2658-6533Research Results in Biomedicine2658-653310.18413/2658-6533-2026-12-1-0-84041Medicine (miscellaneous)<strong>Artificial intelligence models in cardiotocography (review)</strong><strong>Artificial intelligence models in cardiotocography (review)</strong>KonoplevaVioleta V.KonoplevaVioleta V.sokol.vita2010@yandex.ruShamarinStanislav V.ShamarinStanislav V.shamarin-med@yandex.ru202612100

Background: Fetal hypoxia is a pathological state characterized by insufficient oxygen supply to the human fetal tissue. Oxygen deficiency causes a cascade of pathological complications, including decompensation, metabolic acidosis, and, in some cases, fetal death. Cardiotocography (fetal monitoring) is an instrumental method used to assess fetal well-being and screening for fetal distress. Over the past few years, numerous publications on artificial intelligence (AI) in fetal monitoring have appeared. The aim of the study: To evaluate the role of artificial intelligence in fetal monitoring or cardiotocography (CTG) and screening for hypoxia or fetal distress. Materials and methods: A literature review was conducted on the use of artificial intelligence for diagnosing foetal hypoxia or distress during pregnancy and childbirth. Sources from the PubMed, eLIBRARY and Scopus databases published over the past 35 years were used. Results: Analysis of literature data has revealed improvements in the screening of fetal hypoxia using artificial intelligence models in cardiotocography. Machine learning had high diagnostic accuracy compared to traditional methods, ranging from 96.8% to 98.0% and from 80.0% to 84.4%, respectively. Conclusion: Artificial intelligence in cardiotocography improves the screening of fetal hypoxia in the antenatal period and labor. Diagnostic accuracy of artificial intelligence in cardiotocography in screening for hypoxia or fetal distress can exceed 96.0%. Modern diagnostic models based on artificial intelligence in CTG can serve as a virtual digital assistant for obstetricians in making medical decisions.

Background: Fetal hypoxia is a pathological state characterized by insufficient oxygen supply to the human fetal tissue. Oxygen deficiency causes a cascade of pathological complications, including decompensation, metabolic acidosis, and, in some cases, fetal death. Cardiotocography (fetal monitoring) is an instrumental method used to assess fetal well-being and screening for fetal distress. Over the past few years, numerous publications on artificial intelligence (AI) in fetal monitoring have appeared. The aim of the study: To evaluate the role of artificial intelligence in fetal monitoring or cardiotocography (CTG) and screening for hypoxia or fetal distress. Materials and methods: A literature review was conducted on the use of artificial intelligence for diagnosing foetal hypoxia or distress during pregnancy and childbirth. Sources from the PubMed, eLIBRARY and Scopus databases published over the past 35 years were used. Results: Analysis of literature data has revealed improvements in the screening of fetal hypoxia using artificial intelligence models in cardiotocography. Machine learning had high diagnostic accuracy compared to traditional methods, ranging from 96.8% to 98.0% and from 80.0% to 84.4%, respectively. Conclusion: Artificial intelligence in cardiotocography improves the screening of fetal hypoxia in the antenatal period and labor. Diagnostic accuracy of artificial intelligence in cardiotocography in screening for hypoxia or fetal distress can exceed 96.0%. Modern diagnostic models based on artificial intelligence in CTG can serve as a virtual digital assistant for obstetricians in making medical decisions.

