Models for non-invasive fetal electroencephalogram signal extraction during gestation

Abstract

The functional development of the fetal brain is critical for long-term health, yet current diagnostic tools lack the capability to examine it effectively. This paper presents a non-invasive method for extracting fetal brain signals using abdominal recordings obtained before elective cesarean sections, with neonatal brain activity recorded post-delivery serving as a reference. The recorded abdominal signals were preprocessed using digital filters and separated into independent components using the blind source separation technique: Independent component analysis. These components were analyzed to identify potential fetal brain signals based on their similarity to postnatal brain activity and dissimilarity to maternal cardiac signals, which are the primary source of interference in abdominal recordings. Features related to time and frequency characteristics were extracted, and a feature selection was conducted to identify the most informative ones. Preliminary results using simulated data demonstrated effective signal separation, with some segments closely resembling postnatal brain activity in spectral features. Low-frequency bands showed the strongest potential for distinguishing fetal brain activity from maternal interference. This approach demonstrates a feasible pathway for non-invasive fetal brain monitoring with implications for early detection of neurological development issues.

Keywords

Fetal brain function / Neonatal electroencephalogram / Signal processing / Non-invasive monitoring / Independent component analysis / Frequency-domain analysis / Cesarean section

Funding

This research was supported by the Ministry of Innovation, Science and Technology, Israel (grant number: 0004750).

Conflict of interest

The authors declare no competing interests.

References

[1] Buss C, Entringer S, Swanson JM, Wadhwa PD. The role of stress in brain development: The gestational environment’s long-term effects on the brain. Cerebrum. 2012; 2012:4.

[2] Wu Y, Lu YC, Jacobs M, et al. Association of prenatal maternal psychological distress with fetal brain growth, metabolism, and cortical maturation. JAMA Netw Open. 2020; 3(1):e1919940. doi: 10.1001/jamanetworkopen.2019.19940

[3] Castel A, Frank YS, Feltner J, Karp FB, Albright CM, Frasch MG. Monitoring fetal electroencephalogram intrapartum: A systematic literature review. Front Pediatr. 2020; 8:584. doi: 10.3389/fped.2020.00584

[4] Fitzgerald E, Hor K, Drake AJ. Maternal influences on fetal brain development: The role of nutrition, infection and stress, and the potential for intergenerational consequences. Early Hum Dev. 2020; 150:105190. doi: 10.1016/j.earlhumdev.2020.105190

[5] Paz-Levy D, Schreiber L, Erez O, et al. Inflammatory and vascular placental lesions are associated with neonatal amplitude integrated EEG recording in early premature neonates. PLOS One. 2017; 12(6):e0179481. doi: 10.1371/journal.pone.0179481

[6] Van Den Heuvel MI. From the Womb into the World: Protecting the fetal brain from maternal stress during pregnancy. Policy Insights Behav Brain Sci. 2022; 9(1):96-103. doi: 10.1177/23727322211068024

[7] Lindsley DB. Heart and brain potentials of human fetuses in utero. By Donald B. Lindsley, 1942. Am J Psychol. 1942; 55(3):412-416. doi: 10.2307/1417473

[8] Bernstine RL, Borkowski WJ, Price AH. Prenatal fetal electroencephalography. Am J Obstet Gynecol. 1955;70(3):623-630. doi: 10.1016/0002-9378(55)90357-4

[9] Rosen MG, Scibetta JJ, Hochberg CJ. Human fetal electroencephalogram. 3. Pattern changes in presence of fetal heart rate alterations and after use of maternal medications. Obstet Gynecol. 1970; 36(1):132-140.

[10] Eswaran H, Wilson JD, Lowery CL, et al. Brain stem auditory evoked potentials in the human fetus during labor. Am J Obstet Gynecol. 1999; 180(6):1422-1426. doi: 10.1016/S0002-9378(99)70029-3

[11] Abbasi H, Battin MR, Butler R, et al. Early signatures of brain injury in the preterm neonatal EEG. Signals. 2023; 4(3): 630-643. doi: 10.3390/signals4030034

[12] Nayak CS, Anilkumar AC. Neonatal EEG. In: StatPearls. Tresure Islandm, FL: StatPearls Publishing; 2024.

[13] Hyvärinen A, Oja E. Independent component analysis: Algorithms and applications. Neural Networks. 2000; 13(4-5):411-430. doi: 10.1016/S0893-6080(00)00026-5

[14] García-González MA, Argelagós-Palau A, Fernández- Chimeno M, Ramos-Castro J. A Comparison of Heartbeat Detectors for the Seismocardiogram, Computing in Cardiology 2013. Zaragoza, Spain: IEEE; 2013. p. 461-464.

