Patient signal analysis and characterization

• US 9,020,583 B2
• Filed: 02/26/2014
• Issued: 04/28/2015
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhang, Hongxuan
• Primary Examiner(s): Schaetzle, Kennedy
• Application Number:
  US14/190,276
• Publication Number:
  US 20140276156A1
• Time in Patent Office: 426 Days
• Field of Search: None
• US Class Current: 600/517
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/353 Detecting P-waves
• CPC Class Codes: A61B 5/361 Detecting fibrillation
• CPC Class Codes: A61B 5/366 Detecting abnormal QRS complex, e.g. widening
• 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: A61N 1/3621 for treating or preventing abnormally high heart rate
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Disclosed herein is a framework for facilitating patient signal analysis. In accordance with one aspect, at least one region of interest within a cycle of a waveform of patient signal data is identified. The identified region of interest may be segmented into portions using amplitude percentage categories. A sequential morphological data series may be generated by compiling time intervals of the segmented portions. One or more sequential signal parameters may be calculated based on the sequential morphological data series. A report may then be generated based at least in part on the one or more sequential signal parameters.

Claims

1. A method of patient signal analysis, comprising:

receiving patient signal data;

identifying at least one region of interest within a cycle of a waveform of the patient signal data;

segmenting the identified region of interest into portions using amplitude percentage categories;

generating a sequential morphological data series by compiling time intervals of the segmented portions;

calculating one or more sequential signal parameters based on the sequential morphological data series; and

generating a report based at least in part on the one or more sequential signal parameters.

2. The method of claim 1 wherein receiving patient signal data comprises receiving electrophysiological signal data that indicate electrical activity of a patient'"'"'s heart over multiple heart cycles.

3. The method of claim 1 wherein the region of interest comprises a QRS complex segment, an ST segment, a P wave, a R wave, a T wave, a Q wave, an S wave, or a combination thereof.

4. The method of claim 1 further comprising deriving the amplitude percentage categories from at least one corresponding reference region of interest of a reference signal.

5. The method of claim 4 wherein deriving the amplitude percentage categories comprises:

determining a maximum amplitude of the reference region of interest; and

defining the amplitude percentage categories based on percentages of the maximum amplitude.

6. The method of claim 4 wherein deriving the amplitude percentage categories comprises:

determining an average maximum amplitude of multiple reference regions of interest of the reference signal; and

defining the amplitude percentage categories based on percentages of the average maximum amplitude.

7. The method of claim 1 wherein calculating the one or more sequential signal parameters comprises calculating a sequential unilateral ratio.

8. The method of claim 1 wherein calculating the one or more sequential signal parameters comprises calculating a sequential cross unilateral ratio.

9. The method of claim 1 wherein calculating the one or more sequential signal parameters comprises calculating a sequential bilateral ratio.

10. The method of claim 1 wherein calculating the one or more sequential signal parameters comprises calculating a sequential cross bilateral ratio.

11. The method of claim 1 wherein calculating the one or more sequential signal parameters comprises calculating a multi-ratio combination integrated index based on at least two of sequential unilateral ratio, sequential cross unilateral ratio, sequential bilateral ratio and sequential cross bilateral ratio.

12. The method of claim 1 further comprising performing statistical analysis on a series of the one or more sequential signal parameters.

13. The method of claim 12 wherein performing statistical analysis comprises generating a mean value, a standard deviation, a variation, a variability, or a combination thereof of the series of the one or more sequential signal parameters.

14. The method of claim 1 further comprising generating a health status or treatment suggestion based at least in part on the one or more sequential signal parameters.

15. The method of claim 14 wherein generating the health status or treatment suggestion comprises combining, via an artificial neural network, different types of sequential signal parameters to generate the health status or treatment suggestion.

16. The method of claim 14 wherein generating the health status or treatment suggestion comprises combining, via an artificial neural network, the one or more sequential signal parameters with other input patient data to generate the health status or treatment suggestion.

17. The method of claim 1 further comprising adaptively adjusting coefficients for use in calculating the one or more sequential signal parameters.

18. The method of claim 1 wherein generating the report based at least in part on the one or more sequential signal parameters comprises generating the report indicating characteristics of cardiac arrhythmia.

19. A non-transitory computer readable medium embodying a program of instructions executable by machine to perform steps for heart function analysis, the steps comprising:

receiving patient signal data;

identifying at least one region of interest within a cycle of a waveform of the patient signal data;

segmenting the identified region of interest into portions using amplitude percentage categories;

generating a sequential morphological data series by compiling time intervals of the segmented portions;

calculating one or more sequential signal parameters based on the sequential morphological data series; and

characterizing cardiac arrhythmia based at least in part on the one or more sequential signal parameters.

20. A system for patient signal analysis, comprising:

a non-transitory memory device for storing computer readable program code; and

a processor in communication with the memory device, the processor being operative with the computer readable program code to perform steps comprising;

receiving patient signal data;

identifying at least one region of interest within a cycle of a waveform of the patient signal data;

segmenting the identified region of interest into portions using amplitude percentage categories;

generating a sequential morphological data series by compiling time intervals of the segmented portions;

calculating one or more sequential signal parameters based on the sequential morphological data series; and

generating a report based at least in part on the one or more sequential signal parameters.