[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121389-en":3,"doc-seo-121389-105":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":20,"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},121389,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",7,"Healthcare","Predicting Fetal Weight Disorders in Diabetic Pregnancies - an explainable Machine Learning approach","Pregnancy monitoring is essential to reduce complications, especially in pregnancies affected by diabetes mellitus, which increases risk for both mother and fetus. This work analyzes how maternal history and computerized cardiotocography (cCTG) features derived from fetal heart rate (FHR) support classification of fetal weight categories: Small for Gestational Age (SGA), Normal for Gestational Age (NGA), and Large for Gestational Age (LGA). Logistic Regression and MLP models are evaluated, with SHAP-based explanations identifying key contributors and interaction effects, highlighting the importance of cCTG signal parameters alongside maternal variables to improve clinical decision-making.","Predicting Fetal Weight Disorders in Diabetic Pregnancies: an explainable Machine Learning approach  \nTesi di Laurea Magistrale in  \nBiomedical Engineering-Ingegneria biomedica  \nAuthor: Elena Novelli  \nStudent ID: 103301  \nAdvisor: Prof. Maria Gabriella Signorini  \nCo-advisors: Giulio Steyde  \nAcademic Year: 2023-24  \ni  \nAbstract  \nDuring pregnancy, careful monitoring is crucial to prevent complications, with particular attention to diabetes mellitus, which increases the danger of issues for both the mother and the fetus. The most commonly employed examination in clinical practice during pregnancy is Cardiotocography (CTG) and this study focuses on the impact of maternal history and parameters derived from fetal heart rate (FHR) extracted with computerized CTG (cCTG) on the classification of fetal weight categories, particularly Small for Gestational Age (SGA), Normal for Gestational Age (NGA), and Large for Gestational Age (LGA) . Weight pathologies during fetal development are indeed among the complications most closely linked to diabetes. Machine learning classifiers were trained using maternal clinical features and FHR signal parameters obtained from cCTG systems. Logistic Regression models and Multilayer Perceptron (MLP) models were employed to predict weight categories. The first one achieves a balanced accuracy of 54 .7%, while the second one reaches 52 .6% in three class classification. Both results are increased if a majority voting is performed, suggesting that a larger number of records can enhance the accuracy of the prediction. For interpreting the results, SHapley Additive exPlanations was used, a method for explaining machine learning models that employs coalition game theory and Shapley values to interpret the predictions of such models, offering insights into both feature importance and interaction effects. The interpretation of results indicates that maternal history variables play a significant role, as it was known in clinical practice, in predicting weight categories. However, this study highlights how the contribution of parameters from cCTG, in particular the complexity index of Lempel-Ziv, the number of acceleration of the signal, the multiscale entropy and the percentage of activity segments, is also fundamental compared to maternal variables. Some variables have shown a different or less significant impact than expected by previous studies, underscoring that parameters distinguishing between healthy and diseased groups might not equally differentiate within a solely pathological group. The study highlighted so the importance of combination of maternal history and fetal signal parameters in predicting fetal weight categories, aiming to enhance fetal well-being monitoring and clinical decision-making in pregnancies compicated by diabetes mellitus.  \nii | Abstract  \nKeywords: computerized cardiotocography, diabetes, pregnancy, fetal weight, machine learning, explainability  \niii  \nAbstract in lingua italiana  \nDurante la gravidanza, un monitoraggio attento è cruciale per prevenire complicazioni, con particolare attenzione al diabete mellito, che aumenta il rischio di problemi sia per la madre che per il feto. L’esame più comunemente impiegato nella pratica clinica durante la gravidanza è la cardiotocografia (CTG) e questo studio si concentra sull’impatto dellastoria materna e dei parametri derivati dalla frequenza cardiaca fetale (FHR) estrattacon la CTG computerizzata (cCTG) sulla classificazione delle categorie di peso fetale, in particolare Piccolo per l’età gestazionale (PEG), Normale per l’età gestazionale (NEG) e Grande per l’età gestazionale (GEG) . Le patologie legate al peso durante lo sviluppo fetalesono infatti tra le complicazioni più strettamente legate al diabete. Classificatori di apprendimento automatico sono stati addestrati utilizzando caratteristiche cliniche maternee parametri del segnale FHR ottenuti dai sistemi cCTG. Sono stati impiegati modelli di regressione logistica e modelli ","cbCaif9tzBKKccNr","https://ap.wps.com/l/cbCaif9tzBKKccNr","pdf",4644097,1,106,"English","en",105,"# Contents\n## Introduction","[{\"question\":\"Which fetal weight categories are targeted in this study?\",\"answer\":\"The study classifies fetal weight into three categories: Small for Gestational Age (SGA), Normal for Gestational Age (NGA), and Large for Gestational Age (LGA).\"},{\"question\":\"How are the prediction models trained and what algorithms are used?\",\"answer\":\"Models are trained using maternal clinical features and parameters extracted from fetal heart rate signals obtained via computerized CTG. Logistic Regression and Multilayer Perceptron (MLP) are used for three-class prediction.\"},{\"question\":\"How does the study explain model predictions?\",\"answer\":\"SHapley Additive exPlanations (SHAP) is used to interpret predictions by estimating feature importance and interaction effects through coalition game theory and Shapley values.\"}]","Predicting Fetal Weight Disorders in Diabetic Pregnancies - an explainable Machine Learning approach | PDF",1785735433,267,{"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},"predicting-fetal-weight-disorders-in-diabetic-pregnancies-an-explainable-machine-learning-approach","",{"@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/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-fetal-weight-disorders-in-diabetic-pregnancies-an-explainable-machine-learning-approach/121389/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Which fetal weight categories are targeted in this study?","Question",{"text":75,"@type":76},"The study classifies fetal weight into three categories: Small for Gestational Age (SGA), Normal for Gestational Age (NGA), and Large for Gestational Age (LGA).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are the prediction models trained and what algorithms are used?",{"text":80,"@type":76},"Models are trained using maternal clinical features and parameters extracted from fetal heart rate signals obtained via computerized CTG. Logistic Regression and Multilayer Perceptron (MLP) are used for three-class prediction.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study explain model predictions?",{"text":84,"@type":76},"SHapley Additive exPlanations (SHAP) is used to interpret predictions by estimating feature importance and interaction effects through coalition game theory and Shapley values.","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},[93,97,101,105,110,115,118,123,128,131,135],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",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"]