Patient signal analysis based on vector analysis
Disclosed herein is a framework for facilitating patient signal analysis based on vector analysis. In accordance with one aspect, a set of vectors is generated from a patient signal data waveform. The vectors may be directed from a common center to points of interest on the patient signal data waveform. The framework may further extract one or more vector parameters from the set of vectors, and determine one or more vector ratios based on the vector parameters to monitor changes in the patient signal data waveform.
1. A computer-implemented method of patient signal analysis, comprising:
receiving, from a patient monitor, a patient signal data waveform;
generating, by a processor, a set of vectors directed from a common center to points of interest on the patient signal data waveform;
extracting, by the processor, one or more vector parameters from the set of vectors; and
determining, by the processor, one or more vector ratios based on the one or more vector parameters to monitor changes in the patient signal data waveform, wherein determining the one or more vector ratios comprises determining one or more unilateral ratios from the vectors or determining one or more bilateral ratios from the vectors.
2. The method of claim 1 wherein the patient signal data waveform comprises an electrocardiogram waveform.
3. The method of claim 1 wherein generating the vectors comprises generating the vectors directed from an R wave peak center point on the patient signal data waveform.
4. The method of claim 1 wherein generating the vectors comprises generating the vectors directed from the common center point to at least one of P, Q, S, T or U wave peak points on the patient signal data waveform.
5. The method of claim 1 wherein generating the vectors comprises generating the vectors directed from the common center point to an H point defined at a half cycle time point.
6. The method of claim 1 wherein extracting the one or more vector parameters comprises extracting one or more time durations measured from a half cycle time stamp to time stamps of the points of interest.
7. The method of claim 6 wherein determining the one or more vector ratios comprises determining at least one ratio of distances associated with two vectors selected from the set of vectors.
8. The method of claim 6 wherein determining the one or more vector ratios comprises determining at least one ratio of time durations associated with two vectors selected from the set of vectors.
9. The method of claim 6 wherein determining the one or more vector ratios comprises determining at least one ratio comparing a vector amplitude associated with a first vector to a time duration associated with a second vector, wherein the first and second vectors are selected from the set of vectors.
10. The method of claim 9 wherein the first and second vectors are different.
11. The method of claim 9 wherein the first and second vectors are same.
12. The method of claim 1 wherein extracting the one or more vector parameters comprises extracting vector circles, wherein each of the vector circles is centered at the common center and has a radius defined by one of the vectors.
13. The method of claim 12 wherein determining the one or more vector ratios comprises determining at least one ratio of areas associated with two of the vector circles.
14. The method of claim 12 wherein determining the one or more vector ratios comprises determining at least one ratio that compares an area associated with a vector circle of first vector with a time duration associated with a second vector, wherein the first and second vectors are selected from the set of vectors.
15. The method of claim 1 further comprising determining one or more statistical indices based on the vector ratios.
16. The method of claim 1 further comprising mapping, via an artificial neural network, the one or more vector ratios and patient data to a cardiac event or pathology.
17. The method of claim 1 wherein mapping the one or more vector ratios and the patient data to the cardiac event or pathology comprises determining a location, type or severity of cardiac arrhythmia.
18. A non-transitory computer readable medium embodying a program of instructions executable by machine to perform steps for cardiac function characterization, the steps comprising:
detecting an R wave peak of a patient signal data waveform;
generating a set of vectors directed from the R wave peak to points of interest on the patient signal data waveform;
extracting one or more vector parameters from the set of vectors; and
determining one or more vector ratios based on the one or more vector parameters to monitor changes in the patient signal data waveform, wherein determining the one or more vector ratios comprises determining one or more unilateral ratios from the vectors or determining one or more bilateral ratios from the vectors.
19. A computer-implemented method of patient signal analysis, comprising:
receiving, from a patient monitor, a patient signal data waveform;
generating, by a processor, a set of vectors directed from a common center to points of interest on the patient signal data waveform;
extracting, by the processor, one or more vector parameters from the set of vectors; and
determining, by the processor, one or more vector ratios based on the one or more vector parameters to monitor changes in the patient signal data waveform, wherein the one or more vector ratios are determined based on vector parameters extracted from the vectors within a single cycle of the patient signal data waveform.