{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T06:55:18Z","timestamp":1793775318152,"version":"4.6.1"},"reference-count":54,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"UK Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V002511\/1"],"award-info":[{"award-number":["EP\/V002511\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Cardiotocography (CTG) is a widely used technique to monitor fetal heart rate (FHR) during labour and assess the health of the baby. However, visual interpretation of CTG signals is subjective and prone to error. Automated methods that mimic clinical guidelines have been developed, but they failed to improve detection of abnormal traces. This study aims to classify CTGs with and without severe compromise at birth using routinely collected CTGs from 51,449 births at term from the first 20 min of FHR recordings. Three 1D-CNN and LSTM based architectures are compared. We also transform the FHR signal into 2D images using time-frequency representation with a spectrogram and scalogram analysis, and subsequently, the 2D images are analysed using a 2D-CNNs. In the proposed multi-modal architecture, the 2D-CNN and the 1D-CNN-LSTM are connected in parallel. The models are evaluated in terms of partial area under the curve (PAUC) between 0\u201310% false-positive rate; and sensitivity at 95% specificity. The 1D-CNN-LSTM parallel architecture outperformed the other models, achieving a PAUC of 0.20 and sensitivity of 20% at 95% specificity. Our future work will focus on improving the classification performance by employing a larger dataset, analysing longer FHR traces, and incorporating clinical risk factors.<\/jats:p>","DOI":"10.3390\/bioengineering10060730","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T03:04:40Z","timestamp":1687143880000},"page":"730","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Multimodal Deep Learning for Predicting Adverse Birth Outcomes Based on Early Labour Data"],"prefix":"10.3390","volume":"10","author":[{"given":"Daniel","family":"Asfaw","sequence":"first","affiliation":[{"name":"School of Computing, University of Portsmouth, Portsmouth PO1 3HE, UK"},{"name":"Nuffield Department of Women\u2019s & Reproductive Health, University of Oxford, Oxford OX1 2JD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3169-5995","authenticated-orcid":false,"given":"Ivan","family":"Jordanov","sequence":"additional","affiliation":[{"name":"School of Computing, University of Portsmouth, Portsmouth PO1 3HE, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lawrence","family":"Impey","sequence":"additional","affiliation":[{"name":"Nuffield Department of Women\u2019s & Reproductive Health, University of Oxford, Oxford OX1 2JD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana","family":"Namburete","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford OX1 3QG, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raymond","family":"Lee","sequence":"additional","affiliation":[{"name":"Faculty of Technology, University of Portsmouth, Portsmouth PO1 2UP, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5543-6683","authenticated-orcid":false,"given":"Antoniya","family":"Georgieva","sequence":"additional","affiliation":[{"name":"Nuffield Department of Women\u2019s & Reproductive Health, University of Oxford, Oxford OX1 2JD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,19]]},"reference":[{"key":"ref_1","first-page":"CD006066","article-title":"Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour","volume":"2","author":"Alfirevic","year":"2017","journal-title":"Cochrane database Syst. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e1921363","DOI":"10.1001\/jamanetworkopen.2019.21363","article-title":"Clinician Identification of Birth Asphyxia Using Intrapartum Cardiotocography Among Neonates with and Without Encephalopathy in New Zealand","volume":"3","author":"Farquhar","year":"2020","journal-title":"JAMA Netw. Open"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1111\/aogs.13136","article-title":"Computerized data-driven interpretation of the intrapartum cardiotocogram: A cohort study","volume":"96","author":"Georgieva","year":"2017","journal-title":"Acta Obstet. Gynecol. Scand."},{"key":"ref_4","unstructured":"The Cochrane Collaboration (2013). Cochrane Database of Systematic Reviews, John Wiley & Sons, Ltd."},{"key":"ref_5","unstructured":"Draper, E., Gallimore, I., Smith, L., Fenton, A., Kurinczuk, J., and Smith, P. (2020). Maternal, Newborn and Infant Clinical Outcome Review Programme MBRRACE-UK Perinatal Mortality Surveillance Report, Infant Mortality and Morbidity Studies, Department of Health Sciences, University of Leicester."},{"key":"ref_6","unstructured":"Resolution, N.H.S. (2023, March 18). Annual report and accounts 2020\/21\u2019. Available online: https:\/\/resolution.nhs.uk\/wp-content\/uploads\/2021\/07\/Annual-report-and-accounts-2020-2021-WEB-1.pdf."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10302","DOI":"10.1016\/S0140-6736(21)01112-0","article-title":"Global, regional, and national estimates and trends in stillbirths from 2000 to 2019: A systematic assessment","volume":"398","author":"Hug","year":"2021","journal-title":"Lancet"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.ejogrb.2018.07.016","article-title":"Admission cardiotocography: A hospital based validation study","volume":"229","author":"Parts","year":"2018","journal-title":"Eur. J. Obstet. Gynecol. Reprod. Biol."},{"key":"ref_9","first-page":"CD005122","article-title":"Cardiotocography versus intermittent auscultation of fetal heart on admission to labour ward for assessment of fetal wellbeing","volume":"1","author":"Devane","year":"2017","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1111\/aogs.12091","article-title":"The admission CTG: Is there any evidence for still using the test?","volume":"92","author":"Blix","year":"2013","journal-title":"Acta Obstet. Gynecol. Scand."