Method and system of segmentation and time duration analysis of dual-axis swallowing accelerometry signals

Abstract

The proposed invention is a method and system for the segmentation of dual-axis accelerometry signals for the purpose of identifying problematic swallowing events. The method and system employ a sensor, a data collection means including an algorithm for analysis of the data. The proposed invention considers the stochastic properties of swallowing signals in both directions, A•P and S-I to extract events associated with swallowing. A segmentation algorithm may be applied to the signals to establish the time duration of swallows and swallows may be classified with respect to gender, body mass index, age or types of swallow.

What is claimed is: 
     
         1 . A computer software program stored on a tangible computer storage medium and executable by a computer for segmentation and analysis of dual-axis accelerometry signals for the indication of problematic swallowing events, the program causing the computer to perform the following steps:
 a. receiving accelerometry data from an accelerometry sensor, said data comprising a series of vibration events having dual-axis acceleration in an anterior-posterior (A-P) direction and a superior-inferior (S-I) direction and representing swallowing and non-swallowing segments;   b. executing a sequential segmentation algorithm;   c. forming a first indicator function for a non-swallowing segment in said A-P direction;   d. forming a second indicator function for a swallowing segment in the A-P direction;   e. forming a first indicator function for a non-swallowing segment in the S-I direction;   f. forming a second indicator function for a swallowing segment in the S-I direction;   g. applying fuzzy c-means optimization for determining time boundaries for each of said swallowing and non-swallowing segments;   h. multiplying said first function in the A-P direction by said first indicator function in the S-I direction for noise reduction;   i. multiplying said second indicator function in the A-P direction by said second indicator function in the S-I direction for noise reduction;   j. wherein steps h and i form a binary dual-axis indicator function for swallowing and non-swallowing segments;   k. comparing the swallowing segments with known attributes of healthy swallowing; and   l. identifying a subset of problematic swallowing events as a function of step k.   
     
     
         2 . The computer software program of  claim 1  further causing the computer to perform incorporating data representing a patient's anthropometric and demographic characteristics and classifying the swallowing segments according to said characteristics.