Transformative advancements in fetal cardiac health on BiLSTM networks for FPCG classification

Yojana Sharma; Shashwati Ray; Om Prakash Yadav

doi:10.3103/S0735272724030026

Authors

Yojana Sharma Bhilai Institute of Technology, Durg, India https://orcid.org/0000-0002-7576-668X
Shashwati Ray Bhilai Institute of Technology, Durg, India https://orcid.org/0000-0002-5721-1007
Om Prakash Yadav PES Institute of Technology and Management, Shivamogga, India https://orcid.org/0000-0001-6306-9396

DOI:

https://doi.org/10.3103/S0735272724030026

Keywords:

FPCG, deep learning networks, recurrent neural networks, long short-term memory networks, temperature inaccuracy, precision, BiLSTM

Abstract

This article unveils a cutting-edge methodology for Fetal Phonocardiogram (FPCG) classification employing Bidirectional Long Short-Term Memory (BiLSTM) networks. Acknowledging the pivotal role of fetal heart monitoring in early anomaly detection, the research delves into the profound insights offered by FPCG signals concerning fetal cardiac activity. The innovative approach encompasses preprocessing FPCG signals using Mel-Frequency Cepstral Coefficients (MFCC) and spectrogram features, coupled with the strategic application of BiLSTM networks, ensuring a resilient classification framework. The bidirectional nature of the LSTM architecture elevates the model’s ability to capture temporal dependencies in both forward and backward directions, facilitating the discernment of intricate patterns in fetal heart sounds. Experimental findings demonstrate a 98% accuracy, reaffirming the effectiveness and precision of the BiLSTM approach in FPCG classification. This research significantly advances automated methods for evaluating fetal cardiac health, promising transformative enhancements in prenatal care.

References

P. Chetlur Adithya, R. Sankar, W. A. Moreno, S. Hart, “Trends in fetal monitoring through phonocardiography: Challenges and future directions,” Biomed. Signal Process. Control, vol. 33, pp. 289–305, 2017, doi: https://doi.org/10.1016/j.bspc.2016.11.007.

R. Sameni, M. Samieinasab, “Shiraz university fetal heart sounds database,” PhysioNet, 2021. https://physionet.org/content/sufhsdb/1.0.1/.

Z. Cömert, A. F. Kocamaz, “Comparison of machine learning techniques for fetal heart rate classification,” Acta Phys. Pol. A, vol. 132, no. 3, pp. 451–454, 2017, doi: https://doi.org/10.12693/APhysPolA.132.451.

A. K. Mittra, N. K. Choudhari, “Time-frequency analysis of foetal heart sound signal for the prediction of prenatal anomalies,” J. Med. Eng. Technol., vol. 33, no. 4, pp. 296–302, 2009, doi: https://doi.org/10.1080/03091900802454384.

V. S. Chourasia, A. K. Tiwari, R. Gangopadhyay, “A novel approach for phonocardiographic signals processing to make possible fetal heart rate evaluations,” Digit. Signal Process., vol. 30, pp. 165–183, 2014, doi: https://doi.org/10.1016/j.dsp.2014.03.009.

S. H. Abbas, R. Kolikipogu, V. L. Reddy, J. P. Maroor, D. Kumar, M. Singh, “Deep learning framework for analysis of health factors in Internet-of-Medical Things,” Radioelectron. Commun. Syst., vol. 66, no. 3, pp. 146–154, 2023, doi: https://doi.org/10.3103/S0735272723030056.

V. S. Chourasia, A. K. Tiwari, “Fetal heart rate variability analysis from phonocardiographic recordings,” J. Mech. Med. Biol., vol. 11, no. 05, pp. 1315–1331, 2011, doi: https://doi.org/10.1142/S0219519411004174.

D. Springer, L. Tarassenko, G. Clifford, “Logistic regression-HSMM-based heart sound segmentation,” IEEE Trans. Biomed. Eng., vol. 63, no. 4, pp. 822–832, 2015, doi: https://doi.org/10.1109/TBME.2015.2475278.

S. Zhang, R. Zhang, S. Chang, C. Liu, X. Sha, “A low-noise-level heart sound system based on novel thorax-integration head design and wavelet denoising algorithm,” Micromachines, vol. 10, no. 12, p. 885, 2019, doi: https://doi.org/10.3390/mi10120885.

