[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120394-en":3,"doc-seo-120394-105":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},120394,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Data-Efficient Machine Learning on Administrative Healthcare Records - Doctor of Philosophy Thesis","Large-scale administrative healthcare datasets available to the Australian Department of Health and Aged Care include Electronic Health Records and administrative claims, enabling more accurate prediction of patient journeys, better healthcare resource planning, and stronger evidence-based policy decisions. The work addresses complexity, sparsity, irregularity, and scale, which make conventional machine learning—especially deep learning—demand extensive labeled data and substantial computation. The thesis develops data-efficient methods for unsupervised, semi-supervised, supervised, and foundation-model prompt learning, improving efficiency through non-supervised paradigms, knowledge sharing, and efficient learning frameworks.","UNIVERSITY OF TECHNOLOGY SYDNEY Faculty of Engineering and Information Technology  \nData-Efficient Machine Learning on Administrative  \nHealthcare Records  \nby  \nYang (Alvin) Wang  \nTHESIS SUBMITTED  \nIN FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF  \nDoctor of Philosophy  \nAustralia  \nCertificate of Original Authorship  \nI, Yang (Alvin) Wang, declare that this thesis is submitted in fulfilment of the requirements for the award of Doctor of Philosophy, in the School of Computer Science, Faculty of Engineering and Information Technology at the University of Technology Sydney.  \nThis thesis is wholly my own work unless otherwise referenced or acknowledged. In addition, I certify that all information sources and literature used are indicated in the thesis.  \nThis document has not been submitted for qualifications at any other academic institution.  \nThis research is supported by the Australian Government Research Training Program.  \nSignature:  \nProduction Note:  \nSignature removed prior to publication.  \nDate: 12 Nov 2024  \n© Copyright 2024 Yang (Alvin) Wang  \nABSTRACT  \nData-Efficient Machine Learning on Administrative Healthcare Records  \nby  \nYang (Alvin) Wang  \nThe Australian Government Department of Health and Aged Care (DoHAC) has access to large-scale, complex healthcare data, including Electronic Health Records (EHRs) and administrative claims data. These comprehensive healthcare datasets hold immense potential for more accurately predicting patient journeys through the healthcare system, optimising healthcare resource planning, and guiding evidence-based policymaking in the government.  \nWhile having issues of complexity, sparsity, irregularity, and vast scale, healthcare data have been leveraged successfully by many existing machine learning models for various tasks in healthcare. However, these models, particularly deep learning ones, often require extensively labelled training data and substantial computational resources. Such requirements may be impractical or prohibitively expensive for real-world government use.  \nThis doctoral research underscores the necessity of developing data-efficient machine learning methods to facilitate the greater utilisation of deep learning models in government settings. It proposes an array of data-efficient strategies tailored for various machine learning scenarios in healthcare, including unsupervised, semi-supervised, supervised, and foundation model-based prompt learning. The focus of this research is to enhance data and resource efficiency in machine learning healthcare applications by employing non-supervised paradigms, knowledge-sharing techniques, and efficient learning frameworks.  \nSpecifically, the thesis first presents a visualisation-supported interactive deep metric learning approach to enhance labelling efficiency in cohort discovery for population  \nhealthcare policymaking. Subsequently, the thesis demonstrates a machine teachingbased framework, which empowers teacher agency in recommending samples with the highest learning gain, thereby reducing the labelling efforts of student agency. Lastly, building upon a foundation model-based new Artificial Intelligence service architecture, the thesis introduces a prompt learning-based solution to facilitate the efficient adaptation of the foundation model and well-labelled source tasks to the target tasks in healthcare applications, particularly in few-shot settings.  \nKey Words. Machine Learning for Healthcare; Data-Efficient Machine Learning; Nonsupervised Machine Learning; Knowledge Sharing; Interactive Deep Metric Learning; Machine Teaching; Prompt Learning  \nDissertation directed by Associate Professor Guodong Long (Principal Supervisor), Dr. Xueping Peng, and Distinguished Professor Chengqi Zhang  \nAustralian Artificial Intelligence Institute (AAII), Faculty of Engineering and IT (FEIT), University of Technology Sydney (UTS)  \nAcknowledgements  \nI am profoundly grateful to start my acknowledgments by extending heartf","cbCaicdyl81xJMQJ","https://ap.wps.com/l/cbCaicdyl81xJMQJ","pdf",943045,1,116,"English","en",105,"# Abstract\n# Background and Motivation\n## Healthcare data landscape\n## Challenges for existing models\n# Research Contributions\n## Data-efficient learning for healthcare scenarios\n## Interactive deep metric learning for cohort discovery\n## Machine teaching framework for labeling reduction\n## Prompt learning for efficient foundation model adaptation\n# Evaluation Focus and Expected Impact","[{\"question\":\"Why are data-efficient machine learning methods necessary for government healthcare use?\",\"answer\":\"Existing models, particularly deep learning, often require extensive labeled training data and substantial computational resources, which can be impractical or too costly for real-world government settings.\"},{\"question\":\"What types of healthcare data are targeted in the thesis?\",\"answer\":\"The thesis focuses on administrative healthcare datasets available to the Australian Department of Health and Aged Care, including Electronic Health Records (EHRs) and administrative claims data.\"},{\"question\":\"How does the thesis reduce labeling effort in cohort discovery?\",\"answer\":\"It presents a visualization-supported interactive deep metric learning approach designed to enhance labeling efficiency for cohort discovery in population healthcare policymaking.\"}]","Data-Efficient Machine Learning on Administrative Healthcare Records - Doctor of Philosophy Thesis | PDF",1785729815,292,{"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},"data-efficient-machine-learning-on-administrative-healthcare-records-doctor-of-philosophy-thesis","",{"@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/data-efficient-machine-learning-on-administrative-healthcare-records-doctor-of-philosophy-thesis/120394/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are data-efficient machine learning methods necessary for government healthcare use?","Question",{"text":75,"@type":76},"Existing models, particularly deep learning, often require extensive labeled training data and substantial computational resources, which can be impractical or too costly for real-world government settings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What types of healthcare data are targeted in the thesis?",{"text":80,"@type":76},"The thesis focuses on administrative healthcare datasets available to the Australian Department of Health and Aged Care, including Electronic Health Records (EHRs) and administrative claims data.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis reduce labeling effort in cohort discovery?",{"text":84,"@type":76},"It presents a visualization-supported interactive deep metric learning approach designed to enhance labeling efficiency for cohort discovery in population healthcare policymaking.","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"]