Abstract
Cardiotocography (CTG) is a critical component of prenatal fetal monitoring, offering essential multivariate time series data that enables healthcare professionals to assess fetal growth and implement timely interventions for abnormal conditions, ensuring optimal fetal well-being. However, conventional CTG interpretation are susceptible to individual clinical experience and inconsistencies in assessment guidelines. To address these limitations, this study investigates artificial intelligence algorithms for developing an objective fetal assessment method based on multivariate time-series signals of fetal heart rate and uterine contractions. We preprocess data from an open-source fetal heart rate and contraction database, addressing missing values and noise reduction, and enhance the dataset for reliable experimentation. We also propose multivariate time-series signal models, including MT-1DCG, A-BiGRU, and ST-1DCG. The performance of the MT-1DCG model is validated through multiple experiments, demonstrating superior results compared to A-BiGRU and ST-1DCG models. Standard evaluation metrics, including accuracy, sensitivity, specificity, and ROC, are employed to assess model performance. The proposed MT-1DCG model yields an accuracy of 95.15%, sensitivity of 96.20%, and specificity of 94.09% in the test set. These findings indicate that our method effectively evaluates fetal health status and can support obstetricians in clinical decision-making.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asfaw, D., Jordanov, I., Impey, L., Namburte, A., Lee, R., Georgieva, A.: Multimodal deep learning for predicting adverse birth outcomes based on early labour data. Bioengineering 10(6), 730 (2023)
Baghel, N., Burget, R., Dutta, M.K.: 1D-FHRNet: automatic diagnosis of fetal acidosis from fetal heart rate signals. Biomed. Signal Process. Control 71, 102794 (2022)
Boudet, S., Houzé de l’Aulnoit, A., Peyrodie, L., Demailly, R., Houzé de l’Aulnoit, D.: Use of deep learning to detect the maternal heart rate and false signals on fetal heart rate recordings. Biosensors 12(9), 691 (2022)
Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)
Cui, Z., Chen, W., Chen, Y.: Multi-scale convolutional neural networks for time series classification. arXiv preprint arXiv:1603.06995 (2016)
Dervaitis, K.L., Poole, M., Schmidt, G., Penava, D., Natale, R., Gagnon, R.: ST segment analysis of the fetal electrocardiogram plus electronic fetal heart rate monitoring in labor and its relationship to umbilical cord arterial blood gases. Am. J. Obstet. Gynecol. 191(3), 879–884 (2004)
Fasihi, M., Nadimi-Shahraki, M.H., Jannesari, A.: A shallow 1-D convolution neural network for fetal state assessment based on cardiotocogram. SN Comput. Sci. 2(4), 287 (2021)
Fei, Y., et al.: Intelligent classification of antenatal cardiotocography signals via multimodal bidirectional gated recurrent units. Biomed. Signal Process. Control 78, 104008 (2022)
Georgoulas, G.G., Stylios, C.D., Nokas, G., Groumpos, P.P.: Classification of fetal heart rate during labour using hidden Markov models. In: 2004 IEEE International Joint Conference on Neural Networks, vol. 3, pp. 2471–2475. IEEE (2004)
Leszczynska-Gorzelak, B., Poniedzialek-Czajkowska, E., Oleszczuk, J.: Intrapartum cardiotocography and fetal pulse oximetry in assessing fetal hypoxia. Int. J. Gynecol. Obstet. 76(1), 9–14 (2002)
Li, J., et al.: Automatic classification of fetal heart rate based on convolutional neural network. IEEE Internet Things J. 6(2), 1394–1401 (2018)
Liang, S., Li, Q.: Automatic evaluation of fetal heart rate based on deep learning. In: 2021 2nd Information Communication Technologies Conference (ICTC), pp. 235–240. IEEE (2021)
Liu, M., Lu, Y., Long, S., Bai, J., Lian, W.: An attention-based CNN-BiLSTM hybrid neural network enhanced with features of discrete wavelet transformation for fetal acidosis classification. Expert Syst. Appl. 186, 115714 (2021)
Nunes, I., Ayres-de Campos, D.: Computer analysis of foetal monitoring signals. Best Pract. Res. Clin. Obstet. Gynaecol. 30, 68–78 (2016)
Ogasawara, J., et al.: Deep neural network-based classification of cardiotocograms outperformed conventional algorithms. Sci. Rep. 11(1), 13367 (2021)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations (ICLR 2015) (2015)
Spairani, E., Daniele, B., Signorini, M.G., Magenes, G.: A deep learning mixed- data type approach for the classification of FHR signals. Front. Bioeng. Biotechnol. 10 (2022)
Xiao, Y., Lu, Y., Liu, M., Zeng, R., Bai, J.: A deep feature fusion network for fetal state assessment. Front. Physiol. 13, 2506 (2022)
Zanardo, V., De Luca, F., Simbi, A.K., Parotto, M., Guerrini, P., Straface, G.: Umbilical cord blood acid-base analysis and the development of significant hyper-bilirubinemia in near-term and term newborns: a cohort study. Ital. J. Pediatr. 43(1), 1–5 (2017)
Zhao, Z., Deng, Y., Zhang, Y., Zhang, Y., Zhang, X., Shao, L.: DeepFHR: intelligent prediction of fetal acidemia using fetal heart rate signals based on convolutional neural network. BMC Med. Inform. Decis. Mak. 19, 1–15 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Lu, Y., Liang, H., Yu, Z., Fu, X. (2023). MT-1DCG: A Novel Model for Multivariate Time Series Classification. In: Huang, DS., Premaratne, P., Jin, B., Qu, B., Jo, KH., Hussain, A. (eds) Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore. https://doi.org/10.1007/978-981-99-4742-3_18
Download citation
DOI: https://doi.org/10.1007/978-981-99-4742-3_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4741-6
Online ISBN: 978-981-99-4742-3
eBook Packages: Computer ScienceComputer Science (R0)