MACHINE LEARNING FOR CLASSIFICATION OF MAGNETO CARDIOGRAMS

Title:

MACHINE LEARNING FOR CLASSIFICATION OF MAGNETO CARDIOGRAMS

Document Type and Number:

WIPO Patent Application WO2005002313

Kind Code:

A3

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. The results, similar for all three methods, were encouraging, exceeding the quality of classification achieved by the trained experts. Thus, a device and associated method for classifying cardiography data is disclosed, comprising applying a kernel transform to sensed data acquired from sensors sensing electromagnetic heart activity, resulting in transformed data, prior to classifying the transformed data using machine learning.

Inventors:

STERNICKEL KARSTEN (US)
EMBRECHTS MARK J (US)
SZYMANSKI BOLESLAW K (US)

Application Number:

PCT/US2004/021307

Publication Date:

March 31, 2005

Filing Date:

July 01, 2004

Export Citation:

Click for automatic bibliography generation Help

Assignee:

CARDIOMAG IMAGING INC CMI (US)
STERNICKEL KARSTEN (US)
EMBRECHTS MARK J (US)
SZYMANSKI BOLESLAW K (US)

International Classes:

A61B5/04; A61B5/08; G06F17/00; G06K9/00; (IPC1-7): A61B5/08

Foreign References:

US4958638A	1990-09-25
US6210344B1	2001-04-03

Other References: