Method and Apparatus for Predicting Patient Outcomes from a Physiological Segmentable Patient Signal

Abstract

A method and apparatus for predicting patient outcome from a physiological segmentable signal of a patient. In one embodiment, the method comprises the steps of obtaining the physiological segmentable signal of the patient; segmenting the physiological segmentable signal into a plurality of separate segmentable components; calculating a time series of the morphological distance between adjacent separate segmentable components of the plurality of separate segmentable components; and predicting patient outcome in response to the time series of the morphological distance. In another aspect, the invention relates to a method for extracting information from physiological signals for one or more subjects including the steps of partitioning the physiological signal into a plurality of components, grouping the components into a plurality of information classes, assigning a unique symbol to each information class, mapping each component to the assigned symbol, and examining one or more such sequences for clinical significance.

What is claimed is: 
     
         1 - 28 . (canceled) 
     
     
         29 . A method for extracting information from physiological signals comprising the steps of:
 segmenting the physiological signal into a plurality of components;   grouping the components into a plurality of information classes;   assigning a unique symbol and to each information class;   mapping each component to the assigned symbol to form a resulting symbolic sequence, and   examining the resulting symbolic sequence for clinical significance.   
     
     
         30 - 43 . (canceled) 
     
     
         44 . A system for extracting information from physiological signals comprising a processor for:
 segmenting the physiological signal into a plurality of components;   grouping the components into a plurality of information classes;   assigning a unique symbol to each information class   mapping each component by the assigned symbol to form a resulting symbolic sequence, and   examining the resulting symbolic sequence for clinical significance.   
     
     
         45 - 68 . (canceled) 
     
     
         69 . The method of  claim 29  wherein the examining of the resulting symbolic sequence comprises the step of searching for a repeat subsequence within the symbolic sequence. 
     
     
         70 . The method of  claim 69  wherein the repeat subsequence is an approximate match to another subsequence within the resulting symbolic sequence. 
     
     
         71 . The method of  claim 69  wherein the examining of the resulting symbolic sequence comprises the step of searching for a repeat subsequence within the symbolic sequence among a plurality of patients. 
     
     
         72 . The method of  claim 70  wherein the repeat subsequence is an approximate match if the repeat subsequence is within a predefined distance of the other subsequence. 
     
     
         73 . The method of  claim 69  wherein clinical significance is determined by the frequency of the repeat subsequence. 
     
     
         74 . The method of  claim 69  wherein the examining comprises the step of searching for short bursts of infrequent repeat sequences. 
     
     
         75 . The method of  claim 74  wherein the searching for short bursts of infrequent repeat sequences comprises searching for increased entropy. 
     
     
         76 . The method of  claim 29  wherein the step of examining comprises repeating the steps multiple times for the same patient. 
     
     
         77 . The method of  claim 69  wherein the step of examining comprises searching for clusters of repeat subsequences. 
     
     
         78 . The method of  claim 71  further comprising the step of correlating the repeat subsequence with clinical symptoms.