Current perspectives on the use of artificial intelligence in the interpretation of intrapartum cardiotocography: A literature review
DOI:
https://doi.org/10.37800/RM.3.2026.796Keywords:
artificial intelligence, intranatal fetal monitoring, cardiotocography, fetal distress, machine learningAbstract
Relevance: Cardiotocography (CTG) remains a primary tool for intrapartum monitoring, but its clinical value is diminished by high subjectivity in interpretation, low specificity, and a lack of strict criteria for pathological patterns. Consequently, obstetric practice has seen an increase in unjustified operative interventions, not accompanied by a true reduction in adverse neonatal outcomes. Today, implementing artificial intelligence (AI) algorithms is considered one of the most promising avenues to improve the accuracy and objectivity of CTG analysis.
The study aimed to systematize current scientific evidence on the limitations of traditional visual assessment of intrapartum cardiotocography, explore modern neural network approaches to its interpretation, and identify the most informative markers of fetal response to labor stress.
Materials and Methods: We conducted an analytical review of scientific articles published from January 1, 2016, to April 15, 2026, in the Scopus, Web of Science, PubMed, and CyberLeninka databases using the keywords: Artificial Intelligence, Intrapartum Fetal Monitoring, Cardiotocography, Fetal Distress, and Machine Learning.
Results: Multi-layered neural networks, including hybrid models and attention-based architectures, can identify hidden nonlinear relationships between uterine contractions and fetal heart rate. Retrospective studies show that the area under the ROC curve (AUC) for such systems can reach 0.90. At the same time, AI effectiveness in practice remains unstable because of heterogeneous clinical data, the predominance of normal birth outcomes in training samples, and a shortage of large-scale labeled databases. Currently, the most promising avenue of development is shifting away from detecting established hypoxia toward predictive models that assess deviations in fetal parameters from the physiological norm. The findings emphasize the importance of a multimodal approach (integrating medical history and clinical data) and creating algorithms that are “transparent” to the doctor.
Conclusion: Deep machine learning has strong potential to analyze nonlinear CTG patterns and confidently rule out fetal distress. However, implementation of such systems in maternity hospitals has so far been hindered by low-quality training samples, class imbalance, heterogeneity of clinical endpoints, and errors in the research architecture. At this stage of technology development, AI should be considered an intelligent decision support system rather than a substitute for a doctor’s clinical thinking.
References
1. Lovers A, Daumer M, Frasch MG, Ugwumadu A, Warrick P, Vullings R, Pini N, Tolladay J, Petersen OB, Lederer C, Yang L, Djurić PM, Abtahi F, Holzmann M, Boudet S, de l'Aulnoit AH, Georgieva A. Advancements in Fetal Heart Rate Monitoring: A Report on Opportunities and Strategic Initiatives for Better Intrapartum Care. BJOG: Int J Obst Gynaecol. 2025;132(7):853-866.
https://doi.org/10.1111/1471-0528.18097
2. Ogasawara J, Ikenoue S, Yamamoto H, Sato M, Kasuga Y, Mitsukura Y, Ikegaya Y, Yasui M, Tanaka M, Ochiai D. Deep neural network-based classification of cardiotocograms outperformed conventional algorithms. Sci Rep. 2021 Jun 28;11(1):13367.
https://doi.org/10.1038/s41598-021-92805-9
3. Romano M, Iuppariello L, Ponsiglione AM, Improta G, Bifulco P, Cesarelli M. Frequency and Time Domain Analysis of Foetal Heart Rate Variability with Traditional Indexes: A Critical Survey. Computat Math Methods Med. 2016;2016:9585431.
https://doi.org/10.1155/2016/9585431
4. Zhao Z, Zhang Y, Comert Z, Deng Y. Computer-Aided Diagnosis System of Fetal Hypoxia Incorporating Recurrence Plot With Convolutional Neural Network. Front Physiol. 2019;10:255.
https://doi.org/10.3389/fphys.2019.00255
5. Schäffler H, Dimpfl M, Hüner B, Janni W, Reister F, Andres S. Training and Subjective Confidence in CTG Interpretation in Germany: A National Cross-Sectional Survey. J Multidiscipl Healthcare. 2026;19:586934.
