Matrix-Based Patient Signal Analysis

• US 20160135704A1
• Filed: 11/18/2014
• Published: 05/19/2016
• Est. Priority Date: 11/18/2014
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhang, Hongxuan
• Granted Patent: US 9,549,681 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/333 Recording apparatus specially adapted therefor
• CPC Class Codes: A61B 5/339 Displays specially adapted therefor
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• 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

Abstract

Disclosed herein is a framework for facilitating patient signal analysis. In accordance with one aspect, the framework generates a signature cycle matrix corresponding to a single cycle of the patient signal data by segmenting the patient signal data into multiple portions. The signature cycle matrix may further be segmented into sub-matrices corresponding to different levels. Properties of the sub-matrices may then be determined to generate diagnostic results.

Claims

1. A system for patient signal analysis, comprising:

a patient monitor configured to acquire a patient signal data from a patient; and

a computer system communicatively coupled to the patient monitor, wherein the computer system includes

a non-transitory memory device,

a processor device in communication with the memory device, and

a signal analysis unit stored in the memory device and operative with the processor device to perform steps including

generating a signature cycle matrix corresponding to a single cycle of the patient signal data by segmenting the patient signal data into multiple portions,

segmenting the signature cycle matrix into sub-matrices corresponding to different levels,

determining properties of the sub-matrices,

determining a sequential energy index based on the properties of the sub-matrices, and

characterizing an abnormality based on the properties and the sequential energy index.

2. The system of claim 1 wherein the signal analysis unit is further operative with the processor device to generate the signature cycle matrix by

segmenting each of the multiple portions into sub-portions,

generating wave vectors based on values extracted from the sub-portions, and

generating the signature cycle matrix based on the wave vectors.

3. The system of claim 2 wherein the values comprise voltage amplitude values.

4. The system of claim 3 wherein the voltage amplitude values comprise a maximum voltage amplitude value of a corresponding portion.

5. The system of claim 2 wherein the values comprise time durations.

6. The system of claim 1 wherein the sub-matrices comprise:

a first level sub-matrix that represents existence of a P wave in the cycle;

a second level sub-matrix that represents both rising edges of the P wave and a Q wave in the cycle;

a third level sub-matrix that represents rising edges of the P wave, the Q wave and an R wave in the cycle;

a fourth level sub-matrix that represents information from the P wave, the Q wave, the R wave and an S wave in the cycle; and

a fifth level sub-matrix that represents information from the P wave, the Q wave, the R wave, the S wave and a T wave in the cycle.

7. The system of claim 1 wherein the properties comprise trace or determinant values.

8. The system of claim 7 wherein the sequential energy index comprises a sum of squared magnitudes of trace values corresponding to the sub-matrices.

9. The system of claim 7 wherein the sequential energy index comprises a sum of squared magnitudes of determinant values corresponding to the sub-matrices.

10. The system of claim 1 wherein the abnormality comprises cardiac arrhythmia or myocardial ischemia.

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

receiving, from a patient monitor, patient signal data;

generating, by a processor device, a signature cycle matrix corresponding to a single cycle of the patient signal data by segmenting the patient signal data into multiple portions;

segmenting, by the processor device, the signature cycle matrix into sub-matrices corresponding to different levels;

determining, by the processor device, properties of the sub-matrices; and

generating, by the processor device, diagnostic results based on the properties.

12. The method of claim 11 wherein the multiple portions correspond to P, Q, R, S, and T waveform portions.

13. The method of claim 11 wherein generating the signature cycle matrix comprises:

segmenting each of the multiple portions into sub-portions,

generating wave vectors based on values extracted from the sub-portions, and

generating the signature cycle matrix based on the wave vectors.

14. The method of claim 13 wherein the values comprise voltage amplitude values or time durations.

15. The method of claim 11 wherein determining the properties comprises determining trace or determinant values of the sub-matrices.

16. The method of claim 11 wherein generating the diagnostic results comprises combining, via an artificial neural network, the properties and associated indices with other patient data.

17. The method of claim 11 wherein generating the diagnostic results comprises identifying the location, severity, type or timing of a cardiac pathology.

18. The method of claim 11 further comprising:

mapping each entry in the signature cycle matrix to an element on a two-dimensional graphic map; and

presenting, on a display device, the two-dimensional graphic map for a user to monitor the patient signal data.

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

receiving, from a patient monitor, patient signal data;

generating, by a processor device, a signature cycle matrix corresponding to a single cycle of the patient signal data by segmenting the patient signal data into multiple portions;

mapping each entry in the signature cycle matrix to an element on a two-dimensional graphic map; and

presenting, on a display device, the two-dimensional graphic map for a user to monitor the patient signal data.

20. The non-transitory computer readable medium of claim 19, wherein the element is color coded to represent percentage change in the corresponding entry of the signature cycle matrix.