Automatic cardiac therapy advisor with hidden markov model processing

• US 9,339,436 B2
• Filed: 04/23/2012
• Issued: 05/17/2016
• Est. Priority Date: 05/12/2004
• Status: Active Grant

• Current Assignee: Zoll Medical Corporation (Asahi Kasei Corporation)
• Original Assignee: Zoll Medical Corporation (Asahi Kasei Corporation)
• Inventors: Freeman, Gary A., Brewer, James E.
• Primary Examiner(s): MALAMUD, DEBORAH LESLIE
• Application Number:
  US13/454,061
• Publication Number:
  US 20120226178A1
• Time in Patent Office: 1,485 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/7207 of noise induced by motion artifacts
• CPC Class Codes: A61B 5/7257 using Fourier transforms
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61H 2201/5015 using specific interfaces or standards, e.g. USB, serial, parallel
• CPC Class Codes: A61H 2230/04 Heartbeat characteristics, e.g. E.G.C., blood pressure modulation
• CPC Class Codes: A61H 31/005 with feedback for the user
• CPC Class Codes: A61N 1/3925 Monitoring; Protecting
• CPC Class Codes: G09B 23/288 for artificial respiration or heart massage
• CPC Class Codes: G16H 40/60 for the operation of medical equipment or devices
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics
• CPC Class Codes: Y10S 128/923 by comparison of patient data to other data
• CPC Class Codes: Y10S 128/924 using artificial intelligence
• CPC Class Codes: Y10S 706/924 Medical

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.

Claims

1. A method of automatically determining which of a plurality of possible types of cardiac interventions should be performed in treatment of a patient, the method comprising:

storing first prior information representative of types of prior cardiac interventions performed on the patient;

storing second prior information representative of the patient'"'"'s reactions to the prior cardiac interventions;

wherein the first and second prior information are other than heart rhythms or ECG waveforms; and

processing the first and second prior 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 first further information representative of the type of the further cardiac intervention;

storing second further information representative of the patient'"'"'s reaction to the further cardiac intervention,

processing the first and second prior and first and second 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 types of cardiac interventions should be performed in treatment of a patient, the apparatus comprising:

a processor and associated memory for storing first prior information representative of types of prior cardiac interventions performed on the patient;

memory for storing second prior information representative of the patient'"'"'s reactions to the prior cardiac interventions;

wherein the first and second prior information are other than heart rhythms or ECG waveforms; and

wherein the processor is configured to process the first and second prior 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 5 further comprising;

components for sensing the patient'"'"'s reaction to the further cardiac intervention,

memory for storing first further information representative of the type of the further cardiac intervention;

memory for storing second further information representative of the patient'"'"'s reaction to the further cardiac intervention, and

wherein the processor is further configured to process the first and second prior and first and second 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.