[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-657922-105":59,"doc-detail-657922-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","large-language-models-enable-consensus-level-interpretation-in-metagenomic-diagnostics-diagnostic-classifiers-for-metagenomic-interpretation","Large language models enable consensus-level interpretation in metagenomic diagnostics - Diagnostic classifiers for metagenomic interpretation","","Metagenomic sequencing detects many pathogens, but selecting clinically relevant findings requires expert adjudication that is hard to scale and standardize. The study introduces diagnostic classifiers that formalize expert decisions by combining structured decision trees with large language model reasoning to assign diagnoses and select pathogen candidates. A short-read metagenomic assay for sterile-site specimens from the META-GP study (2024–2025) was used to evaluate classifiers on a validation dataset (n=96) and a development cohort (n=78), demonstrating improved performance with clinical context and enabling automated benchmarking and regression testing for pathogen detection tasks.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/large-language-models-enable-consensus-level-interpretation-in-metagenomic-diagnostics-diagnostic-classifiers-for-metagenomic-interpretation/657922/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/large-language-models-enable-consensus-level-interpretation-in-metagenomic-diagnostics-diagnostic-classifiers-for-metagenomic-interpretation/657922.png","ImageObject",300,407,{"name":92,"@type":93},"Dipper","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-26",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How do the proposed diagnostic classifiers use large language models in metagenomic interpretation?","Question",{"text":112,"@type":113},"They combine structured decision trees with large language model reasoning to formalize expert adjudication, assign diagnoses, and select pathogen candidates.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What specimens and study dataset were used to develop and validate the classifiers?",{"text":117,"@type":113},"The classifiers were evaluated using a short-read metagenomic assay for sterile-site specimens (cerebrospinal and ocular fluid) from the META-GP study (Victoria, Australia, 2024–2025), with validation data including clinical samples, spike-ins, and controls.",{"name":119,"@type":110,"acceptedAnswer":120},"How does adding clinical context affect diagnostic performance?",{"text":121,"@type":113},"Performance improved with clinical context: sensitivity and specificity increased compared with results without clinical notes, reaching higher sensitivity and perfect specificity in the reported setting.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},657922,1793063793,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145},1374404997633,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","medRxiv preprint doi: [https://doi.org/10.64898/2026.07.29.26358751](https://doi.org/10.64898/2026.07.29.26358751); this version posted July 31, 2026. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in  \nperpetuity.  \nIt is made available under a CC-BY 4.0 International license .  \nLarge language models enable consensus-level interpretation in metagenomic diagnostics  \nEike Steinig1,2,*, Marcelina Krysiak1,2,*, Kirti Deo1,2,*, Andrew Duncan1,3, Jacqueline Prestedge1,2, Jeremy Barr4,5, Jean Moselen2, Sadid F. Khan6,7, Janath A. Fernando1, Ivana Savic1,2, Bhargavi Yellapu1, Ammar Aziz2, Wytamma Wirth1, Jessica Parry2, Angela McDonald1, Chhay Lim1, Sharon Trevor1, Benjamin AwYeong2, Georgia McCluskey2, Michael Moso1, Eddie Chan6, Sonia L. La Vita8, Penelope A. Bryant8,9, 10, Amy Crowe11, Ramla Maalim12, Diana Velasquez Reyes1, Maryza Graham1,2, Eloise Williams1,2,13, Jason C. Kwong13,14, Rachel Woolstencroft15, Monica Slavin15, Lyndell L Lim16, Lachlan J. M. Coin14, Leon Caly2,17, Katherine Bond2,12, Chuan Kok Lim1,2, Timothy P. Stinear14,18, Deborah A. Williamson19, Prashanth S. Ramachandran1,20  \n* authors contributed