T. H. Chowdhury, K. N. Poudel, Y. Hu, “Time-frequency analysis, denoising, compression, segmentation, and classification of PCG signals,” IEEE Access, vol. 8, pp. 160882–160890, 2020, doi: https://doi.org/10.1109/ACCESS.2020.3020806.

M. Deng, T. Meng, J. Cao, S. Wang, J. Zhang, H. Fan, “Heart sound classification based on improved MFCC features and convolutional recurrent neural networks,” Neural Networks, vol. 130, pp. 22–32, 2020, doi: https://doi.org/10.1016/j.neunet.2020.06.015.

Ö. Arslan, M. Karhan, “Effect of Hilbert-Huang transform on classification of PCG signals using machine learning,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 10, pp. 9915–9925, 2022, doi: https://doi.org/10.1016/j.jksuci.2021.12.019.

P. Chen, Q. Zhang, “Classification of heart sounds using discrete time-frequency energy feature based on S transform and the wavelet threshold denoising,” Biomed. Signal Process. Control, vol. 57, p. 101684, 2020, doi: https://doi.org/10.1016/j.bspc.2019.101684.

N. K. Sawant, S. Patidar, N. Nesaragi, U. R. Acharya, “Automated detection of abnormal heart sound signals using Fano-factor constrained tunable quality wavelet transform,” Biocybern. Biomed. Eng., vol. 41, no. 1, pp. 111–126, 2021, doi: https://doi.org/10.1016/j.bbe.2020.12.007.

O. Alshamma, F. H. Awad, L. Alzubaidi, M. A. Fadhel, Z. M. Arkah, L. Farhan, “Employment of multi-classifier and multi-domain features for PCG recognition,” in 2019 12th International Conference on Developments in eSystems Engineering (DeSE), 2019, pp. 321–325, doi: https://doi.org/10.1109/DeSE.2019.00066.

I. Vican, “Method for classification of fetal phonocardiography signals using empirical mode decomposition and psychoacoustic parameters,” Zagreb, 2022. uri: https://urn.nsk.hr/urn:nbn:hr:168:532472.

S. Magesh, P. S. Rajakumar, “Ensemble feature extraction-based prediction of fetal arrhythmia using cardiotocographic signals,” Meas. Sensors, vol. 25, p. 100631, 2023, doi: https://doi.org/10.1016/j.measen.2022.100631.

A. Darmawahyuni et al., “Accurate fetal QRS-complex classification from abdominal electrocardiogram using deep learning,” Int. J. Comput. Intell. Syst., vol. 16, no. 1, p. 158, 2023, doi: https://doi.org/10.1007/s44196-023-00339-x.

A. I. Rybin, A. D. Melnyk, Y. K. Nizhebetskaya, I. A. Sushko, S. Litvintsev, “Pattern recognition of 1D and 2D signals using normalization and normal transformation,” Radioelectron. Commun. Syst., vol. 59, no. 1, pp. 28–38, 2016, doi: https://doi.org/10.3103/S0735272716010027.

M. aron Goda, P. Hajas, “Morphological determination of pathological PCG signals by time and frequency domain analysis,” in 2016 Computing in Cardiology Conference (CinC), 2016, doi: https://doi.org/10.22489/CinC.2016.324-249.

Z. Cömert, A. F. Kocamaz, “Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach,” in Advances in Intelligent Systems and Computing, Cham: Springer, 2019, pp. 239–248.

J. Li et al., “Automatic classification of fetal heart rate based on convolutional neural network,” IEEE Internet Things J., vol. 6, no. 2, pp. 1394–1401, 2019, doi: https://doi.org/10.1109/JIOT.2018.2845128.

Z. Zhao, Y. Deng, Y. Zhang, Y. Zhang, X. Zhang, L. Shao, “DeepFHR: intelligent prediction of fetal Acidemia using fetal heart rate signals based on convolutional neural network,” BMC Med. Informatics Decis. Mak., vol. 19, no. 1, p. 286, 2019, doi: https://doi.org/10.1186/s12911-019-1007-5.

M. Liu, Y. Lu, S. Long, J. Bai, W. Lian, “An attention-based CNN-BiLSTM hybrid neural network enhanced with features of discrete wavelet transformation for fetal acidosis classification,” Expert Syst. with Appl., vol. 186, p. 115714, 2021, doi: https://doi.org/10.1016/j.eswa.2021.115714.

