Automatic Cardiac Therapy Advisor With Hidden Markov Model Processing

Abstract

A method of automatically determining which type of treatment is most appropriate for (or the physiological state of) a patient. The method comprises transforming one or more time domain measurements from the patient into frequency domain data representative of the frequency content of the time domain measurements; processing the frequency domain data to form a plurality of spectral bands, the content of a spectral band representing the frequency content of the measurements within a frequency band; forming a weighted sum of the content of the spectral bands, with different weighting coefficients applied to at least some of the spectral bands; determining the type of treatment (or physiological state) based on the weighted sum.

What is claimed is: 
     
         1 . A method of automatically determining which of a plurality of possible cardiac interventions should be performed in treatment of a patient, the method comprising:
 storing prior information representative of prior cardiac interventions performed on the patient;   storing prior information representative of the patient's reactions to the prior cardiac interventions; and   processing the information using a hidden Markov model to determine which of a plurality of possible further cardiac interventions should be performed.   
     
     
         2 . The method of  claim 1  further comprising;
 sensing the patient's reaction to the further cardiac intervention, 
 storing further information representative of the further cardiac intervention; 
 storing further information representative of the patient's reaction to the further cardiac intervention, 
 processing the prior and further information using a hidden Markov model to determine which of still further cardiac interventions should be performed in further treatment of the patient. 
 
     
     
         3 . The method of  claim 1  wherein the patient is a cardiac arrest victim. 
     
     
         4 . The method of  claim 2  wherein the patient is a cardiac arrest victim. 
     
     
         5 . Apparatus for automatically determining which of a plurality of possible cardiac interventions should be performed in treatment of a patient, the apparatus comprising:
 a processor and associated memory for storing prior information representative of prior cardiac interventions performed on the patient;   memory for storing prior information representative of the patient's reactions to the prior cardiac interventions; and   wherein the processor is configured to process the information using a hidden Markov model to determine which of a plurality of possible further cardiac interventions should be performed.   
     
     
         6 . The apparatus of  claim 3  further comprising;
 components for sensing the patient's reaction to the further cardiac intervention, 
 memory for storing further information representative of the further cardiac intervention; 
 memory for storing further information representative of the patient's reaction to the further cardiac intervention, and 
 wherein the processor is further configured to process the prior and further information using a hidden Markov model to determine which of still further cardiac interventions should be performed in further treatment of the patient. 
 
     
     
         7 . The apparatus of  claim 5  wherein the patient is a cardiac arrest victim. 
     
     
         8 . The apparatus of  claim 6  wherein the patient is a cardiac arrest victim.