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"784439","DOI":"10.3389\/fped.2022.784439","article-title":"Cardiotocography and Clinical Risk Factors in Early Term Labor: A Retrospective Cohort Study Using Computerized Analysis with Oxford System","volume":"10","author":"Lovers","year":"2022","journal-title":"Front. Pediatr."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"255","DOI":"10.3389\/fphys.2019.00255","article-title":"Computer-Aided Diagnosis System of Fetal Hypoxia Incorporating Recurrence Plot with Convolutional Neural Network","volume":"10","author":"Zhao","year":"2019","journal-title":"Front. Physiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"526","DOI":"10.4236\/jbise.2012.59065","article-title":"Fetal distress prediction using discriminant analysis, decision tree, and artificial neural network","volume":"5","author":"Huang","year":"2012","journal-title":"JBiSE"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"11846","DOI":"10.1016\/j.eswa.2012.01.196","article-title":"Computerized analysis of fetal heart rate signals as the predictor of neonatal acidemia","volume":"39","author":"Czabanski","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102555","DOI":"10.1016\/j.bspc.2021.102555","article-title":"Intelligent classification of antepartum cardiotocography model based on deep forest","volume":"67","author":"Chen","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"62","DOI":"10.3109\/14767058.2016.1161750","article-title":"SisPorto 4.0\u2014Computer analysis following the 2015 FIGO Guidelines for intrapartum fetal monitoring","volume":"30","author":"Rei","year":"2017","journal-title":"J. Matern. Fetal. Neonatal. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.bspc.2018.05.016","article-title":"Open-access software for analysis of fetal heart rate signals","volume":"45","author":"Kocamaz","year":"2018","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.cmpb.2015.10.008","article-title":"Software for computerised analysis of cardiotocographic traces","volume":"124","author":"Romano","year":"2016","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.bspc.2018.10.002","article-title":"Automated fetal heart rate analysis for baseline determination and acceleration\/deceleration detection: A comparison of 11 methods versus expert consensus","volume":"49","author":"Boudet","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"The INFANT Collaborative Group, Brocklehurst, P., Field, D., Greene, K., Juszczak, E., Keith, R., Kenyon, S., Linsell, L., Mabey, C., and Newburn, M. (2017). Computerised interpretation of fetal heart rate during labour (INFANT): A randomised controlled trial. Lancet, 389, 1719\u20131729.","DOI":"10.1016\/S0140-6736(17)30568-8"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1097\/AOG.0000000000001799","article-title":"Central Fetal Monitoring with and Without Computer Analysis: A Randomized Controlled Trial","volume":"129","author":"Nunes","year":"2017","journal-title":"Obstet. Gynecol."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yu, K., Quirk, J.G., and Djuric, P.M. (2016, January 20\u201325). Fetal heart rate analysis by hierarchical dirichlet process mixture models. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.","DOI":"10.1109\/ICASSP.2016.7471767"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103525","DOI":"10.1016\/j.compbiomed.2019.103525","article-title":"Use of automated fetal heart rate analysis to identify risk factors for umbilical cord acidosis at birth","volume":"115","author":"Boudet","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/s00521-011-0743-y","article-title":"Artificial neural networks applied to fetal monitoring in labour","volume":"22","author":"Georgieva","year":"2013","journal-title":"Neural. Comput. Applic."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.compbiomed.2018.06.003","article-title":"Prognostic model based on image-based time-frequency features and genetic algorithm for fetal hypoxia assessment","volume":"99","author":"Kocamaz","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2796","DOI":"10.1109\/TBME.2014.2330556","article-title":"Fetal Heart Rate Classification Using Generative Models","volume":"61","author":"Dash","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"226","DOI":"10.4103\/ijabmr.IJABMR_370_18","article-title":"Use of machine learning algorithms for prediction of fetal risk using cardiotocographic data","volume":"9","author":"Hoodbhoy","year":"2019","journal-title":"Int. J. App. Basic Med. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Petrozziello, A., Jordanov, I., Papageorghiou, T.A., Redman, W.G.C., and Georgieva, A. (2018, January 18\u201321). Deep Learning for Continuous Electronic Fetal Monitoring in Labor. Proceedings of the 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, HI, USA.","DOI":"10.1109\/EMBC.2018.8513625"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"13367","DOI":"10.1038\/s41598-021-92805-9","article-title":"Deep neural network-based classification of cardiotocograms outperformed conventional algorithms","volume":"11","author":"Ogasawara","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"102794","DOI":"10.1016\/j.bspc.2021.102794","article-title":"1D-FHRNet: Automatic Diagnosis of Fetal Acidosis from Fetal Heart Rate Signals","volume":"71","author":"Baghel","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, T., Lu, C., Sun, Y., Yang, M., Liu, C., and Ou, C. (2021). Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network. Entropy, 23.","DOI":"10.3390\/e23010119"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"106981","DOI":"10.1016\/j.cmpb.2022.106981","article-title":"VOC-DL: Deep learning prediction model for COVID-19 based on VOC virus variants","volume":"224","author":"Liao","year":"2022","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Chud\u00e1\u010dek, V., Spilka, J., Bur\u0161a, M., Jank\u016f, P., Hruban, L., Huptych, M., and Lhotsk\u00e1, L. (2014). Open access intrapartum CTG database. BMC Pregnancy Childbirth, 14.","DOI":"10.1186\/1471-2393-14-16"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"115714","DOI":"10.1016\/j.eswa.2021.115714","article-title":"An attention-based CNN-BiLSTM hybrid neural network enhanced with features of discrete wavelet transformation for fetal acidosis classification","volume":"186","author":"Liu","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"112026","DOI":"10.1109\/ACCESS.2019.2933368","article-title":"Multimodal Convolutional Neural Networks to Detect Fetal Compromise During Labor and Delivery","volume":"7","author":"Petrozziello","year":"2019","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1587\/nolta.12.399","article-title":"Predicting high risk birth from real large-scale cardiotocographic data using multi-input convolutional neural networks","volume":"12","author":"Mohannad","year":"2021","journal-title":"NOLTA"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1007\/s12652-021-02926-2","article-title":"Spectrogram analysis of ECG signal and classification efficiency using MFCC feature extraction technique","volume":"13","author":"Arpitha","year":"2021","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/TUFFC.2019.2943626","article-title":"Doppler Ultrasound Technology for Fetal Heart Rate Monitoring: A Review","volume":"67","author":"Hamelmann","year":"2020","journal-title":"IEEE Trans. Ultrason. Ferroelect. Freq. Control."},{"key":"ref_41","first-page":"521","article-title":"Discriminating Normal from \u201cAbnormal\u201d Pregnancy Cases Using an Automated FHR Evaluation Method\u2019","volume":"Volume 8445","author":"Likas","year":"2014","journal-title":"Artificial Intelligence: Methods and Applications"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Barzideh, F., Urdal, J., Hussein, K., Engan, K., Skretting, K., Mdoe, P., Kamala, B., and Brunner, S. (2018, January 3\u20137). Estimation of Missing Data in Fetal Heart Rate Signals Using Shift-Invariant Dictionary. Proceedings of the 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy.","DOI":"10.23919\/EUSIPCO.2018.8553110"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Feng, G., Quirk, J.G., and Djuric, P.M. (September, January 28). Recovery of missing samples in fetal heart rate recordings with Gaussian processes. Proceedings of the 2017 25th European Signal Processing Conference (EUSIPCO), Kos, Greece.","DOI":"10.23919\/EUSIPCO.2017.8081209"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Feng, G., Quirk, J.G., Heiselman, C., and Djuric, P.M. (2021, January 18\u201321). Estimation of Consecutively Missed Samples in Fetal Heart Rate Recordings. Proceedings of the 2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, The Netherlands.","DOI":"10.23919\/Eusipco47968.2020.9287490"},{"key":"ref_45","unstructured":"Asfaw, D., Jordanov, I., Impey, L., Namburete, A., Lee, R., and Georgieva, A. (2022). International Conference on Machine Learning, Optimization, and Data Science, Certosa di Pontignano, Italy, 19\u201322 September 2022, Springer Nature."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1007\/s40708-015-0029-8","article-title":"Time\u2013frequency texture descriptors of EEG signals for efficient detection of epileptic seizure","volume":"3","author":"Guo","year":"2016","journal-title":"Brain Inf."},{"key":"ref_47","first-page":"5067651","article-title":"Deep Learning Enabled Fault Diagnosis Using Time-Frequency Image Analysis of Rolling Element Bearings","volume":"2017","author":"Verstraete","year":"2017","journal-title":"Shock. Vib."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1038\/s41592-021-01302-4","article-title":"The class imbalance problem","volume":"18","author":"Megahed","year":"2021","journal-title":"Nat. Methods."},{"key":"ref_49","unstructured":"Iwana, B.K., and Uchida, S. (2007). An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks. arXiv."},{"key":"ref_50","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv."},{"key":"ref_51","unstructured":"Falkner, S., Klein, A., and Hutter, F. (2021). BOHB: Robust and Efficient Hyperparameter Optimization at Scale. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"103865","DOI":"10.1016\/j.compbiomed.2020.103865","article-title":"Concept attribution: Explaining CNN decisions to physicians","volume":"123","author":"Graziani","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_53","unstructured":"Ramponi, G., Protopapas, P., Brambilla, M., and Janssen, R. (2019). \u2018T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Mousavi, S., Afghah, F., Razi, A., and Acharya, U.R. (2019, January 19\u201322). ECGNET: Learning where to attend for detection of atrial fibrillation with deep visual attention. Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Chicago, IL, USA.","DOI":"10.1109\/BHI.2019.8834637"}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/10\/6\/730\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:56:10Z","timestamp":1760126170000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/10\/6\/730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":54,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["bioengineering10060730"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering10060730","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,19]]}}}