https://doi.org/10.2147/JMDH.S586934
6. Vilimkova Kahankova R, Barnova K, Gorjani OM, Horakova J, Bilik P, Vilimek D. Machine learning based classification in obstetrics: evaluating models, partitioning strategies, and key predictors in cardiotocography. BMC Pregn Childbirth. 2026;26(1):632.
https://doi.org/10.1186/s12884-026-09130-0
7. Georgieva A, Abry P, Chudáček V, Djurić PM, Frasch MG, Kok R, Lear CA, Lemmens SN, Nunes I, Papageorghiou AT, Quirk GJ, Redman CWG, Schifrin B, Spilka J, Ugwumadu A, Vullings R. Computer-based intrapartum fetal monitoring and beyond: A review of the 2nd Workshop on Signal Processing and Monitoring in Labor (October 2017, Oxford, UK). Acta Obstet Gynecol Scand. 2019;98(9):1207-1217.
https://doi.org/10.1111/aogs.13639
8. Leoni RS, Tomich MF, Meireles PT, Petrini CG, Araujo Júnior E, Peixoto AB. Accuracy of intrapartum cardiotocography in identifying acidemia at birth by umbilical cord blood gasometry in high-risk pregnancies. Rev Assoc Méd Brasil. 2023;69(11):e20230511. https://doi.org/10.1590/1806-9282.20230511
9. McCoy JA, Levine LD, Wan G, Chivers C, Teel J, La Cava WG. Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning. Am J Obstet Gynecol. 2025 Jan;232(1):116.e1-116.e9. doi: 10.1016/j.ajog.2024.04.022. Epub 2024 Apr 24. Erratum in: Am J Obstet Gynecol. 2026 Sep;235(3):725.
https://doi.org/10.1016/j.ajog.2026.04.019
10. Quirke F, Biesty L, Battin M, Bloomfield FH, Daly M, Finucane E, Healy P, Hurley T, Kirkham JJ, Molloy E, Haas DM, Meher S, Ní Bhraonáin E, Walker K, Webbe J, Devane D. Neonatal encephalopathy: a systematic review of reported treatment outcomes. BMJ Paediatr Open. 2024;8(1):e002510.
https://doi.org/10.1136/bmjpo-2024-002510
11. Danciu BM, Șișială ME, Dumitru AI, Simionescu AA, Sebacher B. Prediction of Neonatal Length of Stay in High-Risk Pregnancies Using Regression-Based Machine Learning on Computerized Cardiotocography Data. Diagnostics. 2025;15(23):2964.
https://doi.org/10.3390/diagnostics15232964
12. Paikaray S, Jena SK, Balakrishnan D, Mohanty PK. Correlation of cardiotocography with combined APGAR scores and diagnostic performance of umbilical cord parameters in predicting low combined APGAR scores - A prospective Cohort study. Eur J Obstet Gynecol Reprod Biol: X. 2024;23:100329.
https://doi.org/10.1016/j.eurox.2024.100329
13. Kanagal DV, Praveen BK. Intrapartum Fetal Monitoring and Its Correlation with Umbilical Cord Blood pH and Early Neonatal Outcome: A Prospective Cohort Study. J South Asian Fed Obstet Gynaecol. 2022;14(1):63-67.
https://doi.org/10.5005/jp-journals-10006-2007
14. Nazir L, Lakhta G, Anees K, Khan FR, Safdar S, Nazir GR, Irum MI, Khattak SU, Salim A. Admission Cardiotocography as a Predictor of Low Apgar Score: An Observational, Cross-Sectional Study. Cureus. 2021;13(4):e14530.
https://doi.org/10.7759/cureus.14530
15. Wood CE, Keller-Wood M. Current paradigms and new perspectives on fetal hypoxia: implications for fetal brain development in late gestation. Am J Physiol Regulat Integrat Comparat Physiol. 2019;317(1):R1-R13.
https://doi.org/10.1152/ajpregu.00008.2019
16. Alfirevic Z, Devane D, Gyte GML, Cuthbert A. Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour. Cochrane Database Syst Rev. 2017;2:CD006066.
https://doi.org/10.1002/14651858.CD006066.pub3
17. Balayla J, Shrem G. Use of artificial intelligence (AI) in the interpretation of intrapartum fetal heart rate (FHR) tracings: a systematic review and meta-analysis. Arch Gynecol Obstet. 2019;300(1):7-14.
