Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2003 Winter;8(4):206-11.

Classification of cardiac patient states using artificial neural networks

N Kannathal  1 , U Rajendra Acharya, Choo Min Lim, Pk Sadasivan, Sm Krishnan
Affiliations

Classification of cardiac patient states using artificial neural networks

N Kannathal et al. Exp Clin Cardiol. 2003 Winter.

Abstract

Electrocardiogram (ECG) is a nonstationary signal; therefore, the disease indicators may occur at random in the time scale. This may require the patient be kept under observation for long intervals in the intensive care unit of hospitals for accurate diagnosis. The present study examined the classification of the states of patients with certain diseases in the intensive care unit using their ECG and an Artificial Neural Networks (ANN) classification system. The states were classified into normal, abnormal and life threatening. Seven significant features extracted from the ECG were fed as input parameters to the ANN for classification. Three neural network techniques, namely, back propagation, self-organizing maps and radial basis functions, were used for classification of the patient states. The ANN classifier in this case was observed to be correct in approximately 99% of the test cases. This result was further improved by taking 13 features of the ECG as input for the ANN classifier.

Keywords: Electrocardiogram; Heart rate; Intensive care unit; Neural network; Radial basis function; Self-organizing map.

PubMed Disclaimer

Figures

Figure 1)
Figure 1)
Cardiac patient state classification system overview. ECG Electrocardiogram
Figure 2)
Figure 2)
Electrocardiogram measurements made by ST-segment analyzer
Figure 3)
Figure 3)
Five-layer feedforward neural network classifier
Figure 4)
Figure 4)
Five-layer feedforward neural network classifier
Figure 5)
Figure 5)
Probabilistic neural network architecture
See this image and copyright information in PMC

References

    1. Li G, Ye W, Lin L, Yu Q, Yu X. An artificial intelligence approach to ECG analysis. IEEE Eng Med Biol Mag. 2000;19:95–100. - PubMed
    1. Silipo R, Marchesi C. Artificial neural networks for automatic ECG analysis. IEEE Trans Signal Process. 1998;46:1417–25.
    1. van Gils M, Jansen H, Nieminen K, Summers R, Weller PR. Using artificial neural network for classifying ICU patient states. IEEE Eng Med Biol Mag. 1997;16:41–7. - PubMed
    1. Williams JL, Lesaffre E. Comparison of multigroup logistic and linear discriminant ECG and VCG classification. J Electrocardiol. 1987;20:83–92. - PubMed
    1. Coast AD, Stern RM, Casio GG, Britter SA. An approach to cardiac arrhythmia analysis using hidden Markov models. IEEE Trans Biomed Eng. 1990;37:826–35. - PubMed

LinkOut - more resources