{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T17:31:23Z","timestamp":1790184683764,"version":"4.1.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Bio-convergence Technology Education Program (KIAT)","award":["P0017805"],"award-info":[{"award-number":["P0017805"]}]},{"name":"Korea Health Technology R&D Project (KHIDI)","award":["RS-2023-00266038"],"award-info":[{"award-number":["RS-2023-00266038"]}]},{"name":"Machine learning data collection projects"},{"name":"Physician Scientist research fund of Ajou University School of Medicine"},{"name":"MD-PhD\/Medical Scientist Training Program (KHIDI)"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Timely detection of abnormal cardiotocography (CTG) during labor plays a crucial role in enhancing fetal prognosis. Recent research has explored the use of deep learning for CTG interpretation, most studies rely on small, localized datasets or focus on outcomes less relevant to clinical practice. To address these limitations, we developed a clinically applicable model using a large-scale, nationwide CTG dataset with reliable annotations provided by a board-certified obstetrician. Our study utilized 22,522 deliveries from 14 hospitals, each including cardiotocography (CTG) recordings of up to 75\u00a0min in length. The CTG signals were segmented into 5-minute intervals, resulting in a total of 519,800 person-minutes of analyzed data. We trained and validated a deep learning model based on CTG segments for classifying normal and abnormal CTGs. In the independent test dataset, the model achieved an AUC (area under the receiver operating characteristic curve) of 0.880 and PRC (area under the precision-recall curve) of 0.625 in internal tests. External tests across three datasets achieved AUCs of 0.862, 0.895, and 0.862 and PRCs of 0.553, 0.615, and 0.601. Our study results show the potential of the deep learning for automated CTG interpretation. We will evaluate this model in future prospective studies to assess the model\u2019s clinical applicability.<\/jats:p>","DOI":"10.1038\/s41598-025-02849-4","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T06:33:31Z","timestamp":1749018811000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Automated interpretation of cardiotocography using deep learning in a nationwide multicenter study"],"prefix":"10.1038","volume":"15","author":[{"given":"Chang Eun","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byungjin","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rae Woong","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong Wook","family":"Kwak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Sun","family":"Ko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Won Joon","family":"Seong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun-Hwa","family":"Cha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Mi","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jisun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun-Joo","family":"Seol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungyeon","family":"Pyeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soon-Cheol","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun Dan","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyung Joon","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joong Shin","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Nam","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Ah","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoon Ha","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gwang Jun","family":"kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miran","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hye Jin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"issue":"6","key":"2849_CR1","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1016\/j.ajog.2018.03.011","volume":"218","author":"D Ayres-de-Campos","year":"2018","unstructured":"Ayres-de-Campos, D. Electronic fetal monitoring or cardiotocography, 50 years later: what\u2019s in a name? Am. J. Obstet. Gynecol. 218(6), 545\u2013546 (2018).","journal-title":"Am. J. Obstet. Gynecol."},{"issue":"3","key":"2849_CR2","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1097\/GRF.0b013e318253b318","volume":"55","author":"E O\u2019neill","year":"2012","unstructured":"O\u2019neill, E. & Thorp, J. Antepartum evaluation of the fetus and fetal well being. Clin. Obstet. Gynecol. 55(3), 722\u2013730 (2012).","journal-title":"Clin. Obstet. Gynecol."