equally to this project  \n1 Department of Infectious Diseases, The University of Melbourne at the Peter Doherty Institute for Infection and Immunity, Melbourne, Victoria, Australia  \n2 Victorian Infectious Diseases Reference Laboratory, Royal Melbourne Hospital at the Peter Doherty Institute for Infection and Immunity, Melbourne, Victoria, Australia  \n3 Neurosciences Department, St Vincent's Hospital, Melbourne, Victoria, Australia  \n4 School of Biological Sciences, Monash University, Melbourne, Victoria, Australia  \n5 Centre to Impact AMR, Monash University, Clayton, Victoria, Australia  \n6 Department of Infectious Diseases, The Alfred Hospital and School of Translational Medicine, Monash University, Melbourne, Victoria, Australia  \n7 Microbiology Unit, Department of Pathology, The Alfred Hospital, Bayside Health, Melbourne, Victoria, Australia  \n8 Murdoch Children's Research Institute, Melbourne, Victoria, Australia  \n9 Department of Infectious Diseases, The Royal Children’s Hospital Melbourne, Victoria, Australia  \n10 Department of Paediatrics, University of Melbourne, Melbourne, Victoria, Australia  \n11 Department of Infectious Diseases, St Vincent's Hospital, Melbourne, Victoria, Australia  \n12 Department of Microbiology, Royal Melbourne Hospital, Melbourne, Victoria, Australia  \n13 Department of Infectious Diseases and Immunology, Austin Health, Heidelberg, Victoria, Australia  \n14 Department of Microbiology and Immunology, The University of Melbourne at the Peter Doherty Institute for Infection and Immunity, Melbourne, Victoria, Australia  \n15 Department of Infectious Disease, The Peter McCallum Cancer Centre, Melbourne, Victoria, Australia  \n16 CNeOntTrEe: hisor reyritreespeortsarncwAreseustarcraithaa, tRhaosynaolteiecntcoerritifaiendEbyepeeranevEiewaradsohsopuitldao,tUbeniuvsed tersoituido lineilopraucrticnee,. Melbourne, Victoria, Australia  \nmedRxiv preprint doi: [https://doi.org/10.64898/2026.07.29.26358751](https://doi.org/10.64898/2026.07.29.26358751); this version posted July 31, 2026. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in  \nperpetuity.  \nIt is made available under a CC-BY 4.0 International license .  \n17 Department of Biochemistry and Molecular Biology, Monash University, Clayton, Victoria, Australia.  \n18 Centre for Pathogen Genomics, The University of Melbourne at the Peter Doherty Institute for Infection and Immunity, Melbourne, Victoria, Australia  \n19 School of Medicine, University of St Andrews, St Andrews, Scotland, United Kingdom  \n20 Department of Neurology, Royal Melbourne Hospital, Melbourne, Victoria, Australia  \nmedRxiv preprint doi: [https://doi.org/10","cbCaimxmEeUDgWPh","https://ap.wps.com/l/cbCaimxmEeUDgWPh","pdf",3080386,82,"English","# Abstract\n## Diagnostic classifiers and LLM reasoning\n## Metagenomic assay evaluation in META-GP\n## Performance with and without clinical context\n## Benchmarking, regression testing, and missed pathogen recovery","[{\"question\":\"How do the proposed diagnostic classifiers use large language models in metagenomic interpretation?\",\"answer\":\"They combine structured decision trees with large language model reasoning to formalize expert adjudication, assign diagnoses, and select pathogen candidates.\"},{\"question\":\"What specimens and study dataset were used to develop and validate the classifiers?\",\"answer\":\"The classifiers were evaluated using a short-read metagenomic assay for sterile-site specimens (cerebrospinal and ocular fluid) from the META-GP study (Victoria, Australia, 2024–2025), with validation data including clinical samples, spike-ins, and controls.\"},{\"question\":\"How does adding clinical context affect diagnostic performance?\",\"answer\":\"Performance improved with clinical context: sensitivity and specificity increased compared with results without clinical notes, reaching higher sensitivity and perfect specificity in the reported setting.\"}]","Large language models enable consensus-level interpretation in metagenomic diagnostics - Diagnostic classifiers for metagenomic interpretation | PDF",1792994964,207]