Fetal data processing system and method

• US 5,596,993 A
• Filed: 09/21/1994
• Issued: 01/28/1997
• Est. Priority Date: 09/21/1994
• Status: Expired due to Fees

• Current Assignee: Beth Israel Hospital
• Original Assignee: Beth Israel Hospital
• Inventors: Bennett, Frederick M., Oriol, Nancy E.
• Primary Examiner(s): Kamm, William E.
• Application Number:
  US08/309,856
• Time in Patent Office: 860 Days
• Field of Search: 128/661.07, 128/698
• US Class Current: 600/511
• CPC Class Codes: A61B 5/02411 of foetuses
• CPC Class Codes: A61B 5/344 Foetal cardiography
• CPC Class Codes: A61B 5/4035 Evaluating the autonomic nervous system
• CPC Class Codes: A61B 5/4362 Assessing foetal parameters
• 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: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 128/925 Neural network

Abstract

A fetal data processing system and method and a fetal monitor and method for monitoring the condition of a fetus are disclosed. A fetal heart rate time series is received and sampled. A non-linear time-frequency transformation is performed to generate a time-frequency representation of the fetal heart rate time series for heart rate time series data spanning a time period which is preferably less than ten seconds. Analysis of fetal heart rate and fetal heart rate variability and other available data is performed to evaluate fetal well-being. Because of the high time resolution of the transformation, short-term transient variations in heart rate and heart rate variability are considered in the analysis.

Claims

1. A fetal data processing method comprising:

receiving a signal indicative of fetal heart rate time data for the fetus, said fetal heart rate time data indicating heart rate of the fetus over

performing a non-linear time-frequency transformation on the fetal heart rate time data to generate a frequency-domain representation for the fetal heart rate time data; and

analyzing the frequency domain representation to indicate a condition of the fetus related to the fetal heart rate time data.

2. The method of claim 1 further comprising:

monitoring fetal heart rate variability; and

indicating a transient change in fetal heart rate variability.

3. The method of claim 1 further comprising:

monitoring the fetal heart rate; and

indicating a transient change in the fetal heart rate.

4. The method of claim 1 further comprising analyzing the fetal heart rate time data to indicate the condition of the fetus.

5. The method of claim 1 further comprising analyzing a uterine contraction signal to indicate the condition of the fetus.

6. The method of claim 1 further comprising analyzing a fetal movement signal to indicate the condition of the fetus.

7. The method of claim 1 wherein the step of performing the non-linear time-frequency transformation comprises the step of generating a smoothed Wigner distribution.

8. The method of claim 1 further comprising evaluating overall well-being of the fetus based on analysis of the frequency domain representation.

9. The method of claim 8 further comprising:

generating data used to evaluate overall well-being of the fetus;

selecting a subset of the data for display; and

displaying the selected subset of data in real time.

10. The method of claim 8 further comprising:

analyzing the indicated condition of the fetus; and

generating recommendations regarding fetal well-being.

11. The method of claim 1 wherein the step of analyzing the frequency-domain representation comprises:

generating fetal data related to the frequency-domain representation; and

applying a set of classification rules to the fetal data to classify the fetal data.

12. The method of claim 1 wherein the step of analyzing the frequency-domain representation comprises:

generating a pattern of fetal data related to the frequency-domain representation; and

applying the pattern of fetal data to a neural network to classify the pattern of fetal data.

13. The method of claim 1 wherein the step of analyzing the frequency-domain representation comprises:

generating fetal data related to the frequency-domain representation;

applying a set of classification rules to at least a portion of the fetal data to classify the portion of the fetal data; and

applying at least a portion of the fetal data to a neural network to classify the portion of the fetal data.

14. The method of claim 1 wherein the step of analyzing the frequency-domain representation comprises analyzing the frequency-domain representation within a range of frequencies, said range of frequencies being divided into plural frequency bands, each of said frequency bands being associated with a set of physiological characteristics of human fetuses.

15. The method of claim 1 wherein the step of performing the non-linear time-frequency transformation comprises generating the frequency-domain representation over a frequency range from 0.02 Hz to 1.1 Hz , said frequency range being associated with a set of physiological characteristics of human fetuses.

16. The method of claim 1 wherein the step of analyzing the frequency-domain representation comprises computing areas under the frequency-domain representation, said areas being used to indicate the condition of the fetus.

17. The method of claim 1 wherein the step of performing the non-linear time-frequency transformation comprises generating the frequency-domain representation using fetal heart rate time data from a time period of less than ten seconds.

18. The method of claim 1 wherein the step of performing the non-linear time-frequency transformation comprises sampling the fetal heart rate time data at a frequency greater than 2 Hz.

19. The method of claim 1 further comprising:

generating data used to indicate the condition of the fetus;

selecting a subset of the data for display; and

displaying the selected subset of data in real time.

20. A fetal data processing system comprising:

an input that receives fetal heart rate time data for a fetus, said fetal heart rate time data indicating heart rate of the fetus over time; and

a processing subsystem comprising a processor and a memory, the processor running under control of a program stored in the memory to

receive the fetal heart rate time data from the input, to perform a non-linear time-frequency transformation on the fetal heart rate time data said transformation generating a frequency-domain representation for the fetal heart rate time data,

to analyze the frequency-domain representation and to indicate, based on the analysis of the frequency-domain representation, a condition of the fetus related to the fetal heart rate time data.