https://doi.org/10.1007/s00404-019-05151-7
18. Franco LC, Buitrago SM, Arbelaez I, Pinto LF, Blanco D, Pizarro MC, Santamaria L, Trillos C. Development, Validation, and Diagnostic Accuracy of the Fetal Lack of Responsiveness Scale for Diagnosis of Severe Perinatal Hypoxia. J Pregn. 2024;2024:9779831.
https://doi.org/10.1155/2024/9779831
19. Ugwumadu A, Arulkumaran S. A Second Look at Intrapartum Fetal Surveillance and Future Directions. J Perinatal Med. 2023;51(1):135-144.
https://doi.org/10.1515/jpm-2022-0292
20. National Institute for Health and Care Excellence. Intrapartum care for healthy women and babies: clinical guideline CG190 [Internet]. London: NICE; 2014 [cited 2026 Sep 17]. Available from:
https://www.nice.org.uk/guid/cg190
21. Bullens LM, Hulsenboom AD, Moors S, Joshi R, van Runnard Heimel PJ, van der Hout-van der Jagt MB, van den Heuvel ER, Oei SG. Intrauterine resuscitation during the second stage of term labour by maternal hyperoxygenation versus conventional care: study protocol for a randomised controlled trial (INTEREST O2). Trials. 2018;19(1):195.
https://doi.org/10.1186/s13063-018-2567-x
22. Ekengård F, Cardell M, Herbst A. Low sensitivity of the new FIGO classification system for electronic fetal monitoring to identify fetal acidosis in the second stage of labor. Eur J Obstet Gynecol Reprod Biol: X. 2021;9:100120.
https://doi.org/10.1016/j.eurox.2020.100120
23. Spairani E, Steyde G, Podda F, Signorini MG, Magenes G. A multidimensional ensemble pipeline for early detection of IUGR condition through CTG. Front Digit Health. 2026;15;8:1837088.
https://doi.org/10.3389/fdgth.2026.1837088
24. Tolladay J, Albert B, Jones GD. Predicting Fetal Outcomes from Cardiotocography Signals Using a Supervised Variational Autoencoder. arXiv.org. 2025.
https://doi.org/10.48550/arXiv.2509.06540
25. Lu, Y.; Liang, Y.; Bai, J.; Yang, Z. MIRF-Net: A Multimodal Data Fusion Framework for Intrapartum Fetal Risk Assessment. Bioengineering. 2026;13(4):385.
https://doi.org/10.3390/bioengineering13040385
26. Campos I, Gonçalves H, Bernardes J, Castro L. Fetal Heart Rate Preprocessing Techniques: A Scoping Review. Bioengineering. 2024;11(4):368.
https://doi.org/10.3390/bioengineering11040368
27. Sarkar P, Lobmaier S, Fabre B, González D, Mueller A, Frasch MG, Antonelli MC, Etemad A. Detection of maternal and fetal stress from the electrocardiogram with self-supervised representation learning. Sci Rep. 2021 Dec 17;11(1):24146.
https://doi.org/10.1038/s41598-021-03376-8.
28. Cömert Z, Şengür A, Budak Ü, Kocamaz AF. Prediction of intrapartum fetal hypoxia considering feature selection algorithms and machine learning models. Health Info Sci Syst. 2019;7:17.
https://doi.org/10.1007/s13755-019-0079-z
29. M’Barek IB, Jauvion G, Vitrou J, Holmström E, Koskas M, Ceccaldi PF. DeepCTG® 1.0: an interpretable model to detect fetal hypoxia from cardiotocography data during labor and delivery. Front Pediatr. 2023;11:1190441.
https://doi.org/10.3389/fped.2023.1190441
30. Georgieva A, Redman CWG, Papageorghiou AT. Computerized data-driven interpretation of the intrapartum cardiotocogram: a cohort study. Acta Obstet Gynecol Scand. 2017;96(11):1368-1376.
https://doi.org/10.1111/aogs.13217
31. Francis F, Luz S, Wu H, Stock SJ, Townsend R. Machine learning on cardiotocography data to classify fetal outcomes: A scoping review. Comput Biol Med. 2024;172:108220.