fetal distresscardiotocographyfetal electrocardiographyfetal distresscardiotocographyfetal electrocardiographyСписок литературыRussian Society of Obstetricians and Gynaecologists.. Clinical guidelines: Signs of fetal intrauterine hypoxia requiring maternal medical care [Internet]. 2023 [cited 2025 May 20]. Russian. Available from: https://sudact.ru/law/klinicheskie-rekomendatsii-priznaki-vnutriutrobnoi-gipoksii-ploda-trebuiushchie/klinicheskie-rekomendatsii/Norman M. Identifying the true scale of perinatal deaths. Acta Paediatrica. 2017;106(9):1376-1377. DOI: https://doi.org/10.1111/apa.13933Hodgins S. Pre-eclampsia as Underlying Cause for Perinatal Deaths: Time for Action. Global Health: Science and Practice. 2015;17;3(4):525-527. DOI: https://doi.org/10.9745/GHSP-D-15-00350R&ecirc;go MGS, Vilela MBR, Oliveira CM, et al. Perinatal deaths preventable by intervention of the Unified Health System of Brazil. Revista Ga&uacute;chade Enfermagem. 2018;39:e20170084. DOI: https://doi.org/10.1590/1983-1447.2018.2017-0084Helps &Auml;, Leitao S, Greene R, et al. Perinatal mortality audits and reviews: Past, present and the way forward. European Journal of Obstetrics and Gynecology and Reproductive Biology. 2020;250:24-30. DOI: https://doi.org/10.1016/J.EJOGRB.2020.04.054Helps &Auml;, Leitao S, Gutman A, et al. National perinatal mortality audits and resultant initiatives in four countries. European Journal of Obstetrics and Gynecology and Reproductive Biology. 2021;267:111-119. DOI: https://doi.org/10.1016/j.ejogrb.2021.10.012Prikhodko AM, Romanov AYu, Tysyachnyy OV, et al. Modern principles of cardiotocography in childbirth. Meditsinskiy sovet = Medical Council. 2020;3:90-97. Russian. DOI: https://doi.org/10.21518/2079-701X-2020-3-90-97Tharmaratnam S. Fetal distress. Best Practice and Research in Clinical Obstetrics and Gynaecology. 2000;14(1):155-172. DOI: https://doi.org/10.1053/beog.1999.0069Gilstrap LC. A Guest Editorial: Distress over fetal distress. Obstetrical and Gynecological Survey. 1996;51(3):143-144. DOI: https://doi.org/10.1097/00006254-199603000-00001Penning S, Garite TJ. Management of fetal distress. Obstetrics and Gynecology Clinics of North America. 1999;26(2):259-274. DOI: https://doi.org/10.1016/s0889-8545(05)70073-5Baev OR, Prikhodko AM, Ziganshina MM, et al. Antenatal and intrapartum risk factors associated with fetal hypoxia in labor. Obstetrics and Gynecology. 2022;8:47-53. Russian. DOI: https://dx.doi.org/10.18565/aig.2022.8.47-53Loginov VV, Davydov DG, Prikhod&#39;ko AM, et al. Fetal adaptation to cardiotocography as a criterion of fetal condition. Obstetrics and Gynecology. 2021;3:138-144. Russian. DOI: https://dx.doi.org/10.18565/aig.2021.3.138-144Paladugu V, Sreedhar S, Chitra R, et al. Association of CTG Diagnosis of Intrapartum Fetal Distress and Immediate Postpartum Acidemia in Foetal Umbilical Artery. Journal of Obstetrics and Gynecology of India. 2023;73(1):28-35. DOI: https://doi.org/10.1007/s13224-022-01702-2Schifrin BS. CTG and the timing and mechanism of fetal neurological injuries. Best Practice and Research: Clinical Obstetrics and Gynaecology. 2004;18(3):437-456. DOI: https://doi.org/10.1016/j.bpobgyn.2004.03.001Kapila R, Saleti S. Optimizing fetal health prediction: Ensemble modeling with fusion of feature selection and extraction techniques for cardiotocography data. Computational Biology and Chemistry. 2023;107:107973. DOI: https://doi.org/10.1016/j.compbiolchem.2023.107973Shamarin SV, Enkova ЕV, Ippolitova LI, et al. Doppler fetal monitoring and noninvasive fetal ECG in modern obstetrics (review). Research Results in Biomedicine. 