Influence of gestational age on neural networks interpretation of fetal monitoring signals

• Autorzy: Jeżewski M. , Czabański R. , Horoba K. , Wróbel J. , Łęski J. , Jeżewski J.
• Języki publikacji: EN

Abstrakty

EN

Cardiotocographic monitoring (CTG) is a primary biophysical monitoring method for assessment of the fetal state and is based on analysis of fetal heart rate, uterine contraction activity and fetal movement signals. Visual analysis of CTG traces is very difficult so computer-aided fetal monitoring systems have become a standard in clinical centres. We proposed the application of neural networks for the prediction of fetal outcome using the parameters of quantitative description of acquired signals as inputs. We focused on the influence of the gestational age (during trace recording) on the fetal outcome classification quality. We designed MLP and RBF neural networks with changing the number of neurons in the hidden layer to find the best structure. Networks were trained and tested fifty times, with random cases assignment to training, validating and testing subset. We obtained the value of sensitivity index above 0.7, what may be regarded as good result. However additional trace grouping within similar gestational age, increased classification quality in the case of MLP networks.

Słowa kluczowe

EN

fetal monitoring; cardiotocography; classification; neural networks (NN)

PL

monitoring płodu; kardiotokografia; klasyfikacja; sieci neuronowe

• Wydawca: University of Silesia, Institute of Informatics, Computer Systems Department
• Czasopismo: Journal of Medical Informatics & Technologies
• Rocznik: 2008
• Tom: Vol. 12
• Strony: 137--142
• Opis fizyczny: Bibliogr. 12 poz., rys., tab.

Twórcy

autor

Jeżewski M.

• Division of Biomedical Electronics, Institute of Electronics, Silesian University of Technology, Gliwice, Poland

autor

Czabański R.

autor

Horoba K.

autor

Wróbel J.

autor

Łęski J.

autor

Jeżewski J.

Bibliografia

• [1] CATLEY C., FRIZE M., WALKER R., PETRIU D.C., Predicting high-risk preterm birth using artificial neural networks, IEEE Trans. Inf. Technol. Biomed., Vol. 10, No 3, 2006, pp. 540-549.
• [2] CZABAŃSKI R., JEŻEWSKI M., WRÓBEL J., HOROBA K., JEŻEWSKI J.: A neuro-fuzzy approach to the classification of fetal cardiotocograms, IFMBE Proc., Vol. 20, 2008, pp. 446-449.
• [3] CZOGAŁA E., ŁĘSKI J.: Fuzzy and Neuro-Fuzzy Intelligent Systems, Physica-Verlag, A Springer –Verlag Company, 2000.
• [4] DAWES N. W., DAWES G. S., MOULDEN M., REDMAN CH. W. G.: Fetal heart rate patterns in term labour vary with sex, gestational age, epidural analgesia, and fetal weight, Am. J. Obstet. Gynaecol., 1999, Vol. 180, pp. 181-187.
• [5] DRUZIN M. L., MILTON HUTSON J., EDERSHEIM T.G.: Relationship of baseline fetal heart rate to gestational age and fetal sex, Am. J. Obstet. Gynaecol., 1986, Vol. 154, pp. 1102-1103.
• [6] ENNETT C.M., FRIZE M., SCALES N.: Evaluation of the logarithmic-sensitivity index as a neural network stopping criterion for rare outcomes, Proc. of 4th IEEE Conf. Inform. Technol. Applic. Biomed., 2003, pp. 338-341.
• [7] HAYKIN S.: Neural networks: A guided tour, in: Nonlinear Biomedical Signal Processing, Vol. 1, Fuzzy Logic, Neural Networks and New Algorithms, Editor: Akay M.
• [8] JEZEWSKI J., WROBEL J., HOROBA K.: Computerized perinatal database for retrospective qualitative assessment of CTG traces in „Current Perspectives in Healthcare Computing”, Editor: B. Richards, BTHC, 1996, pp. 187-196.
• [9] JEŻEWSKI M., WRÓBEL J., HOROBA K., GACEK A., HENZEL N., ŁĘSKI J.: The prediction of fetal outcome by applying neural network for evaluation of CTG records, in: Computer Recognition Systems, Editors: Kurzyński M., Puchała E., et. al., Advances in Soft Computing Series, Springer Verlag, 2007, pp. 532-541.
• [10] JEZEWSKI J., WROBEL J., HOROBA K., KUPKA T., MATONIA A.: Centralised fetal monitoring system with hardware-based data flow control, Proc. of 3rd Inter. Conf. MEDSIP, Glasgow, VII 2006, pp. 51–54.
• [11] JEŻEWSKI M., WRÓBEL J., ŁABAJ P., ŁĘSKI J., HENZEL N., HOROBA K., JEŻEWSKI J.: Some practical remarks on neural networks approach to fetal cardiotocograms classification, Proc. of 29th Int. Conf. IEEE EMBS, 2007, pp. 5170-5173.
• [12] LANGE S., VAN LEEUWEN P., GEUE D., HATZMANN W., GRONEMEYER D.: Influence of gestational age, heart rate, gender and time of day on fetal heart rate variability, Med. Biol. Eng. Comput., Vol. 43, 2005, pp. 481-486.