https://doi.org/10.1016/j.compbiomed.2024.108220
32. Aeberhard JL, Radan AP, Delgado-Gonzalo R, Strahm KM, Sigurthorsdottir HB, Schneider S, Surbek D. Artificial intelligence and machine learning in cardiotocography: a scoping review. Eur J Obst Gynecol Reprod Biol. 2023;281:54-62.
https://doi.org/10.1016/j.ejogrb.2022.12.008
33. Aeberhard JL, Radan AP, Soltani RA, Strahm KM, Schneider S, Carrié A, Lemay M, Krauss J, Delgado-Gonzalo R, Surbek D. Introducing artificial intelligence in interpretation of foetal cardiotocography: medical dataset curation and preliminary coding—an interdisciplinary project. Methods Protocols. 2024;7(1):5.
https://doi.org/10.3390/mps7010005
34. Lopes-Pereira J, Costa A, Ayres-de-Campos D, Costa-Santos C, Amaral J, Bernardes J. Computerized analysis of cardiotocograms and ST signals is associated with significant reductions in hypoxic-ischemic encephalopathy and cesarean delivery: An observational study in 38,466 deliveries. Am J Obstet Gynecol. 2019;220(3):269.e1-269.e8.
https://doi.org/10.1016/j.ajog.2018.12.037
35. Park CE, Choi B, Park RW, Kwak DW, Ko HS, Seong WJ, Cha HH, Kim HM, Lee J, Seol HJ, Pyeon S, Hong SC, Kang YD, Oh KJ, Park JS, Kim YN, Kim YA, Kim YH, Kim GJ, Kim M, Chang HJ. Automated interpretation of cardiotocography using deep learning in a nationwide multicenter study. Sci Rep. 2025;15:19617.
https://doi.org/10.1038/s41598-025-02849-4
36. Zhou X, Qiu T, Lin C, Zhou J, Jiang S, Wang L, Feng L, Wang X, You Q. Objective interpretation of intrapartum cardiotocography images using attention-guided convolutional neural networks. Front Pediatr. 2026;14:1717012.
https://doi.org/10.3389/fped.2026.1717012
37. Wong S, Albert B, Jones GD. CleanCTG: A Deep Learning Model for Multi-Artefact Detection and Reconstruction in Cardiotocography. arXiv.org. 2025.
https://doi.org/10.48550/arXiv.2508.10928
38. Fridman N, Shachar BB. A Foundation Model Approach for Fetal Stress Prediction During Labor From cardiotocography (CTG) recordings. arXiv.org. 2026.
https://doi.org/10.48550/arXiv.2601.06149
39. Nazli I, Korbeko E, Dogru S, Kugu E, Sahingoz OK. Early Detection of Fetal Health Conditions Using Machine Learning for Classifying Imbalanced Cardiotocographic Data. Diagnostics. 2025;15(10):1250.
https://doi.org/10.3390/diagnostics15101250
40. Oyarzún L, Castillo E, Parrilla L, Meyer-Baese U, García A. PCA-Based Preprocessing for Clustering-Based Fetal Heart Rate Extraction in Non-Invasive Fetal Electrocardiograms. Electronics. 2024;13(7):1264.
https://doi.org/10.3390/electronics13071264
41. Wong S, Shankar R, Albert B, Fei H, Li L, M'Barek IB, Vatish M, Jones GD. PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL. arXiv.org. 2026.
https://doi.org/10.48550/arXiv.2605.02917
42. Melaet R, de Vries IR, Kok RD, Oei SG, Huijben IAM, van Sloun RJG, van Laar JOEH, Vullings R. Artificial intelligence based cardiotocogram assessment during labor. Eur J Obstet Gynecol Reprod Biol. 2024;295:75-85.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 С.С. Искалиева, Б.М. Айтбаева, И.Е. Ли
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The articles published in this Journal are licensed under the CC BY-NC-ND 4.0 (Creative Commons Attribution – Non-Commercial – No Derivatives 4.0 International) license, which provides for their non-commercial use only. Under this license, users have the right to copy and distribute the material in copyright but are not permitted to modify or use it for commercial purposes. Full details on the licensing are available at https://creativecommons.org/licenses/by-nc-nd/4.0/.
