Apparatus and method for feature extraction and classification of fetal heart rate

Abstract

Provided are an apparatus and method for receiving a fetal heart rate (FHR) signal at each interval during a monitoring period, receiving a uterine pressure (UP) signal at each of the intervals to obtain a plurality of FHR-UP signal pairs, and extracting a feature value for each FHR-UP signal pair, with the feature value being extracted from a predefined alphabet of feature values.

What is claimed: 
     
         1 . A monitoring method comprising:
 receiving, from a heart rate monitor, a fetal heart rate (FHR) signal at a plurality of intervals;   receiving a uterine pressure (UP) signal at each interval of the plurality of intervals, to obtain a plurality of FHR-UP signal pairs; and   extracting a feature value for each FHR-UP signal pair,   wherein the feature value is extracted from an alphabet of feature values.   
     
     
         2 . The method of  claim 1 , wherein the extracted feature value describes a time dynamic of the FHR-UP signal pair, with the time dynamic being one of a change in UP contractions, FHR accelerations, FHR decelerations and FHR baseline-variability. 
     
     
         3 . The method of  claim 1 , wherein the extracted feature value is based on a variation of a previous FHR-UP signal pair. 
     
     
         4 . The method of  claim 3 , wherein the variation is one of a UP contraction, FHR acceleration, FHR deceleration and FHR baseline-variability. 
     
     
         5 . The method of  claim 1 , wherein the alphabet of feature values is a finite size. 
     
     
         6 . The method of  claim 5 , wherein the size of the alphabet of feature values is determined by varying a bin width. 
     
     
         7 . The method of  claim 5 , wherein the size of the alphabet of feature values is determined by varying a segmentation period. 
     
     
         8 . The method of  claim 1 , further comprising replacing each FHR-UP signal pair with a feature value sequence. 
     
     
         9 . The method of  claim 8 , further comprising:
 comparing the feature value sequence with a plurality of previously obtained feature value sequences;   classifying the feature value sequence; and   outputting, based on the comparison, an indication of fetus health.   
     
     
         10 . The method of  claim 9 , wherein changes between feature value sequences indicate morphological changes. 
     
     
         11 . The method of  claim 10 , wherein the classifying of the feature value sequence is performed using a generative model. 
     
     
         12 . The method of  claim 1 , further comprising performing parameter learning to update a database of probabilistic models of fetal health. 
     
     
         13 . An apparatus for monitoring fetal health, the apparatus comprising:
 a controller configured to receive a fetal heart rate (FHR) signal at a plurality of intervals, to receive a uterine pressure (UP) signal at each interval of the plurality of intervals, to obtain a plurality of FHR-UP signal pairs, and to extract feature values for each FHR-UP signal pair.   
     
     
         14 . The apparatus of  claim 13 , wherein the feature values are extracted from an alphabet of feature values. 
     
     
         15 . The apparatus of  claim 14 , wherein the alphabet of feature values is limited to a finite size, with the size of the alphabet of feature values being determined by varying a segmentation period and a bin width. 
     
     
         16 . The apparatus of  claim 13 , wherein the extracted feature value is based on a variation of a previous FHR-UP signal pair, with the extracted feature value describing time dynamics of the FHR-UP signal pair. 
     
     
         17 . The apparatus of  claim 16 , wherein the variation is one of a UP contraction, FHR acceleration, FHR deceleration, and FHR baseline-variability. 
     
     
         18 . The apparatus of  claim 11 , wherein the controller is further configured to replace each FHR-UP signal pair with a feature value sequence. 
     
     
         19 . The apparatus of  claim 11 , wherein a change between sequences of feature values indicates a morphological change. 
     
     
         20 . The apparatus of  claim 11 , wherein the controller is further configured to perform parameter learning to update a database of probabilistic models of fetal health.