[15] Study TSHH. Sleep Heart Health Study Polysomnography Database. Oxford: Oxford Acadmic; 2003. doi: 10.13026/C2MK5F

[16] Peterfi I, Kellenyi L, Szilagyi A. Noninvasive recording of true-to-form fetal ECG during the third trimester of pregnancy. Obstet Gynecol Int. 2014; 2014:285636. doi: 10.1155/2014/285636

[17] Butler HL, Newell R, Hubley-Kozey CL, Kozey JW. The interpretation of abdominal wall muscle recruitment strategies change when the electrocardiogram (ECG) is removed from the electromyogram (EMG). J Electromyogr Kinesiol. 2009; 19(2):e102-e113. doi: 10.1016/j.jelekin.2007.10.004

[18] Abdulla W, Wong L. Neonatal EEG signal characteristics using time frequency analysis. Phys A Statis Mech Applic. 2011; 390(6):1096-1110. doi: 10.1016/j.physa.2010.11.013

[19] Rosen MG, Scibetta JJ. The human fetal electroencephalogram. I. An electrode for continuous recording during labor. Am J Obstet Gynecol. 1969;104(7):1057-1060. doi: 10.1016/0002-9378(69)90703-0

[20] Borgstedt AD, Rosen MG, Chik L, Sokol RJ, Bachelder L, Leo P. Fetal electroencephalography. Relationship to neonatal and one-year developmental neurological examinations in high-risk infants. Am J Dis Child. 1975; 129(1):35-38. doi: 10.1001/archpedi.1975.02120380021006

[21] Lundy C, Boylan GB, Mathieson S, Proietti J, O’Toole JM. Quantitative analysis of high-frequency activity in neonatal EEG. Comput Biol Med. 2023; 165:107468. doi: 10.1016/j.compbiomed.2023.107468

[22] Atyabi A, Shic F, Naples A. Mixture of autoregressive modeling orders and its implication on single trial EEG classification. Expert Syst Appl. 2016; 65:164-180. doi: 10.1016/j.eswa.2016.08.044

[23] Boonyakitanont P, Lek-uthai A, Chomtho K, Songsiri J. A review of feature extraction and performance evaluation in epileptic seizure detection using EEG. Biomed Signal Process Control. 2020; 57:101702. doi: 10.1016/j.bspc.2019.101702

[24] Thaler I, Boldes R, Timor-Tritsch I. Real-time spectral analysis of the fetal EEG: A new approach to monitoring sleep states and fetal condition during labor. Pediatr Res. 2000; 48(3):340-345. doi: 10.1203/00006450-200009000-00013

[25] McKnight PE, Najab J. Mann-whitney U test. In: The Corsini Encyclopedia of Psychology. United States: Wiley; 2010. p. 1-1. doi: 10.1002/9780470479216.corpsy0524

[26] Marcano-Cedeño A, Quintanilla-Domínguez J, Cortina- Januchs MG, Andina D. Feature Selection using Sequential Forward Selection and Classification Applying Artificial Metaplasticity Neural Network. In: IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society. United States: IEEE; 2010. p. 2845-2850. doi: 10.1109/IECON.2010.5675075

[27] Kramer O. K-nearest neighbors. In: Kramer O, editor. Dimensionality Reduction with Unsupervised Nearest Neighbors. Berlin: Springer; 2013. p. 13-23. doi: 10.1007/978-3-642-38652-7_2

[28] Poli AA, Cirillo MC. On the use of the normalized mean square error in evaluating dispersion model performance. Atmos Environ Part A Gen Topics. 1993; 27(15):2427-2434. doi: 10.1016/0960-1686(93)90410-Z

[29] Yuan L, Zhou Z, Yuan Y, Wu S. An improved fastICA method for fetal ECG extraction. Comput Math Methods Med. 2018; 2018:7061456. doi: 10.1155/2018/7061456

[30] Taheri N, Kachenoura A, Ansari-Asl K, et al. Feasibility of blind source separation methods for the denoising of dense-array EEG. In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). United States: IEEE; 2015. p. 4773-4776. doi: 10.1109/EMBC.2015.7319461

[31] Haddad N, Govindan RB, Vairavan S, et al. Correlation between fetal brain activity patterns and behavioral states: An exploratory fetal magnetoencephalography study. Exp Neurol. 2011; 228(2):200-205. doi: 10.1016/j.expneurol.2011.01.003

[32] Tierney A, Strait DL, O’Connell S, Kraus N. Developmental changes in resting gamma power from age three to adulthood. Clin Neurophysiol. 2013; 124(5): 1040-1042. doi: 10.1016/j.clinph.2012.09.023

[33] Sokol RJ, Rosen MG. The fetal electroencephalogram. Clin Obstet Gynaecol. 1974; 1(1):123-138. doi: 10.1016/S0306-3356(21)00499-4

[34] Castro Conde JR, González Campo C, González González NL, et al. Assessment of neonatal EEG background and neurodevelopment in full-term small for their gestational age infants. Pediatr Res. 2020; 88(1): 91-99. doi: 10.1038/s41390-019-0693-0

[35] Rooijakkers MJ, Song S, Rabotti C, et al. Influence of electrode placement on signal quality for ambulatory pregnancy monitoring. Comput Math Methods Med. 2014; 2014:960980. doi: 10.1155/2014/960980