{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T12:35:03Z","timestamp":1793190903384,"version":"4.5.0"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No. 2019YFC0121907"],"award-info":[{"award-number":["No. 2019YFC0121907"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:p>CTG (cardiotocography) has consistently been used to diagnose fetal hypoxia. It is susceptible to identifying the average fetal acid-base balance but lacks specificity in recognizing prenatal acidosis and neurological impairment. CTG plays a vital role in intrapartum fetal state assessment, which can prevent severe organ damage if fetal hypoxia is detected earlier. In this paper, we propose a novel deep feature fusion network (DFFN) for fetal state assessment. First, we extract spatial and temporal information from the fetal heart rate (FHR) signal using a multiscale CNN-BiLSTM network, increasing the features\u2019 diversity. Second, the multiscale CNN-BiLSM network and frequently used features are integrated into the deep learning model. The proposed DFFN model combines different features to improve classification accuracy. The multiscale convolutional kernels can identify specific essential information and consider signal\u2019s temporal information. The proposed method achieves 61.97%, 73.82%, and 66.93% of sensitivity, specificity, and quality index, respectively, on the public CTU-UHB database. The proposed method achieves the highest QI on the private database, verifying the proposed method\u2019s effectiveness and generalization. The proposed DFFN combines the advantages of feature engineering and deep learning models and achieves competitive accuracy in fetal state assessment compared with related works.<\/jats:p>","DOI":"10.3389\/fphys.2022.969052","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T06:54:12Z","timestamp":1669791252000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["A deep feature fusion network for fetal state assessment"],"prefix":"10.3389","volume":"13","author":[{"given":"Yahui","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaosheng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mujun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongdan","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieyun","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"102289","DOI":"10.1016\/j.artmed.2022.102289","article-title":"Machine learning-based heart disease diagnosis: A systematic literature review","volume":"128","author":"Ahsan","year":"2022","journal-title":"Artif. Intell. Med."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1149\/10701.1637ecst","article-title":"Classification of fhr signals based on morphological features","volume":"107","author":"Akkanapalli","year":"2022","journal-title":"ECS Trans."},{"key":"B3","doi-asserted-by":"crossref","DOI":"10.1109\/ICEEICT53079.2022.9768509","article-title":"Extraction of morphological, time domain and non-linear features of fhr signals","author":"Akkanapalli","year":"2022"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e452","DOI":"10.7717\/peerj-cs.452","article-title":"A systematic review of automated pre-processing, feature extraction and classification of cardiotocography","volume":"7","author":"Al-Yousif","year":"2021","journal-title":"PeerJ. Comput. Sci."},{"key":"B5","doi-asserted-by":"publisher","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":"Aulnoit","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"B6","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.ijgo.2015.06.020","article-title":"Figo consensus guidelines on intrapartum fetal monitoring: Cardiotocography","volume":"131","author":"Ayres-de Campos","year":"2015","journal-title":"Int. J. Gynaecol. Obstet."},{"key":"B7","doi-asserted-by":"publisher","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":"B8","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-64265-9_9","article-title":"The use of convolutional neural networks in biomedical data processing","volume-title":"International conference on information technology in bio- and medical informatics","author":"Bursa","year":"2017"},{"key":"B9","doi-asserted-by":"publisher","first-page":"661400","DOI":"10.3389\/fped.2021.661400","article-title":"Systematic review of intrapartum fetal heart rate spectral analysis and an application in the detection of fetal acidemia","volume":"9","author":"Castro","year":"2021","journal-title":"Front. Pediatr."},{"key":"B10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/1471-2393-14-16","article-title":"Open access intrapartum ctg database","volume":"14","author":"Chud\u00e1\u010dek","year":"2014","journal-title":"BMC Pregnancy Childbirth"},{"key":"B11","first-page":"6051","article-title":"Assessment of features for automatic ctg analysis based on expert annotation","author":"Chud\u00e1\u010dek","year":"2011"},{"key":"B12","first-page":"569","article-title":"A study based on gray level co-occurrence matrix and neural network community for determination of hypoxic fetuses","volume-title":"International artificial intelligence and data processing symposium","author":"C\u00f6mert","year":""},{"key":"B13","doi-asserted-by":"publisher","first-page":"26","DOI":"10.5120\/ijca2016912417","article-title":"Evaluation of fetal distress diagnosis during delivery stages based on linear and nonlinear features of fetal heart rate for neural network community","volume":"156","author":"C\u00f6mert","year":"","journal-title":"Int. J. Comput. Appl."},{"key":"B14","first-page":"239","article-title":"Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach","volume-title":"Computer science on-line conference","author":"C\u00f6mert","year":"2018"},{"key":"B15","doi-asserted-by":"publisher","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":"C\u00f6mert","year":"","journal-title":"Comput. Biol. Med."