Spatial Propagation, Synchronization, and Short Term Labor Imminence from Multichannel Electrohysterography: A Methodological Study on the Icelandic 16 Electrode Physionet Database

Abstract

Electrohysterography (EHG) captures uterine electrical activity noninvasively and can support labor triage. The Icelandic 16‑electrode Electrohysterogram Database (EHGDB) on PhysioNet provides 122 multichannel 4×4 abdominal recordings (200 Hz) from 45 women, including pregnancy clinic visits and recordings during labor. To develop a transparent, reproducible baseline pipeline for distinguishing pregnancy from labor using multichannel EHG. Signals were detrended, band‑pass filtered (0.1–3.0 Hz), and downsampled to 20 Hz. Each recording was segmented into contiguous, non‑overlapping 60‑s windows. For each window we extracted six interpretable features (RMS, variance, approximate entropy, median frequency, magnitude‑squared coherence between channels 1–2, and a conduction‑velocity proxy based on the delay between channels 1–5). A cost‑sensitive Random Forest (200 trees) was evaluated using participant‑grouped 5‑fold cross‑validation; decision thresholds were calibrated per fold to prioritize sensitivity. From 7,153 windows (pregnancy: 6,794; labor: 359), the model achieved AUROC=0.759 and AUPRC=0.319, with recall=60.7% and specificity=79.2% at the calibrated operating point. Fixed‑window, lightweight features provide clinically interpretable performance for pregnancy‑versus‑labor triage on the EHGDB and establish a baseline for future work incorporating contraction‑based segmentation and richer spatial propagation/synchronization measures.

Keywords

• Electrohysterography
• Labor triage
• Conduction velocity
• Coherence
• Approximate entropy
• Random forest

References

1. ACOG Committee. (2017). ACOG Committee Opinion No. 713: Antenatal corticosteroid therapy for fetal maturation. Obstetrics & Gynecology, 130(2), e102–e109. https://doi.org/10.1097/AOG.0000000000002237
2. Alexandersson, Á., Sauermann, S., Gíslason, M. K., & Alexandersson, S. (2015). The Icelandic 16-electrode electrohysterogram database. Scientific Data, 2, 150017.
3. Alexandersson, A., Steingrimsdottir, T., Terrien, J., Marque, C., & Karlsson, B. (2015). Icelandic 16-electrode electrohysterogram database (EHGDB) v1.0.0 [Data set]. PhysioNet. https://physionet.org/content/ehgdb/1.0.0/
4. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
5. Esgalhado, F., Batista, A. G., Vassalo, J., Castelo-Branco, M., & Henriques, J. (2020). Automatic contraction detection using uterine EHG. Applied Sciences, 10(19), 7014.
6. Gao, H., Wen, Z., Jiang, M., Nan, Y., & Wang, Y. (2025). Enhancing uterine contraction detection through novel EHG signal processing: A pilot study leveraging the relationship between slow and fast wave components to improve signal quality and noise resilience. Frontiers in Physiology, 16, 1568919. https://doi.org/10.3389/fphys.2025.1568919
7. Goldsztejn, U., & Nehorai, A. (2023). Predicting preterm births from electrohysterogram recordings via deep learning. PLoS One, 18(5), e0285219.
8. Kang, J.-H., Kim, G.-Y., Lee, S.-H., & Park, J.-W. (2024). Characteristics of phase synchronization in electrohysterography for prediction of preterm birth in threatened preterm labor. Heliyon, 10(22), e40433.

