Analysis of extracted cardiotocographic signal features to improve automated prediction of fetal outcome

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

Abstrakty

EN

Cardiotocographic monitoring based on automated analysis of the fetal heart rate (FHR) signal is widely used for fetal assessment. However, the conclusion generation system is still needed to improve the abnormal fetal outcome prediction. Classification of the signals according to the predicted fetal outcome by means of neural networks is presented in this paper. Multi-layer perceptron neural networks were learned through seventeen time-domain signal features extracted during computerized analysis of 749 traces from 103 patients. The analysis included estimation of the FHR baseline, detection of acceleration and deceleration patterns as well as measurement of the instantaneous FHR variability. All the traces were retrospectively verified by the real fetal outcome defined by newborn delivery data. Influence of numerical and categorical representation of the input signal features, different data sets during learning, and gestational age as additional information, were investigated. We achieved the best sensitivity and specificity for the neural networks fed with numerical input variables together with additional information on the gestational age in the categorical form.

Słowa kluczowe

EN

cardiotocography; fetal heart rate; monitoring; fetal outcome prediction; pattern classification; signal analysis

PL

kardiotokografia; częstość akcji serca; monitorowanie płodu; klasyfikacja obrazu; analiza sygnału

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2010
• Tom: Vol. 30, no. 4
• Strony: 29--47
• Opis fizyczny: Bibliogr. 34 poz., rys., tab., wykr.

Twórcy

autor

Jeżewski M.

autor

Czabański R.

autor

Wróbel J.

autor

Horoba K.

• Department of Biomedical Signal Processing, Institute of Medical Technology and Equipment, ul. Roosevelta 118, 41-800 Zabrze, Poland,