2023;9(2):234-253. Russian. DOI: https://doi.org/10.18413/2658-6533-2023-9-2-0-7Shamarin SV. FIGO CTG interpretation for Russian EFM experts. Sistemnyj analiz i upravlenie v biomedicinskih sistemah. 2016;15(4):723-733. Russian.Shamarin SV. International CTG standards. Sistemnyj analiz i upravlenie v biomedicinskih sistemah. 2010;9(2):357-365. Russian.Shamarin SV. The use of electronic fetal monitoring in Russia. System analysis and management in biomedical systems. 2015;14(3):510-515. Russian.Cagninelli G, Dall&#39;asta A, DI Pasquo E, et al. STAN: a reappraisal of its clinical usefulness. Minerva Obstetrics and Gynecology. 2021;73(1):34-44. DOI: https://doi.org/10.23736/s2724-606x.20.04690-0Eremina OV, Bayev OR, Prikhodko AM, et al. Cardiotocography used in combination with automatic ST segment analysis of the electrocardiogram of a fetus for its status monitoring during labor and delivery. Obstetrics and Gynecology. 2014;11:49-56. Russian.&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Blencowe H, Hug L, Moller AB, et al. Definitions, terminology and standards for reporting of births and deaths in the perinatal period: International Classification of Diseases (ICD-11). International Journal of Gynecology and Obstetrics. 2025;168(1):1-9. DOI: https://doi.org/10.1002/ijgo.15794Gutman A, Harty T, O&#39;Donoghue K, et al. Perinatal mortality audits and reporting of perinatal deaths: systematic review of outcomes and barriers. Journal of Perinatal Medicine. 2022;50(6):684-712. DOI: https://doi.org/10.1515/jmp-2021-0363Savelyeva GM, Sukhikh GT, Serov VN, et al. editors. Obstetrics: National Guide. 2nd edition, revised and supplemented. GEOTAR-Media; 2022. Russian.Demidov VN, Logvinenko VA, Bychkov PA, et al. Experience in the complex evaluation of fetal condition during pregnancy. Obstetrics and Gynecology. 1991;8:6-8. Russian.&nbsp;&nbsp;&nbsp;&nbsp;Demidov VN, Ogai OYu, Sigizbayeva IN. Assessment of the informative value of automated antenatal cardiotocography. Obstetrics and Gynecology. 2008;6:33-39. Russian.&nbsp;Aye CYL, Redman CWG, Georgieva A. The effect of augmentation of labour with syntocinon on the fetal CTG using objective computerised analysis: a nested case-control study. European Journal of Obstetrics, Gynecology, and Reproductive Biology. 2014;176:112-118. DOI: https://doi.org/10.1016/j.ejogrb.2014.02.032Frizina AV, Zamaleeva RS, Cherepanova NA. The use of antenatal cardiotocography for the diagnosis of fetal hypoxia (literature review). Practical Medicine. 2018;16(6):56-60. Russian. DOI: https://doi.org/10.32000/2072-1757-2018-16-6-56-60Redman CWG. Improving assessment of fetal health [Internet]. The clinical services journal &ldquo;Huntleigh Diagnostics Ltd&rdquo;. 2013 [cited 2024 Dec 20];1-4. Available from: https://www.clinicalservicesjournal.com/story/12094/improving-assessment-of-fetal-healthDawes GS, Moulden M, et al. Computerized analysis of antepartum fetal heart rate. American Journal of Obstetrics and Gynecology. 1995;173(4):1353-1354. DOI: https://doi.org/10.1016/0002-9378(95)91391-2Dawes GS, Moulden M, Redman CWG. Short&ndash;Term Fetal Heart Rate Variation, Decelerations, and Umbilical Flow Velocity Waveforms Before Labor. Obstetrics and&nbsp;Gynecology. 1992;80(4):673-678.Savir&oacute;n-Cornudella R, Bielsa AL, Esteban-Escano J, et al. Diagnosis of cardiotocographic sinusoidal patterns by spectral analyses. Biomedical Signal Processing and Control. 2024;93:106174. DOI: https://doi.org/10.1016/j.bspc.2024.106174Steyde G, Spairani E, Magenes G, et al. Fetal heart rate spectral analysis in raw signals and PRSA-derived curve: normal and pathological fetuses discrimination. Medical and Biological Engineering and Computing. 