[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123459-en":3,"doc-seo-123459-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123459,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning for Detecting Fetal Hypoxia Using Cardiotocography and Pregnancy Risk Factors","Fetal hypoxia during labour reflects inadequate fetal oxygenation during active uterine contractions, and although it can be a compensatory physiologic response, some infants fail to adapt, leading to outcomes such as cerebral palsy, developmental disorders, and neonatal mortality. Cardiotocography (CTG) monitors fetal heart rate alongside uterine contractions to support clinical hypoxia risk detection. Existing ML approaches are limited by reliance on a single dataset, lack of external validation, inconsistent hypoxia surrogates, and minimal integration of pregnancy risk factors. This thesis develops and validates ML prediction models using CTG data and pregnancy risk factors, incorporating scoping review, cross-population comparison, Apgar-scored hypoxia definition, and multi-metric evaluation.","This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use:  \n• This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated.  \n• A copy can be downloaded for personal non-commercial research or study, without prior permission or charge.  \n• This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author.  \n• The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author.  \n• When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given.  \nMachine Learning for Detecting Fetal Hypoxia Using Cardiotocography and Pregnancy Risk Factors  \nFarah Francis  \nThe University of Edinburgh  \nPrimary Supervisor: Dr Rosemary Townsend  \nCo-Supervisors: Professor Saturnino Luz, Dr Honghan Wu and Professor Sarah Jane Stock  \nThesis submitted in fulfilment of the requirements  \nfor the research degree of PhD Precision Medicine  \nUniversity of Edinburgh  \n2025  \nAcknowledgement  \nI am dedicating this thesis to everyone affected by fetal hypoxia. As someone born with a low Apgar score, I am lucky not to experience any of its adverse effects and be able to pursue a PhD. I hope that this thesis can improve our understanding of fetal hypoxia during labour.  \nI would like to thank the opportunity to conduct and complete this PhD study, which had been a lifelong dream since I was a child. I thank the Medical Research Council for funding this study, which made this journey possible.  \nMany thanks to my supervisors, Dr. Townsend, Prof. Luz, Dr. Wu, and Dr. Stock, for their guidance throughout my research. Their trust in my abilities and autonomy have been pivotal in harnessing my skills, motivation, and exploring innovative approaches. Many thanks to Clevermed who provided meaningful collaboration in providing data for my research. I truly appreciate the internship opportunity to further understand the collection and storage of electronic health records in the United Kingdom.  \nI thank Dr. Alex Hunt for all his support both morally and emotionally throughout our PhD journey. Thank you, Jhonti Bird, for being on my side. Thank you to the members of Precision Medicine DTP and the Usher Institute for their support and encouragement.  \nTo the Atkins and Thom family, I truly appreciate your love and encouragements  \nAbstract  \nBackground  \nFetal hypoxia during labour is characterised by an insufficient oxygen supply in the womb during active uterine contractions. Although this condition represents a normal physiological compensatory response, certain infants are unable to adapt, resulting in severe consequences such as cerebral palsy, developmental disorders, and neonatal mortality. Cardiotocography (CTG) is a device that records fetal heart rate (FHR) and uterine contractions (UC), generating a graphical representation of these measurements. Clinicians utilise this noninvasive CTG to monitor alterations in FHR in response to UC, thereby identifying fetuses at risk of hypoxia during labour. However, human factors may compromise the quality and consistency of CTG interpretation. Previous research has indicated an increase in the caesarean section rate without corresponding improvement in the incidence of cerebral palsy. Machine learning (ML) has demonstrated the potential for detecting hypoxic fetuses using CTG data. Nonetheless, the majority of studies have relied on the same open-access dataset, and the absence of external validation and inconsistent hypoxia surrogate measures impedes clinical application. Moreover, although pregnancy risk factors can influence fetal hypoxia during labour, there is a paucity of studies employi","cbCaitNNJt61xDUP","https://ap.wps.com/l/cbCaitNNJt61xDUP","pdf",6818758,1,244,"English","en",105,"# Acknowledgement\n# Abstract\n## Background\n## Methods\n## Results","[{\"question\":\"为什么胎儿缺氧在产程中具有重要临床意义？\",\"answer\":\"胎儿缺氧发生在活跃性宫缩期间供氧不足的情况下。尽管可被视为生理补偿反应，但部分胎儿无法适应，可能引发严重后果，包括脑瘫、发育障碍和新生儿死亡。\"},{\"question\":\"本研究使用了哪些数据来构建机器学习预测模型？\",\"answer\":\"研究同时使用CTG数据以及妊娠风险因素。CTG层面对英国与捷克共和国数据进行对比，并进行探索性数据分析；妊娠风险因素层面基于美国妊娠健康记录建模并预测产程中的胎儿缺氧。\"},{\"question\":\"本研究如何定义并验证“缺氧”的标签，以及如何评估模型表现？\",\"answer\":\"论文采用Apgar评分作为缺氧的金标准。模型评估使用多种指标，包括误分类误差、AUROC、Precision-Recall曲线下面积、Brier score以及校准图。\"}]","Machine Learning for Detecting Fetal Hypoxia Using Cardiotocography and Pregnancy Risk Factors | PDF",1785816634,615,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-detecting-fetal-hypoxia-using-cardiotocography-and-pregnancy-risk-factors","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-detecting-fetal-hypoxia-using-cardiotocography-and-pregnancy-risk-factors/123459/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"为什么胎儿缺氧在产程中具有重要临床意义？","Question",{"text":75,"@type":76},"胎儿缺氧发生在活跃性宫缩期间供氧不足的情况下。尽管可被视为生理补偿反应，但部分胎儿无法适应，可能引发严重后果，包括脑瘫、发育障碍和新生儿死亡。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"本研究使用了哪些数据来构建机器学习预测模型？",{"text":80,"@type":76},"研究同时使用CTG数据以及妊娠风险因素。CTG层面对英国与捷克共和国数据进行对比，并进行探索性数据分析；妊娠风险因素层面基于美国妊娠健康记录建模并预测产程中的胎儿缺氧。",{"name":82,"@type":73,"acceptedAnswer":83},"本研究如何定义并验证“缺氧”的标签，以及如何评估模型表现？",{"text":84,"@type":76},"论文采用Apgar评分作为缺氧的金标准。模型评估使用多种指标，包括误分类误差、AUROC、Precision-Recall曲线下面积、Brier score以及校准图。","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]