ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection

This paper presents a useful technique for totally automatic detection of myocardial infarction from patients' ECGs. Due to the large number of heartbeats constituting an ECG and the high cost of having all the heartbeats manually labeled, supervised learning techniques have achieved limited su...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on biomedical engineering Vol. 59; no. 12; pp. 3348 - 3356
Main Authors: Sun, Li, Lu, Yanping, Yang, Kaitao, Li, Shaozi
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.12.2012
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Adolescent
Adult
Aged
Aged, 80 and over
Algorithms
Biological and medical sciences
Cardiology. Vascular system
Classification
Classification algorithms
Computerized, statistical medical data processing and models in biomedicine
Coronary heart disease
ECG analysis
Electrocardiography
Electrocardiography - methods
Electrocardiography. Vectocardiography
Electrodiagnosis. Electric activity recording
Feature extraction
Female
Heart
Heart attacks
Heart beat
Heart Rate - physiology
Humans
Investigative techniques, diagnostic techniques (general aspects)
Male
Medical management aid. Diagnosis aid
Medical sciences
Middle Aged
multiple instance learning (MIL)
Myocardial infarction
myocardial infarction (MI)
Myocardial Infarction - diagnosis
Myocardial Infarction - physiopathology
ROC Curve
Signal Processing, Computer-Assisted
Studies
Support Vector Machine
Support vector machine classification
Training
Myocardial infarction
Multiple instance
multiple instance learning (MIL)
Cardiovascular disease
ECG analysis
Coronary heart disease
Myocardial disease
Learning
myocardial infarction (MI)
Electrodiagnosis
Acquisition process
Classification
Electrocardiography
Diagnosis
Biomedical engineering
ISSN:0018-9294, 1558-2531, 1558-2531
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a useful technique for totally automatic detection of myocardial infarction from patients' ECGs. Due to the large number of heartbeats constituting an ECG and the high cost of having all the heartbeats manually labeled, supervised learning techniques have achieved limited success in ECG classification. In this paper, we first discuss the rationale for applying multiple instance learning (MIL) to automated ECG classification and then propose a new MIL strategy called latent topic MIL, by which ECGs are mapped into a topic space defined by a number of topics identified over all the unlabeled training heartbeats and support vector machine is directly applied to the ECG-level topic vectors. Our experimental results on real ECG datasets from the PTB diagnostic database demonstrate that, compared with existing MIL and supervised learning algorithms, the proposed algorithm is able to automatically detect ECGs with myocardial ischemia without labeling any heartbeats. Moreover, it improves classification quality in terms of both sensitivity and specificity.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Conference-1
ObjectType-Feature-3
SourceType-Conference Papers & Proceedings-2
ISSN:0018-9294
1558-2531
1558-2531
DOI:10.1109/TBME.2012.2213597