2024;62(2):437-447. DOI: https://doi.org/10.1007/s11517-023-02953-5Matytsina NP, Kudlai VS. Main directions of artificial intelligence development in various spheres of activity of the Russian Federation. Symbol of Science. 2024;12-1-1:99-101. Russian.Ivshin AA, Gusev AV, Novitskiy RE. Artificial intelligence: predictive analytics of perinatal risks. Gynecology, Obstetrics and Perinatology. 2020;19(6):133-144. Russian. DOI: &nbsp;https://doi.org/10.20953/1726-1678-2020-6-133-144Chen Z. Prediction of vasculitic neuropathy using supervised machine learning approaches. Informatics. Economics. Management. 2024;3(1):301-310. Russian. DOI: https://doi.org/10.47813/2782-5280-2024-3-1-0301-0310Podzorova MI, Ptitsyna IV, Bakhtiyarova HE. Neural network as one of the promising directions of artificial intelligence. Modern European Researches. 2022;3(1):169-176. Russian.Mokshanov MV. The use of artificial intelligence in data analysis: an overview of the current state and future directions. Universum: technical sciences. 2024;122(5):40-48. Russian. DOI: https://doi.org/10.32743/UniTech.2024.122.5.17513Chen C, Xie W, Cai Z, et al. Deep Learning for Cardiotocography Analysis: Challenges and Promising Advances. In: Huang DS, Premaratne P, Jin B, et al. editors. Advanced Intelligent Computing Technology and Applications. ICIC 2023. Lecture Notes in Computer Science, vol 14087. Springer, Singapore; 2023. DOI: https://doi.org/10.1007/978-981-99-4742-3_29Kadarina TМ, Basari, Gunawan D. ML-Based Interpretation of Cardiotocography Data: Current State and Future Research. In: The Role of Artificial Intelligence Technology in Human and Computer Interactions in the Industrial Era 5.0. Proceedings of the 7th IEEE International Conference of Computer Science and Information Technology, ICOSNIKOM 2023 Nov 10-11. Indonesia: Hybrid, Binjia; 2023. DOI: &nbsp;https://doi.org/10.1109/ICoSNIKOM60230.2023.10364517M&rsquo;Barek IB, Jauvion G, Ceccaldi PF. Computerized cardiotocography analysis during labor - A state-of-the-art review. Acta Obstetricia et Gynecologica Scandinavica. 2023;102(2):130-137. DOI: &nbsp;https://doi.org/10.1111/aogs.14498Melaet R, de Vries IR, Kok RD, et al. Artificial intelligence based cardiotocogram assessment during labor. European Journal of Obstetrics, Gynecology, and Reproductive Biology. 2024;295:75-85. DOI: &nbsp;https://doi.org/10.1016/j.ejogrb.2024.02.007Dlugatch R, Georgieva A, Kerasidou A. AI-driven decision support systems and epistemic reliance: a qualitative study on obstetricians&rsquo; and midwives&rsquo; perspectives on integrating AI-driven CTG into clinical decision making. BMC Medical Ethics. 2024;25:6. DOI: &nbsp;https://doi.org/10.1186/s12910-023-00990-1O&#39;Sullivan ME, Considine EC, O&#39;Riordan M, et al. Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring. Frontiers in Artificial Intelligence. 2021;4:765210. DOI: https://doi.org/10.3389/frai.2021.765210Spairani E, Steyde G, Tagliaferri S, et al. Fetal states identification in cardiotocographic tracings through discrete emissions multivariate hidden Markov models. Computer Methods and Programs in Biomedicine. 2023;240:107736. DOI: https://doi.org/10.1016/j.cmpb.2023.107736Georgieva A, Abry P, Nunes I, et al. Editorial: Fetal-maternal monitoring in the age of artificial intelligence andcomputer-aided decision support: A multidisciplinary perspective. Frontiers in Pediatrics. 2022;10:1007799. DOI: https://doi.org/10.3389/fped.2022.1007799Zeng R, Lu Y, Long S, et al. Cardiotocography signal abnormality classification using time-frequency features and Ensemble Cost-sensitive SVM classifier. Computers in Biology and Medicine. 