[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121510-en":3,"doc-seo-121510-105":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":20,"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},121510,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Classifying Dry Eye Disease Patients from Healthy Controls Using Machine Learning and Metabolomics Data","Dry eye disease (DED) is a common ocular surface disorder where current diagnosis relies on clinical signs and symptoms, despite weak correlation between them. This study examines whether machine learning applied to metabolomics information can identify cataract patients with DED and separate them from healthy controls. Eight machine learning models were compared and tuned using nested k-fold cross-validation with dataset-tailored metrics. Logistic regression achieved the strongest overall results, with high AUC and balanced accuracy, followed by XGBoost and Random Forest.","Classifying Dry Eye Disease Patients from Healthy Controls Using Machine Learning and Metabolomics Data  \narXiv :2406 . 14068v2 [ cs .CV] 7 Aug 2024  \nSajad Amouei Sheshkal  \nDepartment of Computer Science Oslo Metropolitan University (OsloMet) Oslo, Norway [sajad.amouei@gmail.com](sajad.amouei@gmail.com)  \nMorten Gundersen  \nDepartment of Life Sciences and Health Oslo Metropolitan University Oslo, Norway  \nMichael Alexander Riegler  \nDepartment of Computer Science Oslo Metropolitan University (OsloMet) Oslo, Norway  \nØygunn Aass Utheim  \nDepartment of Ophthalmology Oslo University Hospital Oslo, Norway  \nKjell Gunnar Gundersen  \nIfocus Eye Clinic Haugesund, Norway  \nHugo Lewi Hammer  \nDepartment of Computer Science Oslo Metropolitan University (OsloMet) Oslo, Norway  \nAbstract—Dry eye disease is a common disorder of the ocular surface, leading patients to seek eye care. Clinical signs and symptoms are currently used to diagnose dry eye disease. Metabolomics, a method for analyzing biological systems, has been found helpful in identifying distinct metabolites in patients and in detecting metabolic profiles that may indicate dry eye disease at early stages. In this study, we explored using machine learning and metabolomics information to identify which cataract patients suffered from dry eye disease. As there is noone-size-fits-all machine learning model for metabolomics data, choosing the most suitable model can significantly affect the quality of predictions and subsequent metabolomics analyses. To address this challenge, we conducted a comparative analysis of eight machine learning models on three metabolomics data sets from cataract patients with and without dry eye disease. The models were evaluated and optimized using nested k-fold crossvalidation. To assess the performance of these models, we selected a set of suitable evaluation metrics tailored to the data set’s challenges. The logistic regression model overall performed the best, achieving the highest area under the curve score of 0.8378, balanced accuracy of 0.735, Matthew’s correlation coefficient of 0.5147, an F1-score of 0.8513, and a specificity of 0.5667. Additionally, following the logistic regression, the XGBoost and Random Forest models also demonstrated good performance.  \nIndex Terms—Machine Learning; Classification; Hyperparameters tuning; Dry Eye Disease; Metabolomics  \nI. INTRODUCTION  \nDry Eye Disease (DED) is a multifaceted disorder characterised by a disruption in the composition, integrity, and stability of the tear film due to various internal and external factors. It is one of the most common reasons people seek eye care, with a severity spectrum ranging from minor, fleeting discomfort to severe, persistent pain and visual function impairment. This progression not only presents a substantial economic and healthcare challenge but also significantly impacts the quality of life of sufferers and the broader community. The incidence of DED notably increases following cataract  \nsurgery, highlighting the critical need for ophthalmologists to thoroughly evaluate for existing DED and to implement proactive treatment approaches. The presence of DED before surgery, can also complicate the precision of pre-surgical measurements, necessitate the reduction of intra-operative factors that could harm the ocular surface, and require the adoption of post-surgical care protocols to prevent the worsening of DED symptoms [1]–[6] . Clinical signs and symptoms are currently used to diagnose dry eye disease; however, the correlation between signs and symptoms is weak, leading to challenges in diagnosing and monitoring DED [7] .  \nAdvancements in omics technologies allow researchers to explore the genome, transcriptome, proteome, and more, providing in-depth insights into the molecular mechanisms underlying diseases. Despite their utility, single omics approaches are insufficient for comprehensively understanding the intricate interactions between genes, RNA, proteins, an","cbCaivaAMrTrzFuH","https://ap.wps.com/l/cbCaivaAMrTrzFuH","pdf",455803,1,10,"English","en",105,"# Introduction\n## Dry eye disease and clinical diagnostic challenges\n## Omics technologies and the role of metabolomics\n## Machine learning for biomarker discovery\n## Study motivation and approach","[{\"question\":\"Why is metabolomics useful for dry eye disease identification?\",\"answer\":\"Metabolomics characterizes dynamic metabolite profiles that reflect biological responses to internal and external stimuli, supporting early detection and insight into etiology and pathology.\"},{\"question\":\"How were machine learning models evaluated in the study?\",\"answer\":\"Eight models were compared and optimized using nested k-fold cross-validation, with evaluation metrics selected to match challenges in the metabolomics datasets.\"},{\"question\":\"Which model performed best overall?\",\"answer\":\"Logistic regression performed best overall, achieving the highest reported AUC and strong scores across balanced accuracy, Matthew’s correlation coefficient, F1-score, and specificity.\"}]","Classifying Dry Eye Disease Patients from Healthy Controls Using Machine Learning and Metabolomics Data | PDF",1785736015,25,{"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},"classifying-dry-eye-disease-patients-from-healthy-controls-using-machine-learning-and-metabolomics-data","",{"@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/classifying-dry-eye-disease-patients-from-healthy-controls-using-machine-learning-and-metabolomics-data/121510/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is metabolomics useful for dry eye disease identification?","Question",{"text":75,"@type":76},"Metabolomics characterizes dynamic metabolite profiles that reflect biological responses to internal and external stimuli, supporting early detection and insight into etiology and pathology.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were machine learning models evaluated in the study?",{"text":80,"@type":76},"Eight models were compared and optimized using nested k-fold cross-validation, with evaluation metrics selected to match challenges in the metabolomics datasets.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performed best overall?",{"text":84,"@type":76},"Logistic regression performed best overall, achieving the highest reported AUC and strong scores across balanced accuracy, Matthew’s correlation coefficient, F1-score, and specificity.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]