},{"issue":"10080","key":"2849_CR3","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1016\/S0140-6736(17)30568-8","volume":"389","author":"P Brocklehurst","year":"2017","unstructured":"Brocklehurst, P. et al. Computerised interpretation of fetal heart rate during labour (INFANT): a randomised controlled trial. Lancet 389(10080), 1719\u20131729 (2017).","journal-title":"Lancet"},{"key":"2849_CR4","doi-asserted-by":"crossref","unstructured":"Francis, F., Luz, S., Wu, H., Stock, S. J. & Townsend, R. Machine learning on cardiotocography data to classify fetal outcomes: A scoping review. Comput. Biol. Med. 108220. (2024).","DOI":"10.1016\/j.compbiomed.2024.108220"},{"key":"2849_CR5","doi-asserted-by":"publisher","first-page":"112026","DOI":"10.1109\/ACCESS.2019.2933368","volume":"7","author":"A Petrozziello","year":"2019","unstructured":"Petrozziello, A., Redman, C. W., Papageorghiou, A. T., Jordanov, I. & Georgieva, A. Multimodal convolutional neural networks to detect fetal compromise during labor and delivery. IEEE Access. 7, 112026\u2013112036 (2019).","journal-title":"IEEE Access."},{"issue":"3","key":"2849_CR6","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/JBHI.2016.2546312","volume":"21","author":"J Spilka","year":"2016","unstructured":"Spilka, J. et al. Sparse support vector machine for intrapartum fetal heart rate classification. IEEE J. Biomedical Health Inf. 21(3), 664\u2013671 (2016).","journal-title":"IEEE J. Biomedical Health Inf."},{"key":"2849_CR7","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s12553-017-0201-7","volume":"7","author":"G Georgoulas","year":"2017","unstructured":"Georgoulas, G. et al. Investigating pH based evaluation of fetal heart rate (FHR) recordings. Health Technol. 7, 241\u2013254 (2017).","journal-title":"Health Technol."},{"issue":"1","key":"2849_CR8","doi-asserted-by":"publisher","first-page":"13367","DOI":"10.1038\/s41598-021-92805-9","volume":"11","author":"J Ogasawara","year":"2021","unstructured":"Ogasawara, J. et al. Deep neural network-based classification of cardiotocograms outperformed conventional algorithms. Sci. Rep. 11(1), 13367 (2021).","journal-title":"Sci. Rep."},{"key":"2849_CR9","doi-asserted-by":"crossref","unstructured":"Mendis, L., Karmakar, D., Palaniswami, M., Brownfoot, F. & Keenan, E. Cross-Database evaluation of deep learning methods for intrapartum cardiotocography classification. IEEE J. Transl. Eng. Health Med.(2025).","DOI":"10.1109\/JTEHM.2025.3548401"},{"issue":"1","key":"2849_CR10","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.ajog.2024.04.022","volume":"232","author":"JA McCoy","year":"2025","unstructured":"McCoy, J. A. et al. Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning. Am. J. Obstet. Gynecol. 232(1), 116 (2025). e1-. e9.","journal-title":"Am. J. Obstet. Gynecol."},{"key":"2849_CR11","doi-asserted-by":"crossref","unstructured":"Grivell, R. M., Alfirevic, Z., Gyte, G. M. & Devane, D. Antenatal cardiotocography for fetal assessment. Cochrane Database Syst. Rev. 2015(9).","DOI":"10.1002\/14651858.CD007863.pub4"},{"issue":"1","key":"2849_CR12","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/361237.361242","volume":"15","author":"RO Duda","year":"1972","unstructured":"Duda, R. O. & Hart, P. E. Use of the Hough transformation to detect lines and curves in pictures. Commun. ACM. 15(1), 11\u201315 (1972).","journal-title":"Commun. ACM"},{"issue":"1","key":"2849_CR13","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.ijgo.2015.06.020","volume":"131","author":"D Ayres-de-Campos","year":"2015","unstructured":"Ayres-de-Campos, D., Spong, C. Y. & Chandraharan, E. FIGO consensus guidelines on intrapartum fetal monitoring: cardiotocography. Int. J. Gynecol. Obstet. 131(1), 13\u201324 (2015).","journal-title":"Int. J. Gynecol. Obstet."},{"issue":"4","key":"2849_CR14","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1111\/jep.12368","volume":"21","author":"L Hruban","year":"2015","unstructured":"Hruban, L. et al. Agreement on intrapartum cardiotocogram recordings between expert obstetricians. J. Eval. Clin. Pract. 21(4), 694\u2013702 (2015).","journal-title":"J. Eval. Clin. Pract."},{"issue":"6","key":"2849_CR15","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/j.ajog.2008.06.027","volume":"199","author":"SP Chauhan","year":"2008","unstructured":"Chauhan, S. P. et al. Intrapartum nonreassuring fetal heart rate tracing and prediction of adverse outcomes: interobserver variability. Am. J. Obstet. Gynecol. 199(6), 623 (2008). e1-. e5.","journal-title":"Am. J. Obstet. Gynecol."},{"key":"2849_CR16","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L. & Sun, G. (eds) Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2849_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. (eds) Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2849_CR18","unstructured":"Ioffe, S. Batch normalization: accelerating deep network training by reducing internal covariate shift. ArXiv Preprint arXiv 150203167. (2015)."