},{"key":"B16","article-title":"Performance evaluation of empirical mode decomposition and discrete wavelet transform for computerized hypoxia detection and prediction","author":"C\u00f6mert","year":""},{"key":"B17","first-page":"226","article-title":"Recurrent neural network based classification of fetal heart rate using cardiotocograph","volume-title":"International conference on recent trends in image processing and pattern recognition","author":"Das","year":"2018"},{"key":"B18","first-page":"673","article-title":"Short-term fetal heart rate variation, decelerations, and umbilical flow velocity waveforms before labor","volume":"80","author":"Dawes","year":"1992","journal-title":"Obstet. Gynecol."},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1109\/NEUREL.2018.8586992","article-title":"Supervised and unsupervised learning of fetal heart rate tracings with deep Gaussian processes","author":"Feng","year":"2018"},{"key":"B20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.compbiomed.2017.12.002","article-title":"Machine learning ensemble modelling to classify caesarean section and vaginal delivery types using cardiotocography traces","volume":"93","author":"Fergus","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jogoh.2016.11.002","article-title":"Inter-observer reliability of 4 fetal heart rate classifications","volume":"46","author":"Garabedian","year":"2017","journal-title":"J. Gynecol. Obstet. Hum. Reprod."},{"key":"B22","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s10877-020-00535-6","article-title":"Fetal heart rate variability analysis for neonatal acidosis prediction","volume":"35","author":"Gatellier","year":"2021","journal-title":"J. Clin. Monit. Comput."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1111\/aogs.13639","article-title":"Computer-based intrapartum fetal monitoring and beyond: A review of the 2nd workshop on signal processing and monitoring in labor (october 2017, oxford, UK)","volume":"98","author":"Georgieva","year":"2019","journal-title":"Acta Obstet. Gynecol. Scand."},{"key":"B24","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/TBME.2006.872814","article-title":"Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines","volume":"53","author":"Georgoulas","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1161\/CIRCULATIONAHA.121.054689","article-title":"Breath of life: Heart disease link to developmental hypoxia","volume":"144","author":"Giussani","year":"2021","journal-title":"Circulation"},{"key":"B26","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/j.earlhumdev.2006.12.006","article-title":"Linear and nonlinear analysis of heart rate patterns associated with fetal behavioral states in the antepartum period","volume":"83","author":"Gon\u00e7alves","year":"2007","journal-title":"Early Hum. Dev."},{"key":"B27","doi-asserted-by":"publisher","first-page":"8","DOI":"10.24018\/ejmed.2022.4.2.1308","article-title":"Prediction of neonatal acidosis based on the type of fetal hypoxia observed on the cardiotocograph (ctg)","volume":"4","author":"Gunaratne","year":"2022","journal-title":"Eur. J. Med. Health Sci."},{"key":"B28","doi-asserted-by":"publisher","first-page":"57","DOI":"10.23950\/jcmk\/11683","article-title":"Is fetal ctg a reliable indicator of fetal distress? A prospective study on relationship between ctg suspected fetal distress and immediate postpartum umbilical cord blood ph","volume":"19","author":"Gupta","year":"2022","journal-title":"J. Clin. Med. Kazakhstan"},{"key":"B29","first-page":"262","article-title":"Polynomial flann classifier for fetal cardiotocography monitoring","author":"Haweel","year":"2021"},{"key":"B30","doi-asserted-by":"publisher","first-page":"63","DOI":"10.5005\/jp-journals-10006-2007","article-title":"Intrapartum fetal monitoring and its correlation with umbilical cord blood ph and early neonatal outcome: A prospective cohort study","volume":"14","author":"Kanagal","year":"2022","journal-title":"J. South Asian Fed. Obstetrics Gynaecol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"32","DOI":"10.4236\/jcc.2014.29005","article-title":"Analysis of cardiotocogram data for fetal distress determination by decision tree based adaptive boosting approach","volume":"2","author":"Karabulut","year":"2014","journal-title":"J. Comput. Commun."},{"key":"B32","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1515\/jpm-2017-0035","article-title":"Validation of a new algorithm for the short-term variation of the fetal heart rate: An antepartum prospective study","volume":"46","author":"Kouskouti","year":"2018","journal-title":"J. Perinat. Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/tit.1976.1055501","article-title":"On the complexity of finite sequences","volume":"22","author":"Lempel","year":"1976","journal-title":"IEEE Trans. Inf. Theory"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1109\/jiot.2018.2845128","article-title":"Automatic classification of fetal heart rate based on convolutional neural network","volume":"6","author":"Li","year":"2018","journal-title":"IEEE Internet Things J."},{"key":"B35","first-page":"235","article-title":"Automatic evaluation of fetal heart rate based on deep learning","author":"Liang","year":"2021"},{"key":"B36","doi-asserted-by":"publisher","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":"B37","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1111\/j.1542-474x.1996.tb00275.x","article-title":"Heart rate variability: Standards of measurement, physiological interpretation, and clinical use: Task force of the European society of cardiology and the north American society for pacing and electrophysiology","volume":"1","author":"Malik","year":"1996","journal-title":"Ann. Noninvasive Electrocardiol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1007\/s11227-018-2570-8","article-title":"Nonlinear characterization and complexity analysis of cardiotocographic examinations using entropy measures","volume":"76","author":"Marques","year":"2020","journal-title":"J. Supercomput."