Method and apparatus for automatic arrhythmia classification with confidence estimation

Patent metadata

Field	Value
Publication number	US-9307920-B2
Application number	US-201313864023-A
Country	US
Kind code	B2
Filing date	Apr 16, 2013
Priority date	Apr 17, 2012
Publication date	Apr 12, 2016
Grant date	Apr 12, 2016

Abstract

An arrhythmia classification system receives cardiac data from an implantable medical device, performs automatic adjudication of each cardiac arrhythmia episode indicated by the cardiac data, and generates episode data representative of information associated with the episode. The episode data include at least an episode classification resulting from the automatic adjudication of the episode and a confidence level in the episode classification. In one embodiment, the episode data further include key features rationalizing the automatic adjudication of the episode.

First claim

What is claimed is:

1. A system configured to be communicatively coupled to an implantable medical device sensing one or more cardiac signals indicative of one or more arrhythmia episodes and produce cardiac data representative of the one or more cardiac signals, the system comprising:
an arrhythmia analysis circuit configured to receive cardiac data transmitted from the implantable medical device, perform automatic adjudication of each episode of one or more arrhythmia episodes using the cardiac data by executing a plurality of adjudication algorithms to produce voting classifications for each episode, determining a voting classification of the voting classifications for each episode by executing an adjudication algorithm of the plurality of adjudications algorithms, determining an episode classification for each episode using one or more primary voting classifications selected from the voting classifications and a confidence level in the episode classification based on the voting classifications for each episode, and generate episode data representative of information associated with each episode including the episode classification and the confidence level in the episode classification;
a memory circuit configured to store data including the cardiac data and the episode data; and
a user interface including a presentation device configured to present the information associated with each episode.

2. The system of claim 1 , wherein the arrhythmia analysis circuit comprises an automatic arrhythmia adjudicator configured to execute the adjudication algorithms each being a machine learning algorithm implementing a tachyarrhythmia adjudication algorithm.

3. The system of claim 1 , wherein the arrhythmia analysis circuit comprises a confidence analyzer configured to determine the confidence level in the episode classification using one or more secondary voting classifications selected from the voting classifications produced by executing the plurality of adjudication algorithms, the confidence level indicative of a percentage of the one or more secondary voting classifications consistent with the episode classification.

4. The system of claim 1 , comprising an external telemetry circuit configured to receive the cardiac data from the implantable medical device.

5. The system of claim 4 , comprising an external device including the external telemetry circuit, a remote device including at least the user interface, and a communication network coupling between the external device and the remote device.

6. A system configured to be communicatively coupled to an implantable medical device sensing one or more cardiac signals indicative of one or more arrhythmia episodes and produce cardiac data representative of the one or more cardiac signals, the system comprising:
an arrhythmia analysis circuit configured to receive cardiac data transmitted from the implantable medical device, perform automatic adjudication of each episode of one or more arrhythmia episodes using the cardiac data, and generate episode data representative of information associated with each episode including an episode classification resulting from the automatic adjudication of each episode, a confidence level in the episode classification, and episode features including key features rationalizing the automatic adjudication of each episode;
a memory circuit configured to store data including the cardiac data and the episode data; and a user interface including a presentation device configured to present the information associated with each episode,
wherein the arrhythmia analysis circuit is configured to determine the episode classification for each episode and the confidence level in the episode classification using the cardiac data by executing a plurality of adjudication algorithms.

7. The system of claim 6 , wherein the arrhythmia analysis circuit comprises a rationalization module configured to generate episode features including features used by the automatic arrhythmia adjudicator to determine the episode classification for each episode.

8. The system of claim 7 , wherein the rationalization module is configured to generate episode features including features allowing for manual adjudication of each episode.

9. The system of claim 6 , wherein the arrhythmia analysis circuit comprises an automatic arrhythmia adjudicator configured to execute the adjudication algorithms each being a machine learning algorithm implementing a tachyarrhythmia adjudication algorithm.

10. The system of claim 6 , comprising an external device including the external telemetry circuit configured to receive the cardiac data from the implantable medical device, a remote device including at least the user interface, and a communication network coupling between the external device and the remote device.

11. A method for classifying cardiac arrhythmias, the method comprising:
receiving cardiac data representative of the one or more cardiac signals sensed by an implantable medical device, the one or more cardiac signals indicative of one or more arrhythmia episodes;
performing automatic adjudication of each episode of one or more arrhythmia episodes using the cardiac data, including executing a plurality of adjudication algorithms to produce voting classifications for each episode and determining an episode classification for each episode and a confidence level in the episode classification based on the voting classifications for each episode;
generating episode data representative of information associated with each episode including the episode classification, the confidence level in the episode classification and episode features including key features rationalizing the automatic adjudication of each episode;
storing the cardiac data and the episode data in a memory device; and
presenting the information associated with each episode.

12. The method of claim 11 , wherein the plurality of adjudication algorithms comprises machine learning algorithms each selected to implement a tachyarrhythmia adjudication algorithm.

13. The method of claim 12 , comprising determining an amount of machine learning algorithms to be included in the plurality of adjudication algorithms based on one or more estimated measures of accuracy in the automatic adjudication and an estimated potential need for manual adjudication by a user.

14. The method of claim 13 , comprising determining the amount of machine learning algorithms to be included in the plurality of adjudication algorithms based on one or more factors selected from:
a risk factor being a proportion of arrhythmia episodes with classification identified as high confidence classifications that are misclassified during the automatic adjudication to a total number of classified arrhythmia episodes;
a specificity factor being a proportion of misclassified arrhythmia episodes with classifications identified as low confidence classifications to the total number of classified arrhythmia episodes; and
a service burden factor being a proportion of arrhythmia episodes with classification identified as low confidence classifications to the total number of classified arrhythmia episodes.

15. The method of claim 11 , wherein performing the automatic adjudication comprises:
determining a voting classification of the voting classifications for each episode by executing an adjudication algorithm of the plurality of adjudication algorithms; and
determining the episode classification using one or more primary voting classifications selected from the voting classifications produced by executing the plurality of adjudication algorithms.

16. T

Assignees

• Cardiac Pacemakers Inc

Inventors

• Mahajan Deepa
• Pulliam Christopher
• Dong Yanting
• Perschbacher David L

Classifications

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H40/60

  for the operation of medical equipment or devices · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title

• A61B5/7275

  Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor · CPC title