},{"key":"2849_CR19","unstructured":"Nair, V. & Hinton, G. E. (eds) Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10) (2010)."},{"key":"2849_CR20","doi-asserted-by":"publisher","first-page":"1190441","DOI":"10.3389\/fped.2023.1190441","volume":"11","author":"M Ben","year":"2023","unstructured":"Ben, M. et al. DeepCTG\u00ae 1.0: an interpretable model to detect fetal hypoxia from cardiotocography data during labor and delivery. Front. Pead. 11, 1190441 (2023).","journal-title":"Front. Pead."},{"issue":"5","key":"2849_CR21","doi-asserted-by":"publisher","first-page":"858","DOI":"10.3390\/diagnostics13050858","volume":"13","author":"S Das","year":"2023","unstructured":"Das, S., Mukherjee, H., Roy, K. & Saha, C. K. Fetal health classification from cardiotocograph for both stages of labor\u2014A soft-computing-based approach. Diagnostics 13(5), 858 (2023).","journal-title":"Diagnostics"},{"key":"2849_CR22","doi-asserted-by":"publisher","first-page":"1090937","DOI":"10.3389\/fphys.2023.1090937","volume":"14","author":"Y Deng","year":"2023","unstructured":"Deng, Y. et al. A lightweight fetal distress-assisted diagnosis model based on a cross-channel interactive attention mechanism. Front. Physiol. 14, 1090937 (2023).","journal-title":"Front. Physiol."},{"issue":"11","key":"2849_CR23","doi-asserted-by":"publisher","first-page":"2843","DOI":"10.3390\/diagnostics12112843","volume":"12","author":"V Gude","year":"2022","unstructured":"Gude, V. & Corns, S. Integrated deep learning and supervised machine learning model for predictive fetal monitoring. Diagnostics 12(11), 2843 (2022).","journal-title":"Diagnostics"},{"key":"2849_CR24","doi-asserted-by":"publisher","first-page":"107300","DOI":"10.1016\/j.cmpb.2022.107300","volume":"229","author":"H Liang","year":"2023","unstructured":"Liang, H. & Lu, Y. A CNN-RNN unified framework for intrapartum cardiotocograph classification. Comput. Methods Programs Biomed. 229, 107300 (2023).","journal-title":"Comput. Methods Programs Biomed."},{"key":"2849_CR25","doi-asserted-by":"publisher","first-page":"969052","DOI":"10.3389\/fphys.2022.969052","volume":"13","author":"Y Xiao","year":"2022","unstructured":"Xiao, Y., Lu, Y., Liu, M., Zeng, R. & Bai, J. A deep feature fusion network for fetal state assessment. Front. Physiol. 13, 969052 (2022).","journal-title":"Front. Physiol."},{"key":"2849_CR26","doi-asserted-by":"publisher","first-page":"1021400","DOI":"10.3389\/fphys.2022.1021400","volume":"13","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y. et al. Multimodal learning for fetal distress diagnosis using a multimodal medical information fusion framework. Front. Physiol. 13, 1021400 (2022).","journal-title":"Front. Physiol."},{"key":"2849_CR27","doi-asserted-by":"publisher","first-page":"105190","DOI":"10.1016\/j.bspc.2023.105190","volume":"86","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y. et al. DT-CTNet: A clinically interpretable diagnosis model for fetal distress. Biomed. Signal Process. Control. 86, 105190 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"2849_CR28","doi-asserted-by":"publisher","first-page":"104929","DOI":"10.1016\/j.bspc.2023.104929","volume":"85","author":"Z Zhou","year":"2023","unstructured":"Zhou, Z., Zhao, Z., Zhang, X., Zhang, X. & Jiao, P. Improvement of accuracy and resilience in FHR classification via double trend accumulation encoding and attention mechanism. Biomed. Signal Process. Control. 85, 104929 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"2849_CR29","doi-asserted-by":"publisher","first-page":"106970","DOI":"10.1016\/j.compbiomed.2023.106970","volume":"159","author":"Z Zhou","year":"2023","unstructured":"Zhou, Z. et al. Identifying fetal status with fetal heart rate: deep learning approach based on long convolution. Comput. Biol. Med. 159, 106970 (2023).","journal-title":"Comput. Biol. Med."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02849-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02849-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02849-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T19:01:59Z","timestamp":1749409319000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-02849-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2849"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-02849-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"assertion":[{"value":"23 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19617"}}