Use of machine learning for classification of magneto cardiograms

• US 8,744,557 B2
• Filed: 02/20/2013
• Issued: 06/03/2014
• Est. Priority Date: 07/01/2003
• Status: Expired due to Fees

• Current Assignee: Cardio MAG Imaging Incorporated
• Original Assignee: Cardio MAG Imaging Incorporated
• Inventors: Sternickel, Karsten, Szymanski, Boleslaw, Embrechts, Mark
• Primary Examiner(s): MANUEL, GEORGE C
• Application Number:
  US13/772,138
• Publication Number:
  US 20130178730A1
• Time in Patent Office: 468 Days
• Field of Search: 600/509
• US Class Current: 600/509
• CPC Class Codes: A61B 2560/0475 Special features of memory means, e.g. removable memory cards
• CPC Class Codes: A61B 5/243 specially adapted for magnetocardiographic [MCG] signals
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G06N 3/086 using evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering.

Claims

1. A method for automating the identification of meaningful features and the formulation of expert rules for classifying magnetocardiography data, comprising:

applying a kernel transform to sensed data acquired from sensors sensing magnetic fields generated by a patient'"'"'s heart activity, resulting in transformed data; and

identifying said meaningful features and formulating said expert rules from said transformed data, using machine learning.

2. The method of claim 1, said kernel transform satisfying Mercer conditions.

3. The method of claim 1, said kernel transform comprising a radial basis function.

4. The method of claim 1, said applying a kernel transform comprising:

assigning said transformed data to a first hidden layer of a neural network;

applying training data descriptors as weights of said first hidden layer of said neural network; and

calculating weights of a second hidden layer of said neural network numerically.

5. The method of claim 1, further comprising:

classifying said transformed data using direct kernel partial least square (DK-PLS) machine learning.

6. The method of claim 1, further comprising transforming said sensed data into wavelet domain data prior to applying said kernel transform by:

applying a Daubechies wavelet transform to said sensed data.

7. The method of claim 6, further comprising:

selecting features from said wavelet domain data which improve said classification of magnetocardiography data.

8. The method of claim 1, further comprising:

normalizing said sensed data.

9. The method of claim 8, said normalizing said sensed data comprising:

Mahalanobis scaling said sensed data.

10. The method of claim 1, further comprising:

centering a kernel of said kernel transform.

11. An apparatus for automating the identification of meaningful features and the formulation of expert rules for classifying magnetocardiography data, comprising computerized storage, processing and programming for:

applying a kernel transform to sensed data acquired from sensors sensing magnetic fields generated by a patient'"'"'s heart activity, resulting in transformed data; and

identifying said meaningful features and formulating said expert rules from said transformed data, using machine learning.

12. The apparatus of claim 11, wherein kernel transform satisfies Mercer conditions.

13. The apparatus of claim 11, said kernel transform comprising a radial basis function.

14. The apparatus of claim 11, said computerized storage, processing and programming for applying a kernel transform further comprising computerized storage, processing and programming for:

assigning said transformed data to a first hidden layer of a neural network;

applying training data descriptors as weights of said first hidden layer of said neural network; and

calculating weights of a second hidden layer of said neural network numerically.

15. The apparatus of claim 11, further comprising computerized storage, processing and programming for:

classifying said transformed data using direct kernel partial least square (DK-PLS) machine learning.

16. The apparatus of claim 11, further comprising using said computerized storage, processing and programming for transforming said sensed data into wavelet domain data prior to applying said kernel transform by:

applying a Daubechies wavelet transform to said sensed data.

17. The apparatus of claim 16, further comprising using said computerized storage, processing and programming for:

selecting features from said wavelet domain data which improve said classification of magnetocardiography data.

18. The apparatus of claim 11, further comprising computerized storage, processing and programming for:

normalizing said sensed data.

19. The apparatus of claim 18, said computerized storage, processing and programming for normalizing said sensed data comprising computerized storage, processing and programming for:

Mahalanobis scaling said sensed data.

20. The apparatus of claim 11, further comprising computerized storage, processing and programming for:

centering a kernel of said kernel transform.