21. The fetal data processing system of claim 20 wherein the processing subsystem also analyzes the fetal heart rate time data to indicate the condition of the fetus.

22. The fetal data processing system of claim 20 wherein the processing subsystem also analyzes a uterine contraction signal to indicate the condition of the fetus.

23. The fetal data processing system of claim 20 wherein the processing subsystem also analyzes a fetal movement signal to indicate the condition of the fetus.

24. The fetal data processing system of claim 20 wherein the processing subsystem analyzes the frequency-domain representation in plural frequency bands, each of said frequency bands being associated with a set of physiological characteristics of human fetuses.

25. The fetal data processing system of claim 20 wherein:

the processing subsystem is programmed with a set of classifying rules; and

the processor, in analyzing the frequency-domain representation, generates a pattern of fetal data and applies the set of classifying rules to the pattern of fetal data to classify the pattern of fetal data.

26. The fetal data processing system of claim 25 wherein the processing subsystem comprises at least one neural network, the processor applying a pattern of fetal data to the neural network to classify the fetal data.

27. The fetal data processing system of claim 20 wherein:

the processing subsystem comprises at least one neural network; and

the processor, in analyzing the frequency-domain representation, generates a pattern of fetal data and applies the pattern of fetal data to the neural network to classify the pattern of fetal data.

28. The fetal data processing system of claim 20 wherein the processing subsystem, based on the analysis of the frequency-domain representation, evaluates overall well-being of the fetus.

29. The fetal data processing system of claim 28 further comprising a display, wherein the processor identifies fetal data used to evaluate the overall well-being of the fetus, identifies a subset of the fetal data for display and provides the subset of fetal data to the display.

30. The fetal data processing system of claim 29 wherein the processor generates recommendations regarding overall fetal well-being and forwards the recommendations to the display.

31. The fetal data processing system of claim 20 further comprising a display, wherein the processor identifies fetal data used to indicate the condition of the fetus, identifies a subset of the fetal data for display and provides the subset of fetal data to the display.

32. The fetal data processing system of claim 20 further comprising a sensor that senses fetal heartbeat and generates therefrom the fetal heart rate time data received at the input.

33. The fetal data processing system of claim 20 wherein the processor performs the non-linear time-frequency transformation on fetal heart rate time data from a time period not greater than 10 seconds.

34. A fetal data processing method comprising:

receiving a signal indicative of fetal heart rate time data for a fetus, said fetal heart rate time data indicating heart rate of the fetus over time;

sampling the fetal heart rate time data over a time period which does not exceed 10 seconds to generate sampled fetal heart rate time data;

performing a time-frequency transformation on the sampled fetal heart rate time data to generate a frequency-domain representation for the sampled fetal heart rate time data; and

analyzing the frequency-domain representation to indicate a condition of the fetus related to the fetal heart rate time data.

35. A fetal data processing system comprising:

an input that receives fetal heart rate time data for a fetus, said fetal heart rate time data indicating heart rate of the fetus over time; and

a processing subsystem comprising a processor and a memory, the processor running under control of a program stored in the memory to

receive the fetal heart rate time data, to sample the fetal heart rate time data over a time period that does not exceed 10 seconds such that sampled fetal heart rate time data is generated, to perform a time-frequency transformation on the sampled fetal heart rate time data said transformation generating a frequency-domain representation for the fetal heart rate time data,

to analyze the frequency-domain representation and to indicate, based on the analysis of the frequency-domain representation, a condition of the fetus related to the sampled fetal heart rate time data.

36. A fetal data processing system comprising:

an input that receives fetal heart rate time data for a fetus, said fetal heart rate time data indicating heart rate of the fetus over time; and

a processing system comprising;

a neural network that receives data and classifies the data, and

a processor and a memory, the processor running under control of a program stored in the memory to

receive the fetal heart rate time data from the input, to perform a time-frequency transformation on the fetal heart rate time data said transformation generating a frequency-domain representation for the fetal heart rate time data, to analyze the frequency-domain representation, to generate a pattern of data based on the analysis of the frequency-domain representation, to apply the pattern of data to the neural network such that the neural network provides a classification of the pattern of data, to receive the classification of the pattern of data from the neural network, and to

indicate a condition of the fetus based on the classification of the pattern of data.

37. A method of monitoring the condition of a fetus comprising:

sensing fetal heartbeat from the fetus;

generating a signal indicative of fetal heart rate time data, said fetal heart rate time data indicating heart rate of the fetus over time;

receiving the signal and performing a non-linear time-frequency transformation on the fetal heart rate time data to generate a frequency-domain representation for the fetal heart rate time data; and

analyzing the frequency-domain representation to indicate a condition of the fetus related to the fetal heart rate time data.

38. A fetal monitor comprising:

a sensor that senses a fetal heartbeat and generates fetal heart rate time data for a fetus, said fetal heart rate time data indicating heart rate of the fetus over time; and

a processing system comprising a processor and a memory, the processor running under control of a program stored in the memory to

receive the fetal heart rate time data, to perform a non-linear time-frequency transformation on the fetal heart rate time data said transformation generating a frequency-domain representation for the fetal heart rate time data,

to analyze the frequency-domain representation and to indicate a condition of the fetus related to the fetal heart rate time data.