[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126220-en":3,"doc-seo-126220-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126220,549768702563,"Sage","https://ap-avatar.wpscdn.com/avatar/8000c4aa63b76e948b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786536092046926083",8,"Research & Report","Multimodal Machine Learning for Prognostic Modelling in Idiopathic Pulmonary Fibrosis","Idiopathic Pulmonary Fibrosis (IPF) is a severe lung disease with rapid progression and high mortality, while patient prognosis varies substantially. This dissertation applies machine learning to improve prognosis prediction by combining clinical data and volumetric imaging. It addresses missing patient-record attributes using latent variable models for accurate imputation, then estimates mortality risk with Cox proportional hazards. To overcome computational limitations with volumetric data, it introduces a scalable memory bank training approach and proposes CenTime, which better exploits right-censored data and directly predicts time-to-mortality. Experiments on a comprehensive IPF dataset show improved prediction accuracy, supporting personalized clinical decision-making.","MULTIMODAL MACHINE LEARNING FOR PROGNOSTIC MODELLING INI DIOPATHIC PULMONARY FIBROSIS  \nAhmed H. Shahin  \nA dissertation submitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \nof  \nUniversity College London.  \nDepartment of Computer Science  \nUniversity College London  \nApril 21, 2025  \n2  \nI, Ahmed H. Shahin, confirm that the work presented in this thesis is my own. Where information has been derived from other sources, I confirm that this has been indicated in the work.  \nAbstract  \nIdiopathic Pulmonary Fibrosis (IPF) is a severe lung disease characterized by rapid progression and high mortality, with a highly variable prognosis between patients. This thesis leverages machine learning to enhance prognosis prediction in IPF by analysing clinical data and volumetric imaging. We first address the challenge of missing data in patient records by applying latent variable models to accurately impute missing attributes based on the available information in each record. Next, we use the Cox proportional hazards model to predict mortality risk from patient data. As a ranking objective, the Cox model requires many samples per training iteration, which is computationally expensive and often infeasible for volumetric data. We introduce a scalable memory bank-based training approach for efficient model training with volumetric data. Recognizing the inherent constraints of the Cox model, we also propose a new method, CenTime, which better utilizes censored data and directly predicts the time-to-mortality. CenTime relaxes the assumptions of the Cox model, provides a more precise estimation of patient outcomes, and leverages right-censored data more effectively. Our methods are validated on a comprehensive dataset of IPF patients, demonstrating significant improvements in prediction accuracy over existing approaches. This work can advance personalized prognosis in IPF, aiding clinicians in developing tailored treatment strategies.  \nImpact Statement  \nThis thesis advances prognosis prediction in Idiopathic Pulmonary Fibrosis (IPF) using machine learning techniques. IPF is a severe lung disease with a median survival of 2–3 years post-diagnosis and a highly variable prognosis among patients. This work tackles key challenges in IPF prognosis, including missing data imputation, computationally efficient training with high-resolution volumetric imaging, and precise time-to-death prediction. By improving mortality risk assessment, these models enable clinicians to identify high-risk patients and develop personalized treatment strategies. Additionally, this research facilitates the discovery of novel imaging biomarkers, paving the way for improved disease understanding and targeted therapies.  \nBeyond IPF, the presented methods extend to broader prognosis prediction tasks, including interstitial lung diseases, cancer, and chronic conditions. The CenTime model, in particular, enhances survival prediction by effectively leveraging censored data and providing more accurate time-to-event estimations. This work contributes to the broader field of machine learning for healthcare, advancing personalized medicine and data-driven clinical decision-making.  \nAcknowledgements  \n“Praise to Allah, who has guided us to this; and we would never have been guided if  \nAllah had not guided us”  \nQuran, Al-A’raf 43  \nI would like to sincerely thank my supervisor, David Barber, for his invaluable guidance, unwavering support, and continuous encouragement throughout my PhD journey. His technical expertise, mentorship, and belief in my abilities have been instrumental in shaping this thesis. Despite his demanding schedule, David always made time for discussions, constructive criticism, and motivational advice. His mentorship has fundamentally changed my approach to research, and I am truly fortunate to have had him as my supervisor.  \nI am deeply grateful to my secondary supervisors, Daniel C. Alexander and Joseph Jacob, whose v","cbCaigTFLNyYT4Xx","https://ap.wps.com/l/cbCaigTFLNyYT4Xx","pdf",13199988,9,1,156,"English","en",105,"# Abstract\n# Impact Statement\n# Acknowledgements","[{\"question\":\"How does the thesis handle missing data in IPF patient records?\",\"answer\":\"It uses latent variable models to impute missing attributes based on the information available in each patient record.\"},{\"question\":\"What prediction tasks are used to estimate patient outcomes?\",\"answer\":\"The work predicts mortality risk using the Cox proportional hazards model and also proposes CenTime to directly estimate time-to-mortality from censored data.\"},{\"question\":\"Why is Cox training challenging for volumetric data, and what solution is proposed?\",\"answer\":\"The Cox ranking objective needs many samples per training iteration, which becomes computationally expensive for volumetric imaging. The thesis introduces a scalable memory bank-based training approach to make training efficient.\"}]","Multimodal Machine Learning for Prognostic Modelling in Idiopathic Pulmonary Fibrosis | PDF",1785903881,393,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"multimodal-machine-learning-for-prognostic-modelling-in-idiopathic-pulmonary-fibrosis","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/multimodal-machine-learning-for-prognostic-modelling-in-idiopathic-pulmonary-fibrosis/126220/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"How does the thesis handle missing data in IPF patient records?","Question",{"text":77,"@type":78},"It uses latent variable models to impute missing attributes based on the information available in each patient record.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What prediction tasks are used to estimate patient outcomes?",{"text":82,"@type":78},"The work predicts mortality risk using the Cox proportional hazards model and also proposes CenTime to directly estimate time-to-mortality from censored data.",{"name":84,"@type":75,"acceptedAnswer":85},"Why is Cox training challenging for volumetric data, and what solution is proposed?",{"text":86,"@type":78},"The Cox ranking objective needs many samples per training iteration, which becomes computationally expensive for volumetric imaging. The thesis introduces a scalable memory bank-based training approach to make training efficient.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,122,125,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":118,"doc_module":4,"doc_module_name":47,"category_name":119,"show_sort_weight":120,"slug":121},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":123,"slug":124},30,"research-report",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]