{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T16:54:27Z","timestamp":1790787267586,"version":"4.1.0"},"reference-count":48,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Hospital Administration\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t              https:\/\/ror.org\/00xdrzy17","award":["YLXX24AIA006"],"award-info":[{"award-number":["YLXX24AIA006"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["21625346"],"award-info":[{"award-number":["21625346"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Provincial Cross-Regional Innovation Cooperation Project","award":["2025YFHZ0326"],"award-info":[{"award-number":["2025YFHZ0326"]}]},{"DOI":"10.13039\/501100017691","name":"Key Research and Development Program of Guangxi Province","doi-asserted-by":"publisher","award":["2023AB22074"],"award-info":[{"award-number":["2023AB22074"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017691","name":"Key Research and Development Program of Guangxi Province","doi-asserted-by":"publisher","award":["2024AB04027"],"award-info":[{"award-number":["2024AB04027"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Accurate assessment of hypoxia-related fetal risk during labour is essential for improving perinatal outcomes while avoiding unnecessary operative interventions. Although deep learning has shown promise for automated fetal risk assessment, most existing approaches rely on cardiotocography (CTG) alone; CTG interpretation is known to suffer from a high false-positive rate and may not fully reflect fetal status without complementary clinical context. To address this limitation, we propose MIRF-Net, a multimodal intrapartum fetal risk assessment framework that jointly models (i) CTG time-series signals, (ii) Gramian Angular Difference Field (GADF) images that encode global correlation structure of fetal heart rate, and (iii) structured maternal metadata. MIRF-Net combines a PatchTST encoder for CTG, a pretrained ResNet101 for GADF images, and an autoencoder for maternal metadata and then performs cross-modal interaction learning with a fusion Transformer for final risk prediction. Using 552 eligible CTG recordings from the public CTU-UHB intrapartum database, which were split into training, validation, and test sets at a ratio of 6:2:2, MIRF-Net outperforms representative baselines on the test set, achieving a quality index (QI) of 74.76%, AUC of 0.7413, and Brier score of 0.2537, indicating improved discrimination and better-calibrated risk probabilities. Ablation studies further confirm the complementary contributions of each modality and show that Transformer-based fusion yields the most consistent overall gains. These results suggest that MIRF-Net provides reliable decision support for intelligent intrapartum monitoring.<\/jats:p>","DOI":"10.3390\/bioengineering13040385","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T12:45:53Z","timestamp":1774615553000},"page":"385","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MIRF-Net: A Multimodal Data Fusion Framework for Intrapartum Fetal Risk Assessment"],"prefix":"10.3390","volume":"13","author":[{"given":"Yaosheng","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, College of Information Science and Technology, Jinan University, Guangzhou 510632, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0187-0595","authenticated-orcid":false,"given":"Yaqi","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, College of Information Science and Technology, Jinan University, Guangzhou 510632, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieyun","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, College of Information Science and Technology, Jinan University, Guangzhou 510632, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziduo","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, College of Information Science and Technology, Jinan University, Guangzhou 510632, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1080\/08839514.2016.1193717","article-title":"Fuzzy Analysis of Delivery Outcome Attributes for Improving the Automated Fetal State Assessment","volume":"30","author":"Czabanski","year":"2016","journal-title":"Appl. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"19617","DOI":"10.1038\/s41598-025-02849-4","article-title":"Automated interpretation of cardiotocography using deep learning in a nationwide multicenter study","volume":"15","author":"Park","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1016\/S0143-4004(97)90000-X","article-title":"Oxygen and placental villous development: Origins of fetal hypoxia","volume":"18","author":"Kingdom","year":"1997","journal-title":"Placenta"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.placenta.2006.06.007","article-title":"Development and Mechanisms of Fetal Hypoxia in Severe Fetal Growth Restriction","volume":"28","author":"Regnault","year":"2007","journal-title":"Placenta"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1515\/jpm-2022-0292","article-title":"A second look at intrapartum fetal surveillance and future directions","volume":"51","author":"Ugwumadu","year":"2022","journal-title":"J. P\u00e9rinat. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2349","DOI":"10.1080\/14767058.2019.1666819","article-title":"Physiological CTG interpretation: The significance of baseline fetal heart rate changes after the onset of decelerations and associated perinatal outcomes","volume":"34","author":"Jia","year":"2019","journal-title":"J. Matern. Neonatal Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"105712","DOI":"10.1016\/j.cmpb.2020.105712","article-title":"Classifying the type of delivery from cardiotocographic signals: A machine learning approach","volume":"196","author":"Ricciardi","year":"2020","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1515\/jpme.1993.21.6.475","article-title":"Fetal monitoring by pulse oximetry and CTG","volume":"21","author":"Johnson","year":"1993","journal-title":"J. Perinat. Med."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Saleem, S., Naqvi, S.S., Manzoor, T., Saeed, A., Rehman, N.U., and Mirza, J. (2019). A strategy for classification of`vaginalof`vaginal vs. cesarean section\u2019 delivery: Bivariate empirical mode decomposition of cardiotocographic recordings. Front. Physiol., 10.","DOI":"10.3389\/fphys.2019.00246"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ramla, M., Sangeetha, S., and Nickolas, S. (2018, January 14\u201315). Fetal Health State Monitoring Using Decision Tree Classifier from Cardiotocography Measurements. Proceedings of the 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India.","DOI":"10.1109\/ICCONS.2018.8663047"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104218","DOI":"10.1016\/j.compbiomed.2021.104218","article-title":"Cardiotocography Signal Abnormality Classification Using Time-frequency Features and Ensemble Cost-sensitive SVM Classifier","volume":"130","author":"Zeng","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"54776","DOI":"10.1109\/ACCESS.2020.2980942","article-title":"Analysis of Dimensionality Reduction Techniques on Big Data","volume":"8","author":"Reddy","year":"2020","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1111\/jep.12368","article-title":"Agreement on intrapartum cardiotocogram recordings between expert obstetricians","volume":"21","author":"Hruban","year":"2015","journal-title":"J. Evaluation Clin. Pract."},{"key":"ref_14","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_15","doi-asserted-by":"crossref","unstructured":"Fei, Y., Huang, X., Chen, Q., Chen, J., Li, L., Hong, J., Hao, Z., and Wei, H. (2020). Automatic Classification of Antepartum Cardiotocography Using Fuzzy Clustering and Adaptive Neuro -Fuzzy Inference System. Proceedings of the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Seoul, Republic of Korea, 16\u201319 December 2020, IEEE.","DOI":"10.1109\/BIBM49941.2020.9313143"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e12899","DOI":"10.1111\/exsy.12899","article-title":"Fetal health classification from cardiotocographic data using machine learning","volume":"39","author":"Mehbodniya","year":"2021","journal-title":"Expert Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"107300","DOI":"10.1016\/j.cmpb.2022.107300","article-title":"A CNN-RNN unified framework for intrapartum cardiotocograph classification","volume":"229","author":"Liang","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"115714","DOI":"10.1016\/j.eswa.2021.115714","article-title":"An attention-based CNN\u2013BiLSTM 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_19","doi-asserted-by":"crossref","first-page":"104008","DOI":"10.1016\/j.bspc.2022.104008","article-title":"Intelligent classification of antenatal cardiotocography signals via multimodal bidirectional gated recurrent units","volume":"78","author":"Fei","year":"2022","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Lu, Y., Liu, M., Zeng, R., and Bai, J. (2022). A deep feature fusion network for fetal state assessment. Front. Physiol., 13.","DOI":"10.3389\/fphys.2022.969052"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Asfaw, D., Jordanov, I., Impey, L., Namburete, A., Lee, R., and Georgieva, A. (2024, January 6\u201312). Gated Self Attention Convolutional Neural Networks for Predicting Adverse Birth Outcomes. Proceedings of the 2024 16th IIAI International Congress on Advanced Applied Informatics (IIAI-AAI), Takamatsu, Japan.","DOI":"10.1109\/IIAI-AAI63651.2024.00057"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.bspc.2024.106629","article-title":"ETCNN: An ensemble transformer-convolutional neural network for automatic analysis of fetal heart rate","volume":"96","author":"Wu","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_23","unstructured":"Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2022). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1007\/s13755-023-00219-w","article-title":"Intelligent antepartum fetal monitoring via deep learning and fusion of cardiotocographic signals and clinical data","volume":"11","author":"Cao","year":"2023","journal-title":"Health Inf. Sci. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1038\/s44294-025-00068-w","article-title":"Development and evaluation of deep learning models for cardiotocography interpretation","volume":"3","author":"Chiou","year":"2025","journal-title":"npj Women\u2019s Health"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Khan, M.J., Vatish, M., and Jones, G.D. (2025). PatchCTG: A Patch Cardiotocography Transformer for antepartum fetal monitoring. Sensors, 25.","DOI":"10.3390\/s25092650"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"109448","DOI":"10.1016\/j.compbiomed.2024.109448","article-title":"DeepCTG\u00ae 2.0: Development and validation of a deep learning model to detect neonatal acidemia from cardiotocography during labor","volume":"184","author":"Jauvion","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_28","unstructured":"Wang, Z., and Oates, T. (2015, January 25\u201326). Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks. Proceedings of the Workshops at the Twenty-ninth Aaai Conference on Artificial Intelligence, Austin, TX, USA."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e306","DOI":"10.1016\/S2214-109X(23)00468-0","article-title":"A global analysis of the determinants of maternal health and transitions in maternal mortality","volume":"12","author":"Souza","year":"2024","journal-title":"Lancet Glob. Health"},{"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","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_32","doi-asserted-by":"crossref","unstructured":"Bai, J., Pan, X., Lu, Y., Zhong, M., Wang, H., Zheng, Z., and Guo, X. (2023). Comparison of fetal heart rate baseline estimation by the cardiotocograph network and clinicians: A multidatabase retrospective assessment study. Front. Cardiovasc. Med., 10.","DOI":"10.3389\/fcvm.2023.1059211"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"105690","DOI":"10.1016\/j.dib.2020.105690","article-title":"Annotation dataset of the cardiotocographic recordings constituting the \u201cCTU-CHB intra-partum CTG database\u201d","volume":"31","author":"Romagnoli","year":"2020","journal-title":"Data Brief"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"Physiobank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Holzinger, A. (2016). Survey on Feature Extraction and Applications of Biosignals. Machine Learning for Health Informatics. Lecture Notes in Computer Science, Springer.","DOI":"10.1007\/978-3-319-50478-0"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"62","DOI":"10.3109\/14767058.2016.1161750","article-title":"SisPorto 4.0\u2013computer analysis following the 2015 FIGO Guidelines for intrapartum fetal monitoring","volume":"30","author":"Rei","year":"2017","journal-title":"J. Matern. Neonatal Med."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1007\/s00404-021-06377-0","article-title":"Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: Combining bleeding high risk factors and uterine contraction curve","volume":"306","author":"Liu","year":"2022","journal-title":"Arch. Gynecol. Obstet."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1007\/s11276-015-0891-6","article-title":"A new delay jitter smoothing algorithm based on Pareto distribution in Cyber-Physical Systems","volume":"21","author":"Zhang","year":"2015","journal-title":"Wirel. Networks"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1109\/TCBB.2022.3198998","article-title":"HA-ResNet: Residual Neural Network with Hidden Attention for ECG Arrhythmia Detection Using Two-Dimensional Signal","volume":"20","author":"Guan","year":"2023","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"(2014). Practice bulletin no. 145: Antepartum fetal surveillance. Obstet. Gynecol., 124, 182\u2013192.","DOI":"10.1097\/01.AOG.0000451759.90082.7b"},{"key":"ref_41","first-page":"228","article-title":"Maternal diabetes and fetal hypoxia","volume":"129","author":"Teramo","year":"2013","journal-title":"Duodecim"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"39","DOI":"10.3109\/00016340903418751","article-title":"Risk factors for asphyxia associated with substandard care during labor","volume":"89","author":"Berglund","year":"2010","journal-title":"Acta Obstet. et Gynecol. Scand."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1097\/AOG.0b013e31822c9198","article-title":"Risk factors for severe neonatal acidosis","volume":"118","author":"Maisonneuve","year":"2011","journal-title":"Obstet. Gynecol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"e043827","DOI":"10.1136\/bmjopen-2020-043827","article-title":"Umbilical artery lactate levels and associated maternal and newborn characteristics at Mulago National Referral Hospital: A cross-sectional observational study","volume":"11","author":"Ogik","year":"2021","journal-title":"BMJ Open"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.ajog.2004.05.044","article-title":"How long is too long: Does a prolonged second stage of labor in nulliparous women affect maternal and neonatal outcomes?","volume":"191","author":"Cheng","year":"2004","journal-title":"Am. J. Obstet. Gynecol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1007\/s00592-021-01756-0","article-title":"Intrapartal cardiotocographic patterns and hypoxia-related perinatal outcomes in pregnancies complicated by gestational diabetes mellitus","volume":"58","author":"Tarvonen","year":"2021","journal-title":"Acta Diabetol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s44294-024-00033-z","article-title":"Deep learning with information fusion and model interpretation for long-term prenatal fetal heart rate data","volume":"2","author":"Lin","year":"2024","journal-title":"npj Women\u2019s Health"},{"key":"ref_48","first-page":"36314","article-title":"Medformer: A multi-granularity patching transformer for medical time-series classification","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/4\/385\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T13:33:12Z","timestamp":1774618392000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/13\/4\/385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["bioengineering13040385"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering13040385","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]}}}