},{"key":"B39","first-page":"6","volume-title":"Intrapartum management of the fetal heart rate tracing","author":"Miller","year":"2021"},{"key":"B40","doi-asserted-by":"publisher","first-page":"3255296","DOI":"10.1155\/2022\/3255296","article-title":"The effects of in utero fetal hypoxia and creatine treatment on mitochondrial function in the late gestation fetal sheep brain","volume":"2022","author":"Muccini","year":"2022","journal-title":"Oxid. Med. Cell. Longev."},{"key":"B41","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.bpobgyn.2015.02.009","article-title":"Computer analysis of foetal monitoring signals","volume":"30","author":"Nunes","year":"2016","journal-title":"Best. Pract. Res. Clin. Obstet. Gynaecol."},{"key":"B42","doi-asserted-by":"publisher","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":"B43","first-page":"5866","article-title":"Deep learning for continuous electronic fetal monitoring in labor","author":"Petrozziello","year":"2018"},{"key":"B44","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1063\/1.166092","article-title":"Approximate entropy (apen) as a complexity measure","volume":"5","author":"Pincus","year":"1995","journal-title":"Chaos"},{"key":"B45","doi-asserted-by":"publisher","first-page":"6136","DOI":"10.3390\/s21186136","article-title":"A comprehensive review of techniques for processing and analyzing fetal heart rate signals","volume":"21","author":"Ponsiglione","year":"2021","journal-title":"Sensors"},{"key":"B46","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/S0076-6879(04)84011-4","article-title":"Sample entropy","volume":"384","author":"Richman","year":"2004","journal-title":"Methods Enzymol."},{"key":"B47","first-page":"2606","article-title":"Ctg analyzer: A graphical user interface for cardiotocography","author":"Sbrollini","year":"2017"},{"key":"B48","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.ajog.2019.10.106","article-title":"Scientific pathophysiology of intrapartum fetal hypoxemia and cardiotocography pattern recognition\u2013realignment is a basic prerequisite","volume":"222","author":"Sholapurkar","year":"2020","journal-title":"Am. J. Obstet. Gynecol."},{"key":"B49","doi-asserted-by":"publisher","first-page":"60","DOI":"10.2174\/1573404816999200821162312","article-title":"Fetal distress classification with deep convolutional neural network","volume":"17","author":"Singh","year":"2021","journal-title":"Curr. Women\u2019s Health Rev."},{"key":"B50","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.bspc.2011.06.008","article-title":"Using nonlinear features for fetal heart rate classification","volume":"7","author":"Spilka","year":"2012","journal-title":"Biomed. Signal Process. Control"},{"key":"B51","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/JBHI.2016.2546312","article-title":"Sparse support vector machine for intrapartum fetal heart rate classification","volume":"21","author":"Spilka","year":"2016","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B52","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.procs.2020.02.248","article-title":"Classification of the cardiotocogram data for anticipation of fetal risks using bagging ensemble classifier","volume":"168","author":"Subasi","year":"2020","journal-title":"Procedia Comput. Sci."},{"key":"B53","doi-asserted-by":"publisher","first-page":"8597606","DOI":"10.1155\/2019\/8597606","article-title":"Dmcnn: A deep multiscale convolutional neural network model for medical image segmentation","volume":"2019","author":"Teng","year":"2019","journal-title":"J. Healthc. Eng."},{"key":"B54","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1007\/978-3-030-24322-7_10","article-title":"Feature extraction of cardiotocography signal","volume-title":"Advances in decision sciences, image processing, security and computer vision","author":"Usha Sri","year":"2020"},{"key":"B55","doi-asserted-by":"publisher","first-page":"104466","DOI":"10.1016\/j.compbiomed.2021.104466","article-title":"Corrigendum to \"Cardiotocography signal abnormality classification using time-frequency features and ensemble cost-sensitive SVM classifier\" [Comput. Biol. Med. 130 (2021) 104218]","volume":"130","author":"Zeng","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"B56","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1186\/s12911-019-1007-5","article-title":"Deepfhr: Intelligent prediction of fetal acidemia using fetal heart rate signals based on convolutional neural network","volume":"19","author":"Zhao","year":"","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"B57","doi-asserted-by":"publisher","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":"","journal-title":"Front. Physiol."},{"key":"B58","doi-asserted-by":"publisher","first-page":"E223","DOI":"10.3390\/jcm7080223","article-title":"A comprehensive feature analysis of the fetal heart rate signal for the intelligent assessment of fetal state","volume":"7","author":"Zhao","year":"2018","journal-title":"J. Clin. Med."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2022.969052\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T06:54:23Z","timestamp":1669791263000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2022.969052\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":58,"alternative-id":["10.3389\/fphys.2022.969052"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2022.969052","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"article-number":"969052"}}