System and method for analyzing progress of labor and preterm labor

Patent metadata

Field	Value
Publication number	US-10987047-B2
Application number	US-201815967296-A
Country	US
Kind code	B2
Filing date	Apr 30, 2018
Priority date	Dec 11, 2006
Publication date	Apr 27, 2021
Grant date	Apr 27, 2021

Abstract

Systems and methods for monitoring uterus contraction activity and progress of labor. The system of the subject invention can comprises (1) a plurality of sensors; (2) an amplifying/filtering means; (3) a computing means; and (4) a graphical user interface. Accurate clinical data, which can be extracted and provided to the user in real-time using the system of the invention, include without limitation, progress of labor, prediction and monitoring of preterm labor, and intrauterine pressure prediction. In a preferred embodiment, the system of the invention includes an intelligence means, such as a neural network system, to analyze and interpret clinical data for use in clinical diagnosis as well as delivery strategy.

First claim

We claim:

1. A uterine monitoring system, comprising:
a plurality of surface sensors suitable for attaching to a patient's abdomen and receiving uterine electrical signals;
a user interface;
one or more processors;
a connector interface that is connected to the plurality of surface sensors; and
a non-transitory computer readable medium storing computer software that, when executed, causes the one or more processors of the uterine monitoring system to:
receive or determine a location of each of the plurality of surface sensors and recording the location of each of the plurality of surface sensors;
record electrical signals from each of the plurality of surface sensors over time;
convert the electrical signals from each of the plurality of surface sensors into contraction intensity information;
create a movie comprising a plurality of uterine contractile maps based on the location of each of the plurality of surface sensors;
determine a center of uterine electrical activity based on the plurality of contractile maps;
track movement of the center of uterine electrical activity to establish a contraction pattern, wherein the contraction pattern is based at least in part on a percentage of time the contraction pattern occurs within a period of time; and
based on clinically relevant findings stemming from the contraction pattern, diagnose normal or abnormal labor.

2. The system of claim 1 , wherein the computer software, when executed, further comprises a function for sequentially analyzing the plurality of uterine contractile maps to extract information about the contraction pattern.

3. The system of claim 2 , wherein the computer software, when executed, further causes the one or more processors of the uterine monitoring system to:
extract the information about the contraction pattern including time and location a contraction starts, extent of the contraction, a direction of contractile propagation, and a spread and a speed of contractile propagation over the patient's abdomen from the sequentially analyzed plurality of uterine contractile maps.

4. The system of claim 2 , wherein the computer software, when executed, further causes the one or more processors of the uterine monitoring system to:
perform an electrohysterogram (EHG) extraction function that analyzes the electrical signals to extract the following parameters from a grid of locations corresponding to the plurality of surface sensors: time of contraction, location of contraction, extent of contraction, direction of propagation, speed of propagation over the abdomen, average contraction amplitude of an EHG envelope over time, spatial location of the peak of contraction and variance, spread of the contraction, abdominal intensity distribution, abdominal frequency distribution, patterns of contraction intensity over time, distance of peak power propagation, power changes over time, and frequency changes over time from the sequentially analyzed plurality of uterine contractile maps; and
use the parameters to quantify the contraction pattern to predict labor outcome.

5. The system of claim 1 , wherein the computer software, when executed, further causes the one or more processors of the uterine monitoring system to:
generate location signals, from the electrical signals, by pair-wise subtraction between signal neighbors to remove common signal characteristics; and
provide local information about the contraction pattern.

6. The system of claim 1 , wherein the computer software, when executed, further causes the one or more processors of the uterine monitoring system to apply a Gaussian model to estimate the center of uterine electrical activity based on the plurality of contractile maps.

7. The system of claim 1 , wherein the computer software, when executed, further causes the one or more processors of the uterine monitoring system to fit a Gaussian function to the plurality of contractile maps to capture an amplitude, location, and variances of a contractility model.

8. The system of claim 6 , wherein the Gaussian function is fitted to the plurality of contractile maps using a Levenberg-Marquardt learning algorithm.

9. A method for monitoring uterine contractility in a patient, comprising:
placing a plurality of surface sensors on a patient's abdomen and receiving uterine electrical signals;
receiving or determining, by one or more processors, a location of each of the plurality of surface sensors and recording the location of each of the plurality of surface sensors;
recording, by the one or more processors, electrical signals from each of the plurality of surface sensors over time;
converting, by the one or more processors, the electrical signals from each of the plurality of surface sensors into contraction intensity information;
creating, by the one or more processors, a movie comprising a plurality of uterine contractile maps based on the location of each of the plurality of surface sensors;
determining, by the one or more processors, a center of uterine electrical activity based on the plurality of contractile maps;
tracking, by the one or more processors, movement of the center of uterine electrical activity to establish a contraction pattern, wherein the contraction pattern is based at least in part on a percentage of time the contraction pattern occurs within a period of time; and
based on clinically relevant findings stemming from the contraction pattern, diagnosing normal or abnormal labor.

10. The method of claim 9 , further comprising:
sequentially analyzing the plurality of uterine contractile maps to extract information about the contraction pattern.

11. The method of claim 10 , further comprising:
extracting the information about the contraction pattern including time and location a contraction starts, extent of the contraction, a direction of contractile propagation, and a spread and a speed of contractile propagation over the patient's abdomen from the sequentially analyzed plurality of uterine contractile maps.

12. The method of claim 10 , further comprising:
analyzing the electrical signals to extract the following parameters from a grid of locations corresponding to the plurality of surface sensors: time of contraction, location of contraction, extent of contraction, direction of propagation, speed of propagation over the abdomen, average contraction amplitude of an electrohysterogram (EHG) envelope over time, spatial location of the peak of contraction and variance, spread of the contraction, abdominal intensity distribution, abdominal frequency distribution, patterns of contraction intensity over time, distance of peak power propagation, power changes over time, and frequency changes over time from the sequentially analyzed plurality of uterine contractile maps; and
using the parameters to quantify the contraction pattern to predict labor outcome.

13. The method of claim 9 , further comprising:
generating location signals, from the electrical signals, by pair-wise subtraction between signal neighbors to remove common signal characteristics and provide local information about the contraction pattern.

14. The method of claim 9 , further comprising:
applying a Gaussian model to estimate the center of uterine electrical activity based on the plurality of contractile maps.

15. The method of claim 9 , further comprising:
fitting a Gaussian function to the plurality of contractile maps to capture an amplitude, location, and variances of a contractility model.

16. The method of claim 15 , wherein the Gaussian function is fitted to the plurality of contractile maps using a Levenberg-Ma

Assignees

• Convergent Eng Inc
• Univ Florida

Inventors

• Principe Jose C
• Maroserro Dorothee
• Euliano Tammy Y
• Euliano Ii Neil Russell

Classifications

• G16Z99/00

  Subject matter not provided for in other main groups of this subclass · CPC title

• A61B5/1107

  Measuring contraction of parts of the body, e.g. organ or muscle · CPC title

• A61B2503/02

  Foetus · CPC title

• A61B5/391

  of genito-urinary organs · CPC title

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title