Unsupervised clustering for fetal state assessment based on selected features of the cardiotocographic signals

• Autorzy: Przybyła T. , Jeżewski J. , Roj D.
• Języki publikacji: EN

Abstrakty

EN

In modern obstetrics the cardiotocography is a routine method of fetal condition assessment based mainly on analysis of the fetal heart rate signals. The correct interpretation of recorded traces from a bedside monitor is very difficult even for experienced clinicians. Therefore, computerized fetal monitoring systems are used to yield the quantitative description of the signal. However, the effective techniques enabling automated conclusion generation based on cardiotocograms are still being searched. The paper presents an attempt to diagnose the fetal state basing on seventeen features describing the cardiotocographic records. The proposed method applies the unsupervised classification of signals. During our research we tried to classify the fetal state using the fuzzy c-means (FCM) clustering. We also tested how the efficiency of classification could be influenced by application of principal component analysis (PCA) algorithm. The obtained results showed that unsupervised classification cannot be considered as a support to fetal state assessment.

Słowa kluczowe

EN

unsupervised classification; fuzzy clustering; principal component analysis; fetal monitoring

PL

klasyfikacja algorytmów bez nadzoru; grupowanie danych; monitoring płodu; kardiotokografia

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2009
• Tom: Vol. 13
• Strony: 157--162
• Opis fizyczny: Bibliogr. 15 poz., tab.

Twórcy

autor

Przybyła T.

• Silesian University of Technology, Institute of Electronics, ul. Akademicka 16, 44-100 Gliwice, Poland

autor

Jeżewski J.

autor

Roj D.

Bibliografia

• [1] BEZDEK J.C., Pattern Recognition With Fuzzy Objective Function Algorithms. Plenum, New York, 1981.
• [2] CZABAŃSKI R., JEŻEWSKI M., WRÓBEL J. et al., The Prediction of The Low Fetal Birth Weight Based on Quantitative Description Of Cardiotocographic Signals, Journal of Medical Informatics and Technologies, Vol. 12, pp. 97-102, 2008.
• [3] DAWES G.S., REDMAN C.W.G., Patterns of the normal human fetal heart rate, British Journal of Obstetrics and Gynaecology., 89, pp. 276-284, 1982.
• [4] DUDA R.O., HART P.E., STORK D.G., Pattern Classification. Wiley-Interscience, New Jersey, 2000.
• [5] JEŻEWSKI J., WRÓBEL J., HOROBA K. et al., Centralised Fetal Monitoring System With Hardware-Based Data Flow Control, Proc. of III Int. Conf. MEDSIP, pp. 51-54, Glasgow, 2006.
• [6] JEŻEWSKI M., CZABAŃSKI R., HOROBA K. et al., Prediction of newborn sex with neural networks approach to fetal cardiotocograms classification. In: Pietka E., Kawa J. (eds) Advances in Soft Computing Series, Vol. 47, pp. 299-306, 2008.
• [7] JEŻEWSKI M., WRÓBEL J., HOROBA K. et al., The prediction of fetal outcome by applying neural network for evaluation of CTG records. In: Kurzyński M., Puchała E., et. al. (eds) Advances in Soft Computing Series, Vol. 45, pp. 532-541, Springer Verlag, 2007.
• [8] JIANG X. Asymmetric Principal Component Analysis and Discriminant Analyses for Pattern Classification, IEEE Trans Pattern Analysis and Machine Intelligence, Vol. 31, pp. 931-937, 2009.
• [9] KAUFMAN L., ROUSSEEUW P. Finding Groups In Data. Wiley-Interscience, New Jersey, 1990.
• [10] PEDRYCZ W. Knowledge-Based Clustering. Wiley-Interscience, New Jersey, 2005.
• [11] PRZYBYŁA T., Breast Cancer Diagnosis via Fuzzy Clustering With Partial Supervision, Task Quarterly 8, pp. 193-198, 2004.
• [12] SCHOELKOPF B., SMOLA A.J. Learning with Kernels. The MIT Press, 2002.
• [13] SHAWE-TAYLOR J., CRISTIOANINI N. Kernel Methods for Pattern Analysis. Cambridge University Press, 2004.
• [14] SŁOMKO Z., Biofizyczne Monitorowanie w Medycynie Perinatalnej, PWN, Warszawa, 1991.
• [15] van GEIJN H.P., Fetal monitoring _ present and future: the evaluation of fetal heart rate patterns, European Journal of Obstetrics Gynecology and Reproductive Biology, 24, pp. 117-119, 1987.