Artificial neural networks for automatic ECG analysis
- 1 May 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 46 (5), 1417-1425
- https://doi.org/10.1109/78.668803
Abstract
The analysis of ECGs can benefit from the wide availability of computing technology. This paper presents some results achieved by carrying out the classification tasks of equipment integrating the most common features of the ECG analysis: arrhythmia, myocardial ischemia, chronic alterations. Several ANN architectures are implemented, tested, and compared with competing alternatives. The approach, structure, and learning algorithm of ANNs are designed according to the features of each particular classification task. The trade-off between the time consuming training of ANNs and their performance is also explored. Data pre- and post-processing efforts for system performance are critically tested. The crucial role of these efforts for the reduction of input space dimensions, for a more significant description of the input features, and for improving new or ambiguous event processing is also documented. Finally, algorithm assessment is done on data coming from available ECG databases.Keywords
This publication has 15 references indexed in Scilit:
- One-lead ischemia detection using a new backpropagation algorithm and the European ST-T databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Assessing the robustness of algorithms for detecting transient ischemic ST segment changesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Unified integration of explicit knowledge and learning by example in recurrent networksIEEE Transactions on Knowledge and Data Engineering, 1995
- Learning in multilayered networks used as autoassociatorsIEEE Transactions on Neural Networks, 1995
- The European ST-T database: standard for evaluating systems for the analysis of ST-T changes in ambulatory electrocardiographyEuropean Heart Journal, 1992
- Neural networks for classification of ECG ST-T segmentsJournal of Electrocardiology, 1992
- Recommendations for standardization and specifications in automated electrocardiography: bandwidth and digital signal processing. A report for health professionals by an ad hoc writing group of the Committee on Electrocardiography and Cardiac Electrophysiology of the Council on Clinical Cardiology, American Heart Association.Circulation, 1990
- An approach to cardiac arrhythmia analysis using hidden Markov modelsIEEE Transactions on Biomedical Engineering, 1990
- Learning State Space Trajectories in Recurrent Neural NetworksNeural Computation, 1989
- Computer system for analysis of ST segment changes on 24 hour Holter monitor tapes: Comparison with other available systemsJournal of the American College of Cardiology, 1984