Method and apparatus for predicting patient outcomes from a physiological segmentable patient signal

• US 8,868,163 B2
• Filed: 10/19/2012
• Issued: 10/21/2014
• Est. Priority Date: 01/16/2008
• Status: Expired due to Fees

• Current Assignee: Massachusetts Institute of Technology
• Original Assignee: Massachusetts Institute of Technology
• Inventors: Guttag, John V., Syed, Zeeshan H., Sung, Philip Pohong, Stultz, Collin M.
• Primary Examiner(s): Layno, Carl H
• Assistant Examiner(s): Stice, Paula J
• Application Number:
  US13/656,056
• Publication Number:
  US 20130046193A1
• Time in Patent Office: 732 Days
• Field of Search: None
• US Class Current: 600/509
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/363 Detecting tachycardia or bradycardia
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

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.

Claims

1. A method for improving prediction of patient outcome for a specific patient comprising:

obtaining a plurality of patient outcomes and of energy in frequency bands of ECGs for a plurality of prior patients into a database;

determining an association of energy in each of the frequency bands with a patient outcome for each of the prior patients using a processor accessing the database;

determining the strongest association between energy in one or more of the frequency bands and one of the patient outcomes for each of the prior patients using the processor accessing the database;

defining the frequency band with energy with the strongest association with the patient outcome as a diagnostic band for that patient outcome;

measuring the energy in the diagnostic frequency band of the specific patient using the processor; and

predicting patient outcome for the specific patient in response to energy present in the diagnostic frequency band using the processor.

2. The method of claim 1 wherein the step of identifying the diagnostic frequency band comprises the step of evaluating possible frequency bands between 0.1 Hz-0.6 Hz.

3. The method of claim 2 wherein the diagnostic frequency band is substantially between 0.30 Hz-0.55 Hz.

4. The method of claim 3 wherein the diagnostic frequency band between 0.30 Hz-0.55 Hz is a predictor of death within a predefined amount of time.

5. The method of claim 4 wherein the predetermined amount of time is 90 days.

6. The method of claim 1 wherein high energy in the diagnostic frequency band is strongly associated with risk of death.

7. A system for improving prediction of patient outcome for a specific patient comprising:

a database comprising a plurality of patient outcomes and a plurality of frequency bands of ECGs for a plurality of prior patients;

an processor, in communication with the database, the processor;

determining an association of energy in each of the frequency bands with a patient outcome for each of the prior patients;

determining the strongest association between the energy one or more of the frequency bands and one of the patient outcomes for each of the prior patients;

defining the frequency bands with energy with the strongest association with the patient outcome as the diagnostic frequency bands for that prior patient outcome; and

storing the diagnostic frequency bands for that prior patient outcome in the database;

an energy monitor for measuring, for the specific patient, the energy in the diagnostic frequency band; and

the processor in communication with the energy monitor and the database, the processor comprising a module for predicting patient outcome for the specific patient in response to energy present in the diagnostic frequency band.

8. The system of claim 7 wherein the module for identifying a diagnostic frequency band evaluates possible frequency bands between 0.1 Hz-0.6 Hz.

9. The system of claim 8 wherein the diagnostic frequency band is substantially between 0.30 Hz-0.55 Hz.

10. The system of claim 9 wherein the module for predicting patient outcome predicts death within a predetermined amount of time in response to the energy in the diagnostic frequency band between 0.30 Hz-0.55 Hz.

11. The system of claim 10, wherein the amount of time is 90 days.

12. The system of claim 7 wherein module for predicting patient outcome associates high energy in the diagnostic frequency band with increased risk of death.