[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290364-105":59,"doc-detail-290364-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","machine-learning-for-clinical-decision-support-under-limited-data","Machine Learning for Clinical Decision Support Under Limited Data","","Machine learning increasingly supports clinical decision-making across screening, diagnosis, risk stratification, prognosis, and treatment planning, yet limited and unbalanced datasets threaten overfitting, unstable feature associations, and poor generalization. The thesis studies clinical decision support under limited data via two case studies: ASD screening from children’s speech transcripts and BRCA1/2 variant interpretation in data-limited populations. It reports strong ASD classification performance with interpretable linguistic features and develops bias-aware BRCA modeling combined with population-specific anomaly detection. The work emphasizes feature engineering, interpretability, careful evaluation, and conservative evidence-based inference.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-for-clinical-decision-support-under-limited-data/290364/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-for-clinical-decision-support-under-limited-data/290364.png","ImageObject",300,407,{"name":92,"@type":93},"Eliana","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is limited clinical data a problem for machine learning models?","Question",{"text":113,"@type":114},"Limited and imbalanced datasets can cause overfitting, unstable feature associations, and weak generalization, reducing reliability for clinical tasks.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the thesis approach ASD screening with limited data?",{"text":118,"@type":114},"It extracts interpretable linguistic features from small TalkBank speech transcript datasets and trains models such as Logistic Regression, Random Forest, and TabNet for binary classification, achieving accuracy exceeding 86%.",{"name":120,"@type":111,"acceptedAnswer":121},"How is BRCA1/2 variant interpretation handled in data-limited populations?",{"text":122,"@type":114},"The thesis trains supervised global models using biologically grounded features while excluding population-frequency variables and externally trained meta-predictors to reduce bias, then combines global predictions with population-specific anomaly detection and applies conservative agreement-based support.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290364,1789641499,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","AMERICAN UNIVERSITY OF BEIRUT  \nMACHINE LEARNING FOR CLINICAL DECISION SUPPORT UNDER LIMITED DATA  \nby  \nZEIN MOHAMMAD CHEHABEDDINE  \nA thesis  \nsubmitted in partial fulfillment of the requirements for the degree of Master of Science  \nto the Department of Computer Science  \nof the Faculty of Arts and Sciences  \nat the American University of Beirut  \nBeirut, Lebanon  \nApril 2026  \nAMERICAN UNIVERSITY OF BEIRUT  \nMACHINE LEARNING FOR CLINICAL DECISION SUPPORT UNDER LIMITED DATA  \nby  \nZEIN MOHAMMAD CHEHABEDDINE  \nApproved by:  \n\n| Dr. Rida Assaf, Assistant Professor Department of Computer Science | Advisor |\n| --- | --- |\n| Dr. Haidar Safa, Professor\u003Cbr>Department of Computer Science | Member of Committee |\n\nDr. Shady Elbassuoni, Associate Professor Member of Committee  \nDepartment of Computer Science  \nDate of thesis defense: April 27, 2026  \nAcknowledgments  \nI would like to express my sincere gratitude to my advisor, Dr. Rida Assaf, for his guidance, support, and valuable feedback throughout this work. I also thank the clinicians and collaborators who contributed to this study, as well as my family for their encouragement and support during the completion of this thesis.  \nAbstract of the Thesis of  \nZein Mohammad Chehabeddine for  Master of Science  \nMajor: Computer Science  \nTitle: Machine Learning for Clinical Decision Support Under Limited Data  \nMachine learning is increasingly being used to support clinical decision-making in tasks such as screening, diagnosis, risk stratification, prognosis, and treatment planning. However, many clinical problems do not have access to large, balanced, and representative datasets, making models more vulnerable to overfitting, unstable feature associations, and poor generalization. This thesis investigates machine learning for clinical decision support under limited data through two case studies: Autism Spectrum Disorder (ASD) screening using children’s speech transcripts, and BRCA1/2 variant interpretation in data-limited populations. In the first study, linguistic features extracted from small public TalkBank transcript datasets, including Mean Length of Utterance, Mean Length of Turn Ratio, part-of-speech patterns, and demographic variables, were used to train Logistic Regression, Random Forest, and TabNet models for ASD screening. The models achieved strong performance in binary classification tasks, with accuracy exceeding 86%, and feature analysis showed that a compact set of interpretable linguistic features retained meaningful predictive signal. In the second study, supervised models were trained on expert-curated global BRCA1/2 variant datasets using biologically grounded features while excluding population-frequency variables and externally trained meta-predictors to reduce bias and circularity. The best-performing global model was combined with population-specific anomaly detection in a Lebanese cohort, and a conservative agreement rule was used to support classification only when the global supervised model and local anomaly detector agreed, while retaining uncertainty when predictions diverged. Together, these studies show that limited data should not prevent the use of machine learning in clinically important problems, but it should shape how models are designed, evaluated, and interpreted. Across both case studies, the thesis emphasizes clinically meaningful feature engineering, interpretable model behavior, and cautious decision support, showing that machine learning can provide useful clinical support under limited data when its outputs are treated as evidence to guide, rather than replace, clinical interpretation.  \nTable of Contents  \nACKNOWLEDGMENTS 1  \nABSTRACT 2  \nABBREVIATIONS 7  \n1 Introduction 8  \n1.1 Autism Spectrum Disorder Screening .................... 8  \n1.1.1 Background .............................. 8  \n1.1.2 Machine Learning for Autism Spectrum Disorder Screening .... 9  \n1.2 BRCA1/2 Variant Interpretation ...................... 10  \n1.2.1 Background ..","cbCairY0VMaMRTg0","https://ap.wps.com/l/cbCairY0VMaMRTg0","pdf",2333607,49,"English","# Introduction\n## Autism Spectrum Disorder Screening\n## BRCA1/2 Variant Interpretation\n# Screening Autism Spectrum Disorder in Children Using Machine Learning on Speech Transcripts\n## Materials and Methods\n## Results\n# A Framework for BRCA1/2 Variant Interpretation in Data-Limited Populations\n## Materials and Methods\n## Results\n# Discussion\n# A Supplementary Materials\n# Bibliography","[{\"question\":\"Why is limited clinical data a problem for machine learning models?\",\"answer\":\"Limited and imbalanced datasets can cause overfitting, unstable feature associations, and weak generalization, reducing reliability for clinical tasks.\"},{\"question\":\"How does the thesis approach ASD screening with limited data?\",\"answer\":\"It extracts interpretable linguistic features from small TalkBank speech transcript datasets and trains models such as Logistic Regression, Random Forest, and TabNet for binary classification, achieving accuracy exceeding 86%.\"},{\"question\":\"How is BRCA1/2 variant interpretation handled in data-limited populations?\",\"answer\":\"The thesis trains supervised global models using biologically grounded features while excluding population-frequency variables and externally trained meta-predictors to reduce bias, then combines global predictions with population-specific anomaly detection and applies conservative agreement-based support.\"}]","Machine Learning for Clinical Decision Support Under Limited Data | PDF",123]