Myocardial infarction: diagnosis and vital status prediction using neural networks

E. Micheli-Tzanakou, C. Yi, W. J. Kostis, D. M. Shindler, J. B. Kostis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Neural Networks have been found useful in many biomedical applications. The purpose of this paper is to apply Neural Networks (NN) to two specific problems in cardiology, namely, diagnosis of echocardiograms for myocardial infarction and prediction of vital status of patients that suffered such. We used NN to discriminate between normal and infarcted myocardium, by looking at intensity changes. The intensities of selected regions are used for training and testing. In predicting the vital status of patients that have suffered acute myocardial infarction, we used a large database (MIDAS) with follow-ups. The NN in this case has two hidden layers with eighteen patient variables from the MIDAS dataset as inputs. The NN was again trained with the feedback algorithm ALOPEX and tested with unknown data.

Original languageEnglish (US)
Title of host publicationComputers in Cardiology
PublisherPubl by IEEE
Pages229-232
Number of pages4
ISBN (Print)0818654708
StatePublished - 1993
EventProceedings of the 1993 Conference on Computers in Cardiology - London, UK
Duration: Sep 5 1993Sep 8 1993

Publication series

NameComputers in Cardiology
ISSN (Print)0276-6574

Other

OtherProceedings of the 1993 Conference on Computers in Cardiology
CityLondon, UK
Period9/5/939/8/93

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cardiology and Cardiovascular Medicine

Fingerprint

Dive into the research topics of 'Myocardial infarction: diagnosis and vital status prediction using neural networks'. Together they form a unique fingerprint.

Cite this