Bibliografia

• 1. Jeżewski J., Wrobel J., Horoba K., Kupka T., Matonia A.: Centralised fetal monitoring system with hardware-based data flow control. Proc. III Inter. Conf. MEDSIP, 2006, 51-54.
• 2. Jeżewski M., Wrobel J., Horoba K., Gacek A., Henzel N., Leski J.: The prediction of fetal outcome by applying neural network for evaluation of CTG records. In: Computer Recognition Systems, Kurzynski M., Puchala E. (Eds), Advances in Soft Computing Series, Springer Verlag, 2007, 45, 532-541.
• 3. Catley C., Frize M., Walker R., Petriu D.: Predicting high-risk preterm birth using artificial neural networks. IEEE Trans. Inf. Technol. Biomed. 2006, 10, 540-549.
• 4. Jeżewski M., Czabanski R., Roj D., Wrobel J., Jeżewski J.: Application of RBF neural networks for predicting low birth weight using features extracted from fetal monitoring signals. IFMBE Proc. World Congr. Med. Phys. Biomed. Eng. 2009, 25, 374-377.
• 5. Jeżewski M., Czabanski R., Horoba K., Wrobel J.: Prediction of newborn sex with neural networks approach to fetal cardiotocograms classification. In: Information Technologies in Biomedicine, Pietka E., Kawa J. (Eds). Advances in Soft Computing Series, Springer Verlag, 2008, 47, 299-306.
• 6. Beksac M., Ozdemir K., Erkmen A., Karakas U.: Assessment of antepartum fetal heart rate tracings using neural networks. In: A critical appraisal of fetal surveillance. Van Geijn H.P., Copray F.J.(Eds), Elsevier Science B.V, 1994, 354-362.
• 7. Georgoulas G., Stylios C., Groumpos P.: Predicting the risk of metabolic acidosis fornewborns based on fetal heart rate signal classification using support vector machines, IEEE Trans. Biomed. Eng. 2006, 53, 875-884.
• 8. Arduini D., Giannini F., Magnes G., Signorini M.G.: Fuzzy logic in the management of new perinatal variables. Proc. 5th World Congr. Perinatal Medicine, Carrera J.M., Monduzzi E. (Eds), 2001, 1211-1216.
• 9. Salamalekis E., Thomopoulos P., Giannaris D., Salloum I.: Computerised intrapartum diagnosis of fetal hypoxia based on fetal heart rate monitoring and fetal pulse oximetry recordings utilising wavelet analysis and neural networks. Int. J. Obstet. Gynaecol. 2002, 109, 1137-1142.
• 10. Georgoulas G., Gavrilis D., Tsoulos J.G., Stylios C.: Novel approach for fetal heart rate classification introducing grammatical evolution. Biomed. Signal Proc. Control 2007, 2, 69-79.
• 11. Georgoulas G., Stylios C., Groumpos P.: Feature extraction and classification of fetal heart rate using wavelet analysis and support vector machines. Int. J. Artif. Intel. Tools 2006, 15, 411-432.
• 12. Magenes G., Signorini M.G., Sassi R.: Multiparametric analysis of fetal heart rate: comparison of neural and statistical classifiers. Proc. 9th Conf. Med. Eng. Comput., 2001, 360-363.
• 13. Hasbargen U.: Application of neural networks for intrapartum surveillance. In: A critical appraisal of fetal surveillance, Geijn H.P., Copray F.J. (Eds), Elsevier Science BV 1994, 363-367.
• 14. Fontenla-Romero O., Alonso-Betanzos A., Guijarro-Berdinas B.: Adaptive pattern recognition in the analysis of cardiotocographic records. IEEE Trans. Neural Networks 2001, 12, 1188-1195.
• 15. Guijarro-Berdinas B., Alonso-Betanzos A., Fontenla-Romero O.: Intelligent analysis and pattern recognition in cardiotocographic signals using a tightly coupled hybrid system, Artif. Intel. 2002, 136, 1-27.
• 16 Keith R., Westgate J., Ifeachor E., Greene K.: Suitability of artificial neural networks for feature extraction during labour. Med. Biol. Eng. Comput.1994, 32, 51-57.
• 17 Kol S., Thaler I., Paz N., Shmueli O.: Interpretation of nonstress test by an artificial neural networks. Am. J. Obstet. Gynecol. 1995, 172, 1372-1378.
• 18. Magenes G., Signorini M.G., Sassi R.: Automatic diagnosis of fetal heart rate: comparison of different methodological approaches. Proc. 23rd Intern. Conf. IEEE EMBS 2001, 1, 1604-1607.
• 19. Czabanski R., Jeżewski M., Wrel J., Jeżewski J.: Fuzzy system for evaluation of fetal heart rate signals using FIGO criteria. J. Med. Inform. Technol. 2009, 13, 189-194.
• 20. Czabanski R., Jeżewski M., Wróbel J., Jeżewski J., Horoba K.: Predicting the risk of low fetal birth weight from cardiotocographic signals using ANBLIR system with deterministic annealing and e-insensitive learning. IEEE Trans. Inf. Technol. BioMed. 2010, 14, 1062-1074.
• 21. Magenes G., Signorini M.G., Arduini D.: Classification of cardiotocographic records by neural networks. Proc. IEEE Intern. Joint Conf. Neural Networks 2000, 3, 637-641.
• 22. Arduini D., Giannini F., Magenes G.: Intrapartum surveillance - computer cardiotocography. Proc. 5th World Congress of Perinatal Medicine, 2001, 1217-1223.
• 23. Ayres-de-Campos D., Costa-Santos C., Bernardes J.: Prediction of neonatal state by computer analysis of fetal heart rate tracings - the antepartum arm of the SisPorto multicentre validation study. Eur. J. Obstet. Gynecol. Reprod. Biol. 2005, 118, 52-60.
• 24. Dawes G.S., Moulden M., Redman C.W.: Limitations of antenatal fetal heart rate monitors. Am. J. Obstet. Gynecol. 1990, 162, 170-173.
• 25. Jeżewski J., Kupka T., Horoba K.: Extraction of fetal heart rate signal as time event series from evenly sampled data acquired using Doppler ultrasound technique. IEEE Trans. Biomed. Eng. 2008, 55, 805-810.
• 26. van Geijn H.P.: Analysis of heart rate and beat-to-beat variability: Interval difference index. Am. J. Obstet. Gynecol. 1980, 138, 246-252.
• 27. Jeżewski J., Wrobel J., Horoba K., Moczko J.: Advances in Doppler ultrasound FHR monitoring. Klin. Perinat. Ginekol. 1995, 3, 241-251.
• 28. Rooth G.: Guidelines for the use of fetal monitoring. Int. J. Gynecol. Obstet. 1987, 25, 159-167.
• 29. Dawes G.S., Houghton C.R.: Baseline in human fetal heart rate records. Br. J. Obstet. Gynaecol. 1982, 89, 270-275.
• 30. Mantel R., van Geijn H.P., Caron F.J., Swartjes J.M.: Computer analysis of antepartum fetal heart rate: 1. Baseline determination. Int. J. Bio. Med. Comput. 1990, 25, 261-272.
• 31. Jeżewski J., Wrobel J., Horoba K.: Comparison of Doppler ultrasound and direct electrocardiography acquisition techniques for quantification of fetal heart rate variability. IEEE Trans. Biomed. Eng. 2006, 53, 855-864.
• 32 Jeżewski J., Horoba K., Matonia A., Wrobel J.: Quantitative analysis of contraction patterns in electrical activity signal of pregnant uterus as an alternative to mechanical approach. Physiol, Meas. 2005, 26, 753-767.
• 33. Jeżewski M., Henzel N., Wrobel J., Labaj P.: Application of neural networks for prediction of fetal outcome. J. Med. Inform. Technol. 2006, 10, 127-132.
• 34. Sikora J.: Digital analysis of cardiotocographic traces for clinical fetal outcome prediction. Klin. Perinat. Ginekol. 2001, 10, 57-88.