Browse Prior Art Database

Shape Classification of Waveforms (Qrs Complexes) in Electrocardiogram Records

IP.com Disclosure Number: IPCOM000060030D
Original Publication Date: 1986-Feb-01
Included in the Prior Art Database: 2005-Mar-08
Document File: 1 page(s) / 13K

Publishing Venue

IBM

Related People

Miller, JM: AUTHOR

Abstract

This article describes a solution to the problem of rapidly classifying heartbeat waveforms (QRS complexes) into shape categories in long electrocardiogram records. Long electrocardiogram (ECG) records contain large amounts of digitized data which must be processed either manually or by computer to detect heartbeat waveforms and classify them as being normal or abnormal. This article includes three component sections which describe a technique for accomplishing this and includes determining criteria for establishing the 'normal' shape category, providing a method for rapidly classifying heartbeat waveforms into either the normal or pathological shape categories, and providing a means of deciding when to create new shape categories. The basic steps of the present technique are as follows: 1.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 1 of 1

Shape Classification of Waveforms (Qrs Complexes) in Electrocardiogram Records

This article describes a solution to the problem of rapidly classifying heartbeat waveforms (QRS complexes) into shape categories in long electrocardiogram records. Long electrocardiogram (ECG) records contain large amounts of digitized data which must be processed either manually or by computer to detect heartbeat waveforms and classify them as being normal or abnormal. This article includes three component sections which describe a technique for accomplishing this and includes determining criteria for establishing the 'normal' shape category, providing a method for rapidly classifying heartbeat waveforms into either the normal or pathological shape categories, and providing a means of deciding when to create new shape categories. The basic steps of the present technique are as follows: 1. QRS waveforms and the shape categories into which they may be classified are each characterized by descriptors consisting of a structured representation: sets of 2 or 3 selected, proximate first differences of the original smoothed data with interval(s) between; and ancillary derived quantities, which include a quality score and a noise measure. The descriptors for the waveform shape categories are obtained as moving averages of those from the waveforms classified in them. Structured representations are obtained as described in [*]. This simple characterization of the QRS complex has not been used previously. It permits rapid classification of the waveform shapes. 2. A shape category for 'normal' waveforms is established at the outset from the descriptors for the first candidate beats processed. The prototype for the shape category must have descriptors consistently present in a sequence of candidate beats and satisfying criteria concerning width, quality, strength and noise. The shape category fo...