2021;130:104218. DOI: https://doi.org/10.1016/j.compbiomed.2021.104218Hirono Y, Kai C, Yoshida A, et al. Extracting fetalheart signals from Doppler using semi-supervised convolutional neural networks. Frontiers in Physiology. 2024;15:1293328. DOI: &nbsp;https://doi.org/10.3389/fphys.2024.1293328Gude V, Corns S. Integrated Deep Learning and Supervised Machine Learning Model for Predictive Fetal Monitoring. MDPI journal. Diagnostics. 2022;12(11):2843. DOI: &nbsp;https://doi.org/10.3390/diagnostics12112843Fei Y, Chen Q, Huang X, et al. Automatic Classification of Antepartum Cardiotocography Using Fuzzy Clustering and Adaptive Neuro -Fuzzy Inference System. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Seoul, Korea (South); 2020. DOI: https://doi.org/10.1109/BIBM49941.2020.9313143Spairani E, Daniele B, Signorini MG, et al. A deep learningmixed-data type approach for the classification of FHR signals. Frontiers in Bioengineering and Biotechnology. 2022;10:887549. DOI: &nbsp;https://doi.org/10.3389/fbioe.2022.887549Liang H, Lu Y, Liu Q, et al. Fully Automatic Classification of Cardiotocographic Signals with 1D-CNN and Bi-directional GRU. In: IEEE Engineering in Medicine and Biology Society. Proceedings of the 44th Annual International Conference of the IEEE Engineering in Medicine &amp; Biology Society (EMBC); 2022 July 11-15; Glasgow, Scotland, United Kingdom; 2022. DOI: https://doi.org/10.1109/EMBC48229.2022.9871253Aswathi Mohan PP, Uma V. Fetal Hypoxia Detection using CTG Signals and CNN Models. International Research Journal on Advanced Science Hub. 2023;5:434-441. DOI: &nbsp;http://dx.doi.org/10.47392/irjash.2023.S059Petrozziello A, Redman CWG, Papageorghiou AT, et al. Multimodal Convolutional Neural Networks to Detect Fetal Compromise During Labor and Delivery. IEEE Access. 2019;7:112026-112036. DOI: https://doi.org/10.1109/ACCESS.2019.2933368Mendis L, Palaniswami M, Brownfoot F, et al. Computerised Cardiotocography Analysis for the Automated Detection of Fetal Compromise during Labour: A Review. Bioengineering. 2023;10(9):1007. DOI: &nbsp;https://doi.org/10.3390/bioengineering10091007Alotaibi D, Aldossary H, Albrahim R, et al. Fetal Hypoxia Detection Using Machine Learning: A Narrative Review. AI. 2024;5(2):516-532. DOI: &nbsp;https://doi.org/10.3390/ai5020026Francis F, Luz S, Wu H, et al. Machine learning on cardiotocography data to classify fetal outcomes: A scoping review. Computers in Biology and Medicine. 2024;172:108220. DOI: &nbsp;https://doi.org/10.1016/j.compbiomed.2024.108220Harish S, Reeja SR. Comprehensive Review of Fetal Health Monitoring using DL and ML techniques with Ultrasound and Cardiotocography data. In: International Conference on Emerging Systems and Intelligent Computing (ESIC); 2024 Feb 9-10; Bhubaneswar, India; 2024. DOI: https://doi.org/10.1109/ESIC60604.2024.10481665Tarvonen M, Manninen M, Lamminaho P, et al. Computer Vision for Identification of Increased Fetal Heart Variability in Cardiotocogram. Neonatology. 2024;121(4):460-467. DOI: &nbsp;https://doi.org/10.1159/000538134Frasch MG. Fetal heart rate variability: An ocean of meanings beyond ups and downs. BJOG: An International Journal of Obstetrics and Gynaecology. 2023;130(12):1557-1558. DOI: https://doi.org/10.1111/1471-0528.17391M&rsquo;Barek IB, Jauvion G, Vitrou J, et al. DeepCTG 1.0: an interpretable model to detect fetal hypoxia from cardiotocographydata during labor and delivery. Frontiers in Pediatrics. 2023;11:1190441. DOI: https://doi.org/10.3389/fped.2023.1190441Baxi S. Machine learning based clinical decision support system to predict fetal hypoxia in women during antenatal check-up. Paripex - Indian Journal Of Research. 