[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119007-en":3,"doc-seo-119007-105":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},119007,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Deep Learning for Electronic Health Records - Risk Prediction, Explainability, and Uncertainty","Deep learning models are developed for electronic health records to improve risk prediction while addressing a persistent clinical gap: existing models often lack adequate accuracy, reliability, and interpretability. The thesis proposes approaches spanning risk prediction with minimal processed EHR inputs, medical explainability through association and counterfactual reasoning, and uncertainty estimation via probabilistic modelling. Experiments on a representative UK EHR dataset show stronger performance, clinically useful explanations for risk factors, counterfactual insights for intervention scenarios, and uncertainty ranges that support confidence and decision quality.","Deep Learning for Electronic Health Records:  \nRisk Prediction, Explainability, and Uncertainty  \nYikuan Li  \nSt Cross College, University of Oxford  \nA thesis submitted for the degree of  \nDoctor of Philosophy  \nMichaelmas Term 2022  \nSupervised by:  \nProfessor Kazem Rahimi  \nProfessor Thomas Lukasiewicz  \nDoctor Mohammadhossein Mamouei  \nTo my wife and my parents for their enormous love and support.  \nI hereby declare that except where specific reference is made to the work of others, the contents ofthis dissertation are original and have not been submitted in whole or in part for consideration for any other degree or qualification in this, or any other university. This dissertation is my own work and contains nothing which is the outcome of work done in collaboration with others, except as specified in the text. This dissertation contains approximately 46,000 words including appendices, footnotes, tables, and equations.  \nYikuan Li  \nSeptember 2022  \nBackground: Risk models are essential for care planning and disease prevention. The unsatisfactory performance of the established clinical models has raised broad awareness and concerns. An accurate, explainable, and reliable risk model is highly beneficial but remains a challenge.  \nObjective: This thesis aims to develop deep learning models that can make more accurate risk predictions with the provision of uncertainty estimation and the ability to provide medical explanations using a large and representative electronic health records (EHR) dataset.  \nMethods: We investigated three directions in this thesis: risk prediction, explainability, and uncertainty estimation. For risk prediction, we investigated deep learning tools that can incorporate the minimal processed EHR for modelling and comprehensively compared them with the established machine learning and clinical models. Additionally, the post-hoc explanations were applied to deep learning models for medical information retrieval, and we specifically looked into explanations in risk association and counterfactual reasoning. Uncertainty estimation was qualitatively investigated using probabilistic modelling techniques. Our analyses relied on Clinical Practice Research Datalink, which contains anonymised EHR collected from primary care, secondary care, and death registration and is representative of the UK population.  \nResults: We introduced a deep learning model, named BEHRT, that can incorporate minimal processed EHR for risk prediction. Without expert engagement, it learned meaningful representations that can automatically cluster highly correlated diseases. Compared to the established machine learning and clinical models that relied on expertselected predictors, our proposed deep learning model showed superior performance on a wide range of risk prediction tasks and highlighted the necessity of recalibration when applying a risk model to a population with severe prior distribution shifts , and the importance of regular model updating to preserve the model’s discrimination performance under temporal data shifts.  \nAdditionally, we showed that the deep learning model explanation is an excellent tool for discovering risk factors. By explaining the deep learning model, we not only identified factors that were highly consistent with the established evidence but also those that have not been considered in expert-driven studies. Furthermore, the deep learning model also captured the interplay between risk and treated risk and the differential association of medications across different years, which would be difficult if the temporal context was not included in the modelling. Besides the explanations in terms of association, we introduced a framework that can achieve accurate risk prediction, while enabling counterfactual reasoning under hypothetical interventions. This offers counterfactual explanations that could inform clinicians for selection of those who will benefit the most. We demonstrated the benefit of the proposed fr","cbCais9Og2JzLBaN","https://ap.wps.com/l/cbCais9Og2JzLBaN","pdf",6065298,1,200,"English","en",105,"# Background\n# Objective\n# Methods\n## Risk prediction\n## Explainability and counterfactual reasoning\n## Uncertainty estimation\n# Results\n## BEHRT model performance and representation learning\n## Explanation as a tool for discovering risk factors\n## Counterfactual risk prediction framework\n## Probabilistic modelling for uncertainty ranges\n# Conclusions","[{\"question\":\"What is the main goal of the thesis on electronic health records?\",\"answer\":\"To develop deep learning models that produce more accurate risk predictions, provide uncertainty estimation, and generate medical explanations using a large, representative EHR dataset.\"},{\"question\":\"How does the thesis approach risk prediction with electronic health records?\",\"answer\":\"It introduces deep learning methods such as BEHRT that can incorporate minimally processed EHR and are compared against established machine learning and clinical models.\"},{\"question\":\"What role do explainability and uncertainty estimation play in the proposed methods?\",\"answer\":\"Explainability identifies risk factors and supports association and counterfactual reasoning under hypothetical interventions, while uncertainty estimation provides prediction confidence ranges to support clinical decision-making.\"}]","Deep Learning for Electronic Health Records - Risk Prediction, Explainability, and Uncertainty | PDF",1785721799,504,{"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},"deep-learning-for-electronic-health-records-risk-prediction-explainability-and-uncertainty","",{"@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/deep-learning-for-electronic-health-records-risk-prediction-explainability-and-uncertainty/119007/",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},"What is the main goal of the thesis on electronic health records?","Question",{"text":75,"@type":76},"To develop deep learning models that produce more accurate risk predictions, provide uncertainty estimation, and generate medical explanations using a large, representative EHR dataset.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis approach risk prediction with electronic health records?",{"text":80,"@type":76},"It introduces deep learning methods such as BEHRT that can incorporate minimally processed EHR and are compared against established machine learning and clinical models.",{"name":82,"@type":73,"acceptedAnswer":83},"What role do explainability and uncertainty estimation play in the proposed methods?",{"text":84,"@type":76},"Explainability identifies risk factors and supports association and counterfactual reasoning under hypothetical interventions, while uncertainty estimation provides prediction confidence ranges to support clinical decision-making.","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"]