1. A method for diagnosing a condition, comprising using a processor:

processing a physiological signal from a patient using a continuous wavelet transform;

comparing a result of the continuous wavelet transform to a library comprising a plurality of wavelet signatures categorized based on different respective physiological conditions and patient characteristics to determine physiological information of the patient; and

displaying an output related to the physiological information.

2. The method, as set forth in claim 1, wherein the wavelet transform comprises a Morelet wavelet.

3. The method, as set forth in claim 1, wherein the physiological information comprises a pulse rate and/or an oxygen saturation measurement.

4. The method, as set forth in claim 1, wherein the physiological information comprises a diagnosis, a recommendation comprising one or more of an alert and a recommendation for improving a measurement of the physiological signal, or both a diagnosis and a recommendation.

5. The method, as set forth in claim 1, wherein the different respective physiological conditions comprise one or more of disease states or pharmacological states.

6. The method, as set forth in claim 1, wherein comparing the result comprises:

cross-correlating the image with a wavelet signature in the library to produce a cross-correlated image; and

determining whether the image representation substantially includes the pattern based on the cross-correlated image.

7. The method, as set forth in claim 6, wherein determining whether the image representation substantially includes the pattern is based on comparing the spectral intensity of the cross correlated image to a threshold intensity.

8. The method, as set forth in claim 1, wherein comparing the results comprises matching a respective filter derived for each wavelet signature in the library to a corresponding region of the result.

9. The method, as set forth in claim 1, wherein comparing the results comprises deriving a correlation value between the result and the plurality of wavelet signatures in the library.

10. The method, as set forth in claim 1, comprising:

utilizing the physiological information in a learning based algorithm; and

updating the library based on the physiological information and the learning based algorithm, wherein comparing the result comprises comparing the continuous wavelet transform to the updated library.

11. A method for generating a data library, comprising the acts of:

acquiring a plurality of physiological signals associated with a physiological condition of a patient;

performing a continuous wavelet transform on each physiological signal to generate a respective wavelet transform product for each physiological signal;

organizing the wavelet transform products so that the wavelet transform products may be searched using a current wavelet transform product derived from a current physiological signal.

12. The method, as set forth in claim 11, wherein acquiring the plurality of physiological signals comprises acquiring the wavelet transform products.

13. The method, as set forth in claim 11, comprising saving the wavelet transform products to the data library.

14. The method, as set forth in claim 11, wherein the physiological condition of the patient comprises one or more of patient physiological data, recommendations, diagnoses, and patient characteristics.

15. The method, as set forth in claim 11, comprising organizing the wavelet transform products based on one or more of patient physiological data, recommendations, diagnoses, and patient characteristics.

16. A monitor, comprising:

a display;

a connector port capable of receiving a signal generated by a pulse oximetry sensor; and

data processing circuitry capable of generating a physiological waveform in response to the signal, applying a continuous wavelet transform to the physiological waveform, comparing a result of the continuous wavelet transform to a library of wavelet signatures, and generating one or more physiological data based on the comparison.

17. The monitor of claim 16, wherein the library of wavelet signatures is categorized based on different respective patient characteristics and physiological conditions.

18. The monitor of claim 16, wherein the result of the continuous wavelet transform is compared to wavelet signatures in the library based on characteristics of a patient using the pulse oximeter.

19. The monitor of claim 16, wherein the result of the continuous wavelet transform comprises a scalogram comprising a spectral density of the signal with respect to frequency and time.

20. The monitor of claim 16, wherein the data processing circuitry is capable of modifying the library based on one or more of the result of the continuous wavelet transform and the physiological data.

21. The monitor of claim 16, wherein the data processing circuitry is capable of executing supervised learning algorithms based on one or more of the result of the continuous wavelet transform and the physiological data.