Improving interpretability: combined use of LVQ and ARTMAP in decision support

• Autorzy: Kwok H. F. , Giorgi A. , Raffone A.
• Języki publikacji: EN

Abstrakty

EN

The learning vector quantization (LVQ) network was used to classify the ECG ST segment into different morphological categories. Due to the lack of data in the ST elevation categories, the classifier was only trained to identify different types of ST depressions (horizontal, upsloping and downsloping). The accuracies were 91%, 85% and 65% respectively for the training, validation and testing data respectively. Despite the low accuracy for the testing data, most of the mis-classifications were downsloping ST depression being classified as horizontal ST depression. We concluded that more data and more training are needed in order to train the LVQ to recognize other morphological types of ST deviation and to improve the accuracy.

Słowa kluczowe

EN

learning vector quantization; ARTMAP; decision support systems; ischemic heart disease

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2005
• Tom: nr 4
• Strony: 129--132
• Opis fizyczny: Bibliogr. 9 poz., rys.

Twórcy

autor

Kwok H. F.

• Sensory and Motor Neuroscience (SyMoN), Behavioural Brain Science Centre, Hills Building, The University of Birmingham, Edgbaston, Birmingham B15 2TT, United Kingdom

autor

Giorgi A.

• Department of Internal Medicine, Sensory and Motor Neuroscience San Raffaele Hospital (IRCCS) Via della Pisana n. 237 cap 00100 Rome, Italy

autor

Raffone A.

• Theoretical and Applied Simulation Laboratory Department of Psychology Sunderland University United Kingdom

Bibliografia

• [1] W. G. Baxt, “Use of artificial neural network for the diagnosis of myocardial infarction”, Ann. Int. Med., vol. 115, pp. 843–848, 1991.
• [2] B. Heden, M. Ohlsson, R. Rittner, O. Pahlm, W. K. Haisty Jr, C. Peterson, and L. Edenbrandt, “Agreement between artificial neural networks and experienced electrocardiographer on electrocardiographic diagnosis of healed myocardial infarction”, J. Amer. Coll. Cardiol., vol. 28, pp. 1012–1016, 1996.
• [3] J. S. Jorgensen, J. B. Pedersen, and S. M. Pedersen, “Use of neural networks to diagnose acute myocardial infarction. I. Methodology”, Clin. Chem., vol. 42, pp. 604–612, 1996.
• [4] R. L. Kennedy, R. F. Harrison, A. M. Burton, H. S. Fraser, W. G. Hamer, D. MacArthur, R. McAllum, and D. J. Steedman, “An artificial neural network system for diagnosis of acute myocardial infarction (AMI) in the accident and emergency department: evaluation and comparison with serum myoglobin measurements”, Comput. Meth. Progr. Biomed., vol. 52, pp. 93–103, 1997.
• [5] T. Kohonen, “Learning vector quantization”, in Self-Organising Maps, Springer Series in Information Sciences. Berlin, Heidelberg, New York: Springer-Verlag, 1995, 3rd ed.
• [6] H. F. Kwok, A. Giorgi, R. Fenici, and A. Raffone, “Identification of electrocardiogram characteristic points: wavelet transform vs derivative-based method”, J. Amer. Coll. Cardiol., vol. 43, no. 5 (Suppl. A), p. 400A, 2004.
• [7] N. Maglaveras, T. Stamkopoulos, and M. G. Strintzis, “An adaptive backpropagation neural network for real-time ischemic episodes detection: development and performance analysis using the European ST-T database”, IEEE Trans. Biomed. Eng., vol. 45, pp. 805–813, 1998.
• [8] B. P. Simon and C. Eswaran, “An ECG classifier designed using modified decision based neural networks”, Comput. Biomed. Res., vol. 30, pp. 257–272, 1997.
• [9] K.Wang, R.W. Asinger, and H. J. L. Marriot, “ST-segment elevation in conditions other than myocardial infarction”, New Eng. J. Med., vol. 349, pp. 2128–2135, 2003.