Determination of a physiological parameter

• US 8,855,749 B2
• Filed: 08/16/2010
• Issued: 10/07/2014
• Est. Priority Date: 09/24/2009
• Status: Active Grant

• Current Assignee: Covidien LP (Medtronic Plc)
• Original Assignee: Covidien LP (Medtronic Plc)
• Inventors: McKenna, Edward M.
• Primary Examiner(s): Le, Long V.
• Assistant Examiner(s): KELLOGG, MICHAEL S
• Application Number:
  US12/856,801
• Publication Number:
  US 20110071376A1
• Time in Patent Office: 1,513 Days
• Field of Search: 600/473, 600/310, 600/323, 600/475, 600/476, 600/477
• US Class Current: 600/473
• 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 assessing a plethysmography signal to provide an output related to a physiological condition, comprising using a processor of a pulse oximeter monitor to perform the steps of:

receiving the plethysmography signal from a pulse oximeter sensor applied to a patient, wherein the pulse oximeter sensor comprises an encoder configured to transmit information indicative of a type of the pulse oximeter sensor to the pulse oximeter monitor;

processing the plethysmography signal using a continuous wavelet transform;

comparing a result of the continuous wavelet transform to a library comprising a plurality of wavelet signatures, the plurality of wavelet signatures comprising previously-determined patterns that correspond to physiological conditions and being categorized based on characteristics of a pulse oximeter system;

identifying one or more wavelet signatures of the plurality of wavelet signatures in the library that have sensor specifications similar to the pulse oximeter sensor, wherein comparing the result comprises comparing the result to the one or more identified wavelet signatures to determine the physiological condition of the patient; and

displaying the output related to the physiological condition of the patient.

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

3. The method, as set forth in claim 1, wherein the output related to the physiological condition comprises one or more of a diagnosis, a first recommendation comprising an alert, or a second recommendation for improving a measurement of the physiological signal.

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

5. The method, as set forth in claim 1, wherein comparing the result comprises filtering the result to determine whether the result meets a threshold level of correlation with the one or more identified wavelet signatures of the plurality of wavelet signatures in the library.

6. The method, as set forth in claim 1, wherein comparing the result comprises deriving a correlation value between the result and the one or more identified wavelet signatures of the plurality of wavelet signatures in the library.

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

utilizing the result and the determined physiological condition in a learning based algorithm; and

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

8. The method, as set forth in claim 1, wherein the result of the continuous wavelet transform comprises a scalogram comprising a spectral density of the signal with respect to frequency and time.

18. The method, as set forth in claim 1, wherein the characteristics of the pulse oximeter system comprise one or more of a sensor type or a sensor placement.

9. A method for assessing a plethysmography signal to provide an output related to a physiological condition, comprising using a processor of a pulse oximeter monitor to perform the steps of:

receiving the plethysmography signal from a pulse oximeter sensor applied to a patient, wherein the pulse oximeter sensor comprises an encoder configured to provide information indicative of the type of pulse oximeter sensor to the pulse oximeter monitor;

processing the plethysmography signal using a continuous wavelet transform;

accessing a plurality of wavelet signatures comprising previously determined features that correspond to a plurality of physiological conditions;

identifying one of more wavelet signatures of the plurality of wavelet signatures that have a sensor type similar to the pulse oximeter sensor;

comparing a result of the continuous wavelet transform to the one or more identified wavelet signatures to determine a physiological condition of the patient; and

displaying the output related to the physiological condition of the patient.

10. The method, as set forth in claim 9, wherein the wavelet transform comprises a Morlet wavelet.

11. The method, as set forth in claim 9, wherein the output related to the physiological condition comprises one or more of a diagnosis, a first recommendation comprising an alert, or a second recommendation for improving a measurement of the physiological signal.

12. The method, as set forth in claim 9, wherein the plurality of physiological conditions comprise one or more disease states.

13. The method, as set forth in claim 9, wherein the result of the continuous wavelet transform comprises a scalogram comprising a spectral density of the signal with respect to frequency and time.

14. The method, as set forth in claim 9, comprising updating the library based on one or more of the result or the determined physiological condition.

15. The method, as set forth in claim 9, wherein comparing the result comprises:

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

determining whether the result meets a threshold level of correlation with the wavelet signature based on the cross-correlated image.

16. The method, as set forth in claim 15, wherein determining whether the result meets the threshold level of correlation is based on comparing a spectral intensity of the cross-correlated image to a threshold intensity.

17. The method, as set forth in claim 9, wherein comparing the result comprises filtering the result to determine whether the result meets a threshold level of correlation with the wavelet signature.