[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127766-en":3,"doc-seo-127766-105":31,"detail-sidebar-cat-0-en-105":92},{"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},127766,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","The application of multi-modal machine learning to identify new biomarkers for neurological diseases - Doctor of Philosophy thesis","The brain’s complexity drives ongoing efforts to use high-dimensional data to clarify neurological diseases, including neurodegenerative disorders, psychiatric conditions, and nervous system disorders that impose a growing health burden as populations age. Despite progress, mechanistic understanding remains limited across several areas of neurology. Advances in high-throughput omics, wearable data, imaging, mass spectrometry, and electronic health records enable large, multi-modal datasets. This thesis introduces IDEARS for ML-driven disease risk scoring and feature ranking, and ReTimeML for automated retention time regression in LC-MS/MS, enabling biomarker association discovery and analysis for multiple conditions.","The application of multi-modal machine learning to identify new biomarkers for neurological diseases in large biomedical datasets  \nBy Michael Allwright  \nBrain and Mind Centre and School of Medical Sciences,  \nFaculty of Medicine and Health, The University of Sydney, Camperdown NSW 2050, Australia  \nA thesis submitted to fulfil requirements for the degree of Doctor of Philosophy  \nAward Year: 2024  \nAcknowledgments  \nI would like to thank the following people who have made this possible: Dr Boris Guennewig for his inspiration, guidance, mentorship and friendship while being a supervisor to my PhD; Dr Paul Austin for his mentorship and detailed support in chapters two, three and four; Assoc Professor Greg Sutherland for all of his support in chapters two and five; Dr Timothy Couttas for his detailed support and mentorship in Chapters six and seven. Professor Simon Lewis for his inspirational ideas and for collaborations in the earlier years of my PhD.  \nThe research reported in this thesis was supported by the award of a Research Training Program scholarship to the PhD Candidate.  \nAbstract  \nThe brain is considered the most complex structure on the planet. In recent years, neuroscientists have leveraged modern high-dimensional techniques and data to attempt to unravel its mysteries. Neurological Diseases (NDs) include both neurodegenerative diseases such as Alzheimer’s Disease (AD) and Parkinson’s Disease (PD), psychiatric conditions such as Schizophrenia (SCZ), and nervous system disorders such as multiple sclerosis (MS) and diabetic polyneuropathy (DPN) . These conditions pose a significant health burden, which is expected to increase with an aging population. Despite the technological advancements, our understanding of neurological diseases (NDs) remains limited, especially compared to other areas of medicine.  \nThe progress to date understanding NDs include the linking of the APOE e4 genotype to AD and the development of pharmacological interventions such as Leqembi and donanemab to target amyloid plaques. Significant strides in the treatment of MS include the application of monoclonal antibodies targeting plaques that form in the central nervous system (CNS) . Levodopa and its derivatives have succeeded in alleviating many PD symptoms, but not in altering the course of the disease. However, for psychiatric disorders such as schizophrenia (SCZ), both anti-psychotic treatments and other interventions have shown limited efficacy in treatment and the underlying patho-mechanisms remain poorly understood.  \nRecent advances in medical technology, including high-throughput-omics (which include genomics, transcriptomics, proteomics and lipidomics), wearable devices, medical imaging, mass spectrometry (MS) techniques and more sophisticated electronic health records (EHR) are revolutionising the collection of large volumes of high-resolution, personalised, and multi-modal medical data. This has resulted in a great increase in the depth and breadth of data available for analysis, offering the potential for higher powered studies to deepen our understanding of NDs. Initiatives such as the UK Biobank (UKB) have enabled this data to be collected for over 500k study participants.  \nML is a branch of artificial intelligence that focuses on developing algorithms and statistical models that enable computers to learn from and make predictions or decisions based on data. Unlike traditional programming, where explicit instructions are coded, ML systems improve their performance over time by identifying patterns and relationships in data. This technology is widely used in various fields, including healthcare, finance, and technology, to solve complex problems and automate tasks that would be difficult or impossible for humans to manage manually. The depth and breadth of data repositories such as the UKB make it well suited to machine learning (ML) techniques, which outperform traditional statistical methods when applied to such high dimensiona","cbCaitxJeVmGgG9P","https://ap.wps.com/l/cbCaitxJeVmGgG9P","pdf",12482733,2,1,269,"English","en",105,"# Abstract\n# Background and motivation\n## Neurological diseases and current limitations\n## Modern data sources and high-dimensional measurement\n# Machine learning approach\n## Learning from large biomedical datasets\n# IDEARS platform (Chapter 2)\n## Data pre-processing\n## XGBoost risk prediction\n## Game-theoretic feature ranking (tree-based SHAP)\n# ReTimeML (Chapter 6)\n## Regression for retention time automation in LC-MS/MS\n# Published manuscripts (Chapters 3–5)\n## Parkinson’s disease risk factors\n## Diabetic polyneuropathy risk factors\n## Alzheimer’s disease genetic risk factors","[{\"question\":\"What problem does the thesis address in neurological diseases?\",\"answer\":\"It addresses limited mechanistic understanding and the need for new biomarker discovery and risk factor identification across neurological diseases using large multi-modal biomedical datasets.\"},{\"question\":\"How does IDEARS support disease risk prediction and biomarker identification?\",\"answer\":\"IDEARS automates data pre-processing, uses an XGBoost gradient boosting model to predict disease risk, and applies a game-theoretic feature ranking method with tree-based SHAP to identify top associations among UK Biobank fields.\"},{\"question\":\"What is the purpose of ReTimeML in the thesis workflow?\",\"answer\":\"ReTimeML applies regression methods to automate expected retention times for ceramide and sphingomyelin profiles from LC-MS/MS chromatograms, enabling efficient determination of sphingolipid species concentrations.\"}]","The application of multi-modal machine learning to identify new biomarkers for neurological diseases - Doctor of Philosophy thesis | PDF",1785941486,678,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":29},"the-application-of-multi-modal-machine-learning-to-identify-new-biomarkers-for-neurological-diseases-doctor-of-philosophy-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/the-application-of-multi-modal-machine-learning-to-identify-new-biomarkers-for-neurological-diseases-doctor-of-philosophy-thesis/127766/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address in neurological diseases?","Question",{"text":76,"@type":77},"It addresses limited mechanistic understanding and the need for new biomarker discovery and risk factor identification across neurological diseases using large multi-modal biomedical datasets.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does IDEARS support disease risk prediction and biomarker identification?",{"text":81,"@type":77},"IDEARS automates data pre-processing, uses an XGBoost gradient boosting model to predict disease risk, and applies a game-theoretic feature ranking method with tree-based SHAP to identify top associations among UK Biobank fields.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the purpose of ReTimeML in the thesis workflow?",{"text":85,"@type":77},"ReTimeML applies regression methods to automate expected retention times for ceramide and sphingomyelin profiles from LC-MS/MS chromatograms, enabling efficient determination of sphingolipid species concentrations.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"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":107,"slug":139},19,"General","general"]