[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124784-en":3,"doc-seo-124784-105":30,"detail-sidebar-cat-0-en-105":95},{"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},124784,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","On Critical Care Data and Machine Learning Loss Function Landscapes - Doctoral Dissertation","Intensive care patients face constant risk, making timely discharge decisions crucial because premature discharge increases readmission and mortality. This dissertation trains neural network classifiers to predict ICU mortality and uses basin-hopping methods to map loss-function landscapes and locate local minima, evaluating performance via AUC. It compares two clinical databases, MIMIC III and Amsterdam UMC db, finding generally stronger results for Amsterdam UMC db and identifying time-window sensitivity with a notable Respiration Rate exception. It extends the analysis using clinically motivated worst-value inputs inspired by APACHE II, synthetic spiral tests, and alternative loss landscapes such as AUC-like and SAM, concluding limited practical benefit despite deeper insight into model geometry.","Yusuf Hamied Department of Chemistry University of Cambridge  \nOn Critical Care Data and Machine Learning Loss Function  \nLandscapes  \nThis dissertation is submitted to the University of Cambridge for the degree  \nDoctor of Philosophy.  \nConor Thomas Cafolla  \nSelwyn College  \nSeptember 2023  \nSupervised by Professor David J. Wales FRS  \nDeclaration  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the Preface and specified in the text. I further state that no substantial part of my thesis has already been submitted, or, is being concurrently submitted for any such degree, diploma or other qualification atthe University of Cambridge or any other University or similar institution except as declared in the Preface and specified in the text. It does not exceed the prescribed word limit for the Degree Committee of Physics and Chemistry, which is 60,000 words.  \nConor Cafolla  \nSeptember 2023  \nSummary  \nOn Critical Care Data and Machine Learning Loss Function Landscapes  \nConor Thomas Cafolla  \nIntensive Care Units (ICUs) are constantly under strain, with many vulnerable people needing urgent critical care. Often doctors do not have the capacity to accommodate everyone, and so it is important that patients are discharged when it is safe to do so. However, discharging a patient at the wrong time may result in the patient being readmitted or simply not surviving; both of these cases are highly undesirable. Therefore, it is useful for there to be an understanding of what factors contribute most to the mortality rate of patients in intensive care units.  \nIn the present work, machine learning models are trained to predict the mortality of a given patient with certain measurements. Neural networks with one hidden layer and two outcomes (alive or deceased) are used in these models, and local minima of the neural network loss functions are found using basin-hopping methods implemented with the open source software GMIN. In this way, the landscape of the loss function defined by the neural network model can be explored. Area Under the Curve (AUC) values were used to evaluate these models.  \nTwo databases, MIMIC III and Amsterdam UMC db, are compared. There are many possible calculations to perform, and initially time-series for single variablesand pairs of variables are used as inputs to the neural network. From MIMIC III, Glasgow Coma Scale (GCS) and Blood Urea Nitrogen (BUN) perform well, with AUCs just below 0 .8 on their own, and an AUC above 0 .8 together. From Amsterdam UMC db, Blood Pressure (BP) measurements perform well, with AUCs around 0 .8. Generally the data from Amsterdam UMC db appears to outperform MIMIC III. The effect of using a model trained on one time window and evaluated on different time windows is also investigated, and we find that the AUC value decreases  \nbut not substantially for most clinical variables, suggesting the most recent data is the most useful for mortality prediction. There is a notable exception in Respiration Rate, where it is found that data from earlier times may actually provide more prognostic value than the most recent measurements. A permutational shuffling analysis is performed, which reveals patterns in the ways the data is organised, and sheds light on some innate properties of the data.  \nThe data from the two ICU databases are then applied to another model, where inputs to the neural network are the worst values of a set of pre-chosen clinical variables, inspired by a score used elsewhere in the medical prognosis picture (APACHE II) . The AUCs obtained in this way are generally better than for the time-series data above, with AUCs reaching just under 0.8 for MIMIC III and 0.85 for Amsterdam UMC db.  \nSynthetic spiral data is created to test some new machine learning methods, including an ensemble-like method where minima from the loss function landscape are combined in a process called Machine Learnin","cbCaimP5FmHmIGR6","https://ap.wps.com/l/cbCaimP5FmHmIGR6","pdf",22016485,1,144,"English","en",105,"# Summary\n## Predicting ICU mortality with loss-function landscapes\n## Database comparison: MIMIC III vs Amsterdam UMC db\n## Time-window effects and data organization\n## APACHE II-inspired worst-value modelling\n## Synthetic tests and MLSUP superposition method\n## Alternative loss landscapes and practical conclusions","[{\"question\":\"What problem does the dissertation address in intensive care units?\",\"answer\":\"It investigates which factors most strongly influence mortality and how machine learning can support safer discharge timing decisions in ICUs.\"},{\"question\":\"How are neural network loss-function landscapes explored in the work?\",\"answer\":\"Neural networks with one hidden layer and two outcomes (alive or deceased) are trained, and basin-hopping with GMIN is used to find local minima and explore the loss landscape geometry.\"},{\"question\":\"What datasets are compared, and what overall performance trend is reported?\",\"answer\":\"The work compares MIMIC III and Amsterdam UMC db; the data from Amsterdam UMC db generally appears to outperform MIMIC III for mortality prediction.\"},{\"question\":\"Does using newer loss functions like SAM or an AUC-like loss improve practical performance?\",\"answer\":\"Although AUC values from synthetic and real data are comparable to cross-entropy, the study concludes the new landscapes offer limited practical improvement and mainly provide insight into model nature.\"}]","On Critical Care Data and Machine Learning Loss Function Landscapes - Doctoral Dissertation | PDF",1785894639,363,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"on-critical-care-data-and-machine-learning-loss-function-landscapes-doctoral-dissertation","",{"@graph":36,"@context":89},[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/on-critical-care-data-and-machine-learning-loss-function-landscapes-doctoral-dissertation/124784/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the dissertation address in intensive care units?","Question",{"text":75,"@type":76},"It investigates which factors most strongly influence mortality and how machine learning can support safer discharge timing decisions in ICUs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are neural network loss-function landscapes explored in the work?",{"text":80,"@type":76},"Neural networks with one hidden layer and two outcomes (alive or deceased) are trained, and basin-hopping with GMIN is used to find local minima and explore the loss landscape geometry.",{"name":82,"@type":73,"acceptedAnswer":83},"What datasets are compared, and what overall performance trend is reported?",{"text":84,"@type":76},"The work compares MIMIC III and Amsterdam UMC db; the data from Amsterdam UMC db generally appears to outperform MIMIC III for mortality prediction.",{"name":86,"@type":73,"acceptedAnswer":87},"Does using newer loss functions like SAM or an AUC-like loss improve practical performance?",{"text":88,"@type":76},"Although AUC values from synthetic and real data are comparable to cross-entropy, the study concludes the new landscapes offer limited practical improvement and mainly provide insight into model nature.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]