Method and apparatus for the early diagnosis of subacute, potentially catastrophic illness

• US 20020052557A1
• Filed: 02/27/2001
• Published: 05/02/2002
• Est. Priority Date: 03/17/1998
• Status: Active Grant

• Current Assignee: University of Virginia Patent Foundation (University of Virginia)
• Original Assignee: University of Virginia Patent Foundation (University of Virginia)
• Inventors: Kovatchev, Boris P., Moorman, J. Randall, Griffin, M. Pamela
• Granted Patent: US 6,804,551 B2
• Time in Patent Office: Days
• US Class Current: 600/515
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02411 of foetuses
• CPC Class Codes: A61B 5/344 Foetal cardiography
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/412 Detecting or monitoring sepsis
• CPC Class Codes: A61B 5/4362 Assessing foetal parameters
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

In one aspect of the invention, there is provided a method and apparatus for early detection of subacute, potentially catastrophic illness in a patient. The method comprises: (a) monitoring heart rate variability in the patient; and (b) identifying at least one characteristic abnormality in the heart rate variability that is associated with the illness. This method can be use to diagnose illnesses such as, but not limited to, sepsis, necrotizing enterocolitis, pneumonia and meningitis, as well as noninfectious illnesses. In another aspect of the present invention, there is provided a method and apparatus for early detection of subacute, potentially catastrophic illness in a patient. The method comprises: (a) monitoring the patient'"'"'s RR intervals; (b) generating a normalized data set of the RR intervals; (c) calculating one or more of (i) moments of the data set selected from the second and higher moments, including the standard deviation (ii) percentile values of the data set, (iii) sample entropy, and (iv) sample asymmetry; and (d) identifying an abnormal heart rate variability associated with the illness based on one or more of the moments, the percentile values, sample entropy, and sample asymmetry analysis.

Claims

1. A method for early detection of subacute, potentially catastrophic illness in a patient comprising:

(a) monitoring the patient'"'"'s RR intervals;

(b) generating a normalized data set of the RR intervals;

(c) calculating one or more of

(i) moments of the data set selected from the second and higher moments, including the standard deviation,

(ii) percentile values of the data set,

(iii) sample entropy, and

(iv) sample asymmetry,

(d) identifying an abnormal heart rate variability associated with the illness based on one or more of the moments and the percentile values, sample entropy and sample asymmetry analysis.

2. The method of claim 1, wherein the moments include the second moment of the data set.

3. The method of claim 1, wherein the moments include the third moment and the standard deviation of the data set.

4. The method of claim 1, wherein the moments include the fourth moment of the data set.

5. The method of claim 1, wherein the percentile values include about the 10^th and/or 50^th percentile value.

6. The method of claim 1, wherein the sample entropy is calculated.

7. The method of claim 1, wherein the sample asymmetry of the data set is calculated.

8. The method of claim 1 wherein step (c) is carried out using a multivariable statistical analysis selected from the group including but not limited to multivariable regression analysis, neural networks, k-nearest neighbor analysis, and combinations thereof.

9. The method of claim 8 wherein the multivariable statistical analysis is multivariable regression analysis.

10. The method of claim 8 wherein the multivariable statistical analysis is a neural network.

11. The method of claim 8 wherein the multivariable statistical analysis is k-nearest neighbor analysis.

12. The method of claim 8 wherein the patient is a neonate.

13. The method of claim 8 wherein the patient is an infant.

14. The method of claim 8 wherein the patient is a toddler.

15. The method of claim 8 wherein the patient is a child.

17. The apparatus of claim 16, wherein the microprocessor calculates the second moment of the data set.

18. The apparatus of claim 16, wherein the microprocessor calculates the third moment of the data set.

19. The apparatus of claim 16, wherein the microprocessor calculates the fourth moment of the data set.

20. The apparatus of claim 16, wherein the microprocessor calculates the 10^th and/or the 50^th percentile of the data set.

21. The apparatus of claim 16, wherein the microprocessor calculates the sample entropy.

22. The apparatus of claim 16, wherein the microprocessor calculates sample asymmetry of the data set.

23. The apparatus of claim 16, wherein the microprocessor performs step (b) by carrying out using a multivariable statistical analysis selected from the group including but not limited to multivariable regression analysis, neural networks, k-nearest neighbor analysis, and combinations thereof, k-nearest neighbor analysis, neural networks, or a combination thereof.

16. An apparatus for early detection of subacute, potentially catastrophic infectious illness in a patient comprising (1) a monitoring device, which monitors the patient'"'"'s RR intervals, and (2) a microprocessor, said microprocessor performing steps comprising:

(a) generating a normalized data set of the RR intervals;

(b) calculating one or more of

(i) moments of the data set selected from the second and higher moments,

(ii) percentile values of the data set,

(iii) sample entropy, and

(iv) sample asymmetrys,

(c) identifying an abnormal heart rate variability associated with the illness based on one or more of the moments, the percentile values, sample entropy and sample asymmetry analysis.