Presentation 1994/12/16
Differential diagnosis of myocardial infarction between automatic ECG diagnosis system and neural network system
Kenji Shimizu, Koji Oguri, Akira Iwata, Kazunobu Yamauchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recent automatic ECG diagnose systems have high performance.But these systems are apt to give the desease decission even for suspricious case.For these overestimated cases for example 'poor R wave progress or QS V1,2 wave',a neural network method is applied to cleassify whether those are really desease case or not.A back propagation neural network was designed to classify between myocardial infarction or not.Diagnostic accuracy is 96.21% under this neural network system using leave one out method.Thus an automatic ECG diagnose system using artificial neural network can classify high specificity and sensitivity.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / automatic diagnosis of ECG / myocardial infarction
Paper # MBE94-96
Date of Issue

Conference Information
Committee MBE
Conference Date 1994/12/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To ME and Bio Cybernetics (MBE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Differential diagnosis of myocardial infarction between automatic ECG diagnosis system and neural network system
Sub Title (in English)
Keyword(1) neural network
Keyword(2) automatic diagnosis of ECG
Keyword(3) myocardial infarction
1st Author's Name Kenji Shimizu
1st Author's Affiliation Nagoya Institute of Technology()
2nd Author's Name Koji Oguri
2nd Author's Affiliation Aichi Pref.University
3rd Author's Name Akira Iwata
3rd Author's Affiliation Nagoya Institute of Technology
4th Author's Name Kazunobu Yamauchi
4th Author's Affiliation Nagoya University School of Med.
Date 1994/12/16
Paper # MBE94-96
Volume (vol) vol.94
Number (no) 416
Page pp.pp.-
#Pages 6
Date of Issue