9. Lange, L., Rabotti, C., Beulen, L., Mischi, M., & Lefeber, E. (2014). Velocity and directionality of the electrohysterographic signal propagation. PLoS One, 9(1), e86775.
10. Li, W., Yang, L., Peng, J., Du, M., Song, X., Jiang, H., & Zheng, D. (2025). Synchronization study of electrohysterography for discrimination of imminent delivery in TPL. Computers in Biology and Medicine, 184, 109417.
11. Lucovnik, M., Kuon, R. J., Chambliss, L. R., Balducci, J., Waller, S. S., & Garfield, R. E. (2011). Use of uterine electromyography to diagnose term and preterm labor. American Journal of Obstetrics and Gynecology, 204(6), 386.e1–e9.
12. Mas-Cabo, J., Ye-Lin, Y., Prats-Boluda, G., Garcia-Casado, J., Monfort-Ortiz, R., & Alberola-Rubio, J. (2020). Electrohysterogram for ANN-based prediction of imminent labor in TPL pregnancies. Sensors, 20(9), 2681.
13. Mikkelsen, E., Johansen, P., Fuglsang-Frederiksen, A., & Uldbjerg, N. (2013). Electrohysterography of labor contractions: Propagation velocity and direction. Acta Obstetricia et Gynecologica Scandinavica, 92(9), 1070–1078. https://doi.org/10.1111/aogs.12190
14. Nolte, G., Bai, O., Wheaton, L., Mari, Z., Vorbach, S., & Hallett, M. (2004). Identifying true brain interaction from EEG data using the imaginary part of coherency. Clinical Neurophysiology, 115(10), 2292–2307.
15. Paljk Likar, I., Trojner Bregar, A., Lucovnik, M., & Geršak, K. (2022). Comparison of oxytocin vs. carbetocin uterotonic activity after cesarean section using EHG. Sensors, 22(22), 8994.
16. Peng, J., Hao, D., Yang, L., Du, M., Song, X., Jiang, H., Zhang, Y., & Zheng, D. (2020). Evaluation of electrohysterogram measured from different gestational weeks for recognizing preterm delivery: A preliminary study using random forest. Biocybernetics and Biomedical Engineering, 40(1), 352–362. https://doi.org/10.1016/j.bbe.2019.12.003
17. Prats-Boluda, G., Mas-Cabo, J., Ye-Lin, Y., Monfort-Ortiz, R., Alberola-Rubio, J., & Garcia-Casado, J. (2021). Optimization of imminent labor prediction systems in TPL based on EHG. Sensors, 21(7), 2496.
18. Rabotti, C. (2010). Characterization of uterine activity by electrohysterography (Doctoral dissertation, Eindhoven University of Technology).
19. Rabotti, C., & Mischi, M. (2010). Two-dimensional estimation of the electrohysterographic conduction velocity. Proceedings of the 32nd Annual International Conference of the IEEE EMBS, 2470–2473.
20. Song, X., Yang, L., Peng, J., Du, M., Jiang, H., & Zheng, D. (2021). Automatic recognition of uterine contractions with EHG signals based on the zero-crossing rate. Scientific Reports, 11(1), 1956. https://doi.org/10.1038/s41598-021-81589-3
21. Vandewiele, G., Dehaene, I., Kovács, G., Sterckx, L., Ongenae, F., Femont, D., Coorevits, P., Weyers, S., De Backer, G., Decruyenaere, J., Zuallaert, J., Fostier, J., & Segers, C. (2021). Overly optimistic prediction results on imbalanced data: A case study of preterm birth forecasting. Artificial Intelligence in Medicine, 111, 101987.
22. Vasist, S. N., Prats-Boluda, G., Ye-Lin, Y., Garcia-Casado, J., Monfort-Ortiz, R., & Alberola-Rubio, J. (2022). Identification of contractions from EHG for labor evaluation. Sensors, 22(6), 2070.
23. Vinck, M., Oostenveld, R., van Wingerden, M., Battaglia, F., & Pennartz, C. M. (2011). An improved index of phase-synchronization for electrophysiological data in the presence of volume-conduction, noise and sample-size bias. NeuroImage, 55(4), 1548–1565.
24. Vinken, M. P. G. C., Rabotti, C., Mischi, M., & Oei, S. G. (2009). Accuracy of frequency-related parameters of the electrohysterogram for predicting preterm delivery: A review. Obstetricial & Gynecological Survey, 64(8), 529–541.
25. Ye, Y., Alberola-Rubio, J., Garcia-Casado, J., Prats-Boluda, G., & Monfort-Ortiz, R. (2015). Effects of patient-controlled epidural analgesia on uterine EMG during labor. Clinical and Investigative Medicine, 38(2), E71–E83.