S. Li, F. Li, S. Tang, F. Luo, “Heart sounds classification based on feature fusion using lightweight neural networks,” IEEE Trans. Instrum. Meas., vol. 70, pp. 1–9, 2021, doi: https://doi.org/10.1109/TIM.2021.3109389.

Y. Xu, B. Xiao, X. Bi, W. Li, J. Zhang, X. Ma, “Pay more attention with fewer parameters: a novel 1-D convolutional neural network for heart sounds classification,” in 2018 Computing in Cardiology Conference (CinC), 2018, doi: https://doi.org/10.22489/CinC.2018.072.

M. B. Er, “Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features,” Appl. Acoust., vol. 180, p. 108152, 2021, doi: https://doi.org/10.1016/j.apacoust.2021.108152.

R. D. I. Puspitasari, M. A. Ma’sum, M. R. Alhamidi, W. Kurnianingsih Jatmiko, “Generative adversarial networks for unbalanced fetal heart rate signal classification,” ICT Express, vol. 8, no. 2, pp. 239–243, 2022, doi: https://doi.org/10.1016/j.icte.2021.06.007.

A. Bakhshi, A. Harimi, S. Chalup, “CyTex: Transforming speech to textured images for speech emotion recognition,” Speech Commun., vol. 139, pp. 62–75, 2022, doi: https://doi.org/10.1016/j.specom.2022.02.007.

S. Ismail, B. Ismail, I. Siddiqi, U. Akram, “PCG classification through spectrogram using transfer learning,” Biomed. Signal Process. Control, vol. 79, p. 104075, 2023, doi: https://doi.org/10.1016/j.bspc.2022.104075.

R. Khanmohammadi, M. S. Mirshafiee, M. M. Ghassemi, T. Alhanai, “Fetal gender identification using machine and deep learning algorithms on phonocardiogram signals,” arXiv, 2021. https://arxiv.org/abs/2110.06131.

M. G. M. Milani, P. E. Abas, L. C. De Silva, “A critical review of heart sound signal segmentation algorithms,” Smart Heal., vol. 24, p. 100283, 2022, doi: https://doi.org/10.1016/j.smhl.2022.100283.

V. S. Chourasia, A. K. Tiwari, R. Gangopadhyay, “Time-frequency characterization of fetal phonocardiographic signals using wavelet scalogram,” J. Mech. Med. Biol., vol. 11, no. 02, pp. 391–406, 2011, doi: https://doi.org/10.1142/S0219519410003782.

R. Abburi et al., “Adopting artificial intelligence algorithms for remote fetal heart rate monitoring and classification using wearable fetal phonocardiography,” Appl. Soft Comput., vol. 165, p. 112049, 2024, doi: https://doi.org/10.1016/j.asoc.2024.112049.

S. Siami-Namini, N. Tavakoli, A. S. Namin, “The performance of LSTM and BiLSTM in forecasting time series,” in 2019 IEEE International Conference on Big Data (Big Data), 2019, pp. 3285–3292, doi: https://doi.org/10.1109/BigData47090.2019.9005997.

R. Zhao, R. Yan, J. Wang, K. Mao, “Learning to monitor machine health with convolutional bi-directional LSTM networks,” Sensors, vol. 17, no. 2, p. 273, 2017, doi: https://doi.org/10.3390/s17020273.

K. N. Khan et al., “Deep learning based classification of unsegmented phonocardiogram spectrograms leveraging transfer learning,” Physiol. Meas., vol. 42, no. 995003, 2021, doi: https://doi.org/10.1088/1361-6579/ac1d59.

A. Patwa, M. Mahboob Ur Rahman, T. Y. Al-Naffouri, “Heart murmur and abnormal PCG detection via wavelet scattering transform and 1D-CNN,” IEEE Sensors J., vol. 25, no. 7, pp. 12430–12443, 2025, doi: https://doi.org/10.1109/JSEN.2025.3541320.

J. Li, L. Ke, Q. Du, X. Ding, X. Chen, “Research on the classification of ECG and PCG signals based on BiLSTM-GoogLeNet-DS,” Appl. Sci., vol. 12, no. 22, p. 11762, 2022, doi: https://doi.org/10.3390/app122211762.