2021;10(4):82-90. DOI: &nbsp;https://doi.org/10.36106/paripex/0609546Chen M, Yin Z. Classification of Cardiotocography Based on the Apriori Algorithm and Multi-Model Ensemble Classifier. Frontiers in Cell and Developmental Biology. 2022;10:888859. DOI: &nbsp;https://doi.org/10.3389/fcell.2022.888859Jones GD, Cooke W, Vatish M. Identifying high-risk pre-term pregnancies using the fetal heart rate and machine learning. medRxiv. 2024;24303280. DOI: https://doi.org/10.1101/2024.02.26.24303280Frasch MG, Strong SB, Nilosek D, et al. Detection of Preventable Fetal Distress During Labor From Scanned Cardiotocogram Tracings Using Deep Learning. Frontiers in Pediatrics. 2021;9:736834. DOI: https://doi.org/10.3389/fped.2021.736834Zhong M, Yi H, Lai F, et al. CTGNet: Automatic analysis of fetal heart rate from cardiotocograph using artificial intelligence. Maternal-Fetal Medicine. 2022;4(2):103-112. DOI: &nbsp;https://doi.org/10.1097/FM9.0000000000000147Ponsiglione AM, Cosentino C, Cesarelli G, et al. A Comprehensive Review of Techniques for Processingand Analyzing Fetal Heart Rate Signals. Sensors. 2021;21(18):6136. DOI: https://doi.org/10.3390/s21186136Mendis L, Palaniswami M, Keenan E, et al. Rapid detection of fetal compromise using input length invariant deep learning on fetal heart rate signals. Scientific Reports. 2024;14(1):12615. DOI: https://doi.org/10.1038/s41598-024-63108-6Sahin H, Subasi A. Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniques. Procedia Computer Science. 2020;168:34-39. DOI: &nbsp;https://doi.org/10.1016/j.procs.2020.02.248Bertieaux J, Shateri M, Labeau F, et al. Cardiotocography Signal Abnormality Detection Based on Deep Semi-Unsupervised Learning. Proceedings of the IEEE/ACM 10th International Conference on Big Data Computing, Applications and Technologies (BDCAT &#39;23). Association for Computing Machinery; 2022 Sep 29; New York, USA; 2022. DOI: https://doi.org/10.1145/3632366.3632391Yu Z, Hu Y, Lu Y, et al. CTGGAN: Reliable Fetal Heart Rate Signal Generation Using GANs. Proceedings of the 2024 International Joint Conference on Neural Networks (IJCNN); 2024 June; Yokohama, Japan; 2024. DOI: https://doi.org/10.1109/IJCNN60899.2024.10650729Zhang Y, Zhao Z, Deng Y, et al. FHRGAN: Generative adversarial networks for synthetic fetal heart rate signal generation in low-resource settings. Information Sciences. 2022;594:136-150. DOI: https://doi.org/10.1016/j.ins.2022.01.070Zhao Z, Zhu J, Jiao P, et al. Hybrid-FHR: a multi-modal AI approach for automated fetal acidosis diagnosis. BMC Medical Informatics and Decision Making. 2024;24(1):19. DOI: &nbsp;https://doi.org/10.1186/s12911-024-02423-4Cao Z, Wang G, Xu L, et al. Intelligent antepartum fetal monitoring via deep learning and fusion of cardiotocographic signals and clinical data. Health Information Science and Systems. 2023;11(1):16. DOI: &nbsp;https://doi.org/10.1007/s13755-023-00219-wBlack S, Jiaqi Zhao, Xinrong Miao, Yanqiao Wu. NeuroFetalNet: Advancing Remote Electronic Fetal Monitoring with a New Dataset and Comparative Analysis of FHR and UCP Impact. EasyChair. 2024. DOI:10.1109/ICDH62654.2024.00039Fergus P, Chalmers C, Montanez CC, et al. Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes. IEEE Transactions on Emerging Topics in Computational Intelligence. 2021;5(6):882-892. DOI: https://DOI.org/10.1109/TETCI.2020.3020061Baghel N, Burget R, Dutta MK. 1D-FHRNet: Automatic Diagnosis of Fetal Acidosis from Fetal Heart Rate Signals. Biomedical Signal Processing and Control. 2021;71(1):102794. DOI: 10.1016/j.bspc.2021.102794