System for cardiac condition detection responsive to blood pressure analysis

• US 9,320,445 B2
• Filed: 08/23/2011
• Issued: 04/26/2016
• Est. Priority Date: 05/17/2011
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Zhang, Hongxuan
• Primary Examiner(s): Patel, Niketa
• Assistant Examiner(s): Hankins, Lindsey G
• Application Number:
  US13/215,311
• Publication Number:
  US 20120296225A1
• Time in Patent Office: 1,708 Days
• Field of Search: 600373-375, 600449-450, 600481-503, 600508-528
• US Class Current: 1/1
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• 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: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A system provides cardiac arrhythmia detection and performs blood pressure analysis of multiple catheter channels of blood pressure signals to characterize heart hemodynamic activity. A system for heart performance characterization and abnormality detection includes a repository, data processor and output processor. The repository of data comprises, first distribution data representing a probability distribution of a first patient parameter over a first time period and acquired on a first occasion and second distribution data representing a probability distribution of the first patient parameter over a second time period and acquired on a second occasion subsequent to the first occasion. The data processor calculates an overlap indicator indicating degree of overlap of the first distribution data and the second distribution data in a predetermined interval of the distributions. The output processor provides the calculated overlap indicator to a destination device.

Claims

1. A system for heart performance characterization and abnormality detection, comprising:

a repository of data comprising,

first statistical distribution data representing a first statistical distribution of values of a first patient parameter over a first time period and acquired on a first occasion and

second statistical distribution data representing a second statistical distribution of values of said first patient parameter over a second time period and acquired on a second occasion subsequent to said first occasion;

a data processor configured to;

calculate a first mean of the first statistical distribution data;

calculate a second mean of the second statistical distribution data;

calculate an overlap indicator indicating degree of overlap of said first statistical distribution data and said second statistical distribution data only in a predetermined interval of the data distributed substantially between the first mean of the first statistical distribution data and the second mean of the second statistical distribution data;

use predetermined mapping information, associating ranges of said overlap indicator with corresponding medical conditions;

compare said overlap indicator or values derived from said overlap indicator, with said ranges; and

generate an alert message indicating a potential medical condition; and

an output processor configured to provide the calculated overlap indicator to a destination device.

2. The system according to claim 1, wherein

said first statistical distribution data represents a first statistical distribution of values of the first patient parameter associated with a normal healthy condition and

said second statistical distribution data represents a second statistical distribution of values of said first patient parameter associated with an abnormal condition indicating pathology.

3. A system according to claim 1, wherein

said first statistical distribution data represents a first statistical distribution of values of the first patient parameter associated with pathology and

said second statistical distribution data represents a second statistical distribution of values of the first patient parameter associated with pathology.

4. The system according to claim 1, wherein

said data processor calculates said overlap indicator by integrating functions representing said first statistical distribution and said second statistical distribution to provide an integral value representing an area under said first statistical distribution and said second statistical distribution in said predetermined interval.

5. A system according to claim 1, wherein

said data processor calculates said overlap indicator by dividing said integral value by a value a representing an area under at least one of the first and second statistical distributions in a predetermined interval.

6. A system according to claim 1, wherein

said overlap indicator is of the form of,

7. A system according to claim 1, wherein

said first statistical distribution and said second statistical distribution comprise a Gaussian distribution.

8. A system according to claim 1, wherein

said first statistical distribution and said second statistical distribution comprise at least one of, (a) a uniform distribution, (b) a Cauchy distribution, (c) a T distribution, (d) an F distribution, (e) a Gamma distribution and (f) a Poisson distribution.

9. The system according to claim 1, wherein

said first statistical distribution and said second statistical distribution comprise different types of distribution.

10. The system according to claim 1, wherein

said first patient parameter comprises a vital sign related parameter.

11. The system according to claim 10, wherein

said first patient parameter comprises at least one of, (a) a blood pressure related parameter, (b) a temperature related parameter, (c) an End of Diastolic blood pressure related parameter and (d) an End of Systolic blood pressure related parameter.

12. The system according to claim 11, wherein

said first patient parameter comprises at least one of, (a) a blood pressure related parameter, (b) a temperature related parameter, (c) an End of Diastolic blood pressure related parameter and (d) an End of Systolic blood pressure related parameter.

13. The system according to claim 12, wherein

said first patient parameter comprises at least one of, (a) an amplitude related characteristic, (b) a frequency related characteristic, (c) a timing related characteristic and (d) an energy related characteristic.

14. The system according to claim 1, wherein

said predetermined mapping information associates ranges of said overlap indicator or values derived from said overlap indicator with particular patient demographic characteristics and with corresponding medical conditions and said data processor uses patient demographic data including at least one of, age weight, gender and height in comparing said overlap indicator or values derived from said overlap indicator with said ranges and generating an alert message indicating a potential medical condition.

15. The system according to claim 1, wherein

said first patient parameter comprises a weighted combination of different parameters.

16. The system according to claim 15, wherein said weighted combination of different parameters is derived using a function of the form,

17. A system for heart performance characterization and abnormality detection, comprising:

a repository of data comprising,

first statistical distribution data representing a first statistical distribution of values of a first patient parameter over a first time period and acquired on a first occasion and

second statistical distribution data representing a second statistical distribution of values of said first patient parameter over a second time period and acquired on a second occasion subsequent to said first occasion;

a data processor configured to;

calculate a first mean of the first statistical distribution data;

calculate a second mean of the second statistical distribution data;

calculate an overlap indicator indicating degree of overlap of said first statistical distribution data and said second statistical distribution data only in a predetermined interval of the data distributed substantially between the first mean of the first statistical distribution data and the second mean of the second statistical distribution data by determining an area under said first statistical distribution and said second statistical distribution in said predetermined interval;

use predetermined mapping information, associating ranges of said overlap indicator with corresponding medical conditions;

compare said overlap indicator or values derived from said overlap indicator, with said ranges; and

generate an alert message indicating a potential medical condition; and

an output processor configured to provide the calculated overlap indicator to a destination device.

18. A method employing at least one processing device for heart performance characterization and abnormality detection, comprising the activities of:

storing data in at least one repository comprising,

first statistical distribution data representing a first statistical distribution of values of a first patient parameter over a first time period and acquired on a first occasion and

second statistical distribution data representing a second statistical distribution of values of said first patient parameter over a second time period and acquired on a second occasion subsequent to said first occasion;

calculating a first mean of the first statistical distribution data;

calculating a second mean of the second statistical distribution data;

calculating an overlap indicator indicating degree of overlap of said first statistical distribution data and said statistical second distribution data only in a predetermined interval of the data distributed substantially between the first mean of the first statistical distribution data and the second mean of the second statistical distribution data;

using predetermined mapping information, associating ranges of said overlap indicator with corresponding medical conditions;

comparing said overlap indicator or values derived from said overlap indicator, with said ranges; and

generating an alert message indicating a potential medical condition; and

providing the calculated overlap indicator to a destination device.