Analysis and characterization of patient signals

• US 10,278,595 B2
• Filed: 11/07/2017
• Issued: 05/07/2019
• Est. Priority Date: 12/05/2013
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Siemens Healthcare GMBH (Siemens AG)
• Inventors: Zhang, Hongxuan
• Primary Examiner(s): Winakur, Eric F
• Assistant Examiner(s): Fardanesh, Marjan
• Application Number:
  US15/806,043
• Publication Number:
  US 20180064354A1
• Time in Patent Office: 546 Days
• Field of Search: None
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 take precedence
• CPC Class Codes: A61B 5/14551 for measuring blood gases
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• 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

Abstract

Disclosed herein is a framework for facilitating patient signal analysis. In accordance with one aspect, first and second patient signal data are received from a patient monitor. The first and second patient signal data may then be segmented into respective first and second regions of interest, from which respective first and second waveform parameters may be extracted. One or more morphology indices may then be generated based on the first and second waveform parameters to compare shapes of the first and second regions of interest.

Claims

1. A computer-implemented method of patient signal analysis, comprising:

receiving over multiple successive cycles, from a patient monitor including a first sensor and a second sensor, a first and a second patient signal data, wherein the first patient signal data is a characterization of one of blood flow information and vessel circulation information and the second patient signal data is a characterization of one of blood flow information and vessel circulation information that is different from the first patient signal data characterization;

pre-processing the first and the second patient signal data by a patient signal analysis unit;

segmenting, by a processor, the pre-processed first and the second patient signal data into respective first and second regions of interest;

extracting, by the processor, a respective first and a respective second waveform parameters from the first and the second regions of interest; and

generating, by the processor, one or more respective morphology indices based on the respective first and the respective second waveform parameters over the multiple successive cycles;

comparing, by the processor, shapes of the one or more respective morphology indices to detect at least one of a change due to cardiac blood flow functionality and vessel abnormality;

determining, by the processor, whether an abnormality exists in at least one of the first and the second patient signal data based on the results of the comparison of the one or more respective morphology indices; and

if an abnormality is determined, generating, by the patient signal analysis unit, a patient report alert on the multi-channel patient monitor.

2. The method of claim 1 wherein the first and the second waveform parameters comprise a first and a second amplitude data series.

3. The method of claim 2 wherein the one or more morphology indices are generated based on the first and the second amplitude data series.

4. The method of claim 2 wherein the one or more morphology indices comprise one or more mutual entropy values.

5. The method of claim 1 wherein the first and the second waveform parameters comprise a first and a second set of time points associated with key amplitude points.

6. The method of claim 5 wherein the key amplitude points include at least one maximum amplitude, at least one minimum amplitude and at least one local amplitude turning point.

7. The method of claim 5 wherein the one or more morphology indices comprise one or more unilateral or bilateral time duration ratios.

8. The method of claim 5 wherein the one or more morphology indices comprise one or more unilateral or bilateral time duration averaging ratios.

9. The method of claim 5 wherein the one or more morphology indices comprise one or more unilateral or bilateral time duration variability ratios.

10. The method of claim 5 wherein the one or more morphology indices comprise one or more unilateral or bilateral energy duration ratios.

11. The method of claim 5 wherein the one or more morphology indices comprise one or more unilateral or bilateral energy duration averaging ratios.

12. The method of claim 5 wherein the one or more morphology indices comprise one or more unilateral or bilateral energy variability ratios.

13. The method of claim 5 wherein the one or more morphology indices comprise one or more cross mutual time delays.

14. The method of claim 5 wherein the one or more morphology indices comprise one or more cross mutual time delay ratios.

15. The method of claim 5 wherein the one or more morphology indices comprise one or more cross mutual time delay variabilities.

16. The method of claim 1 further comprising non-linearly combining, via an artificial neural network structure, the one or more morphology indices with input patient data.

17. The method of claim 1, the blood flow information and the vessel circulation information each being one of respiration, blood flow sound, electrocardiography, intra-cardiac electro-gram, heart sound, and muscle contracting force signals.

18. The method of claim 1, the one or more morphology indices being one of morphology distribution ratios, mutual entropy values, unilateral ratios, bilateral ratios, and a combination thereof.

19. The method of claim 1, the patent report alert including a patient health status report resulting from combining one or more of the respective morphology indices with at least one of associated statistical parameters, demographic data, hemodynamic data, electrophysiological data, and vital sign data.