{"id":"https://openalex.org/W7213750705","doi":"https://doi.org/10.64898/2026.09.17.26363303","title":"LLM-enabled Natural History Study Analysis to Support Rare Disease Research","display_name":"LLM-enabled Natural History Study Analysis to Support Rare Disease Research","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7213750705","doi":"https://doi.org/10.64898/2026.09.17.26363303","pmid":"https://pubmed.ncbi.nlm.nih.gov/42779962","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/13596668"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.17.26363303","doi":"https://doi.org/10.64898/2026.09.17.26363303","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.26363303","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.17.26363303.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.17.26363303.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049437592","display_name":"Kevin Li","orcid":"https://orcid.org/0000-0003-2038-7217","observed_orcids":["https://orcid.org/0000-0003-2038-7217"]},"institutions":[{"id":"https://openalex.org/I4210148682","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210148682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Li","raw_affiliation_strings":["Division of Preclinical Innovations, National Center for Advancing Translational Sciences, Rockville, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-2038-7217","affiliations":[{"raw_affiliation_string":"Division of Preclinical Innovations, National Center for Advancing Translational Sciences, Rockville, MD, USA","institution_ids":["https://openalex.org/I4210148682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010367865","display_name":"Eric Sid","orcid":"https://orcid.org/0000-0001-7697-3026","observed_orcids":["https://orcid.org/0000-0001-7697-3026"]},"institutions":[{"id":"https://openalex.org/I4210148682","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210148682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Sid","raw_affiliation_strings":["Division of Rare Disease Research Innovations, National Center for Advancing Translational Sciences, Bethesda, MD, USA"],"raw_orcid":"https://orcid.org/0000-0001-7697-3026","affiliations":[{"raw_affiliation_string":"Division of Rare Disease Research Innovations, National Center for Advancing Translational Sciences, Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210148682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073074181","display_name":"Qian Zhu","orcid":"https://orcid.org/0000-0002-4858-6333","observed_orcids":["https://orcid.org/0000-0002-4858-6333"]},"institutions":[{"id":"https://openalex.org/I4210148682","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210148682"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qian Zhu","raw_affiliation_strings":["Division of Preclinical Innovations, National Center for Advancing Translational Sciences, Rockville, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-4858-6333","affiliations":[{"raw_affiliation_string":"Division of Preclinical Innovations, National Center for Advancing Translational Sciences, Rockville, MD, USA","institution_ids":["https://openalex.org/I4210148682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073074181"],"corresponding_institution_ids":["https://openalex.org/I4210148682"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-history-research","display_name":"natural history research","score":0.9440000057220459},{"id":"https://openalex.org/keywords/rare-diseases","display_name":"rare diseases","score":0.9729999899864197},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9259999990463257},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.878000020980835},{"id":"https://openalex.org/keywords/pubmed-abstracts","display_name":"PubMed abstracts","score":0.7429999709129333},{"id":"https://openalex.org/keywords/open-source-llms","display_name":"open-source LLMs","score":0.796999990940094},{"id":"https://openalex.org/keywords/gemma","display_name":"Gemma","score":0.6970000267028809},{"id":"https://openalex.org/keywords/llama-3-1","display_name":"Llama 3.1","score":0.8270000219345093},{"id":"https://openalex.org/keywords/evidence-synthesis","display_name":"evidence synthesis","score":0.5989999771118164},{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406999826431274},{"id":"https://openalex.org/C163276114","wikidata":"https://www.wikidata.org/wiki/Q484591","display_name":"Natural history","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C2779701055","wikidata":"https://www.wikidata.org/wiki/Q929833","display_name":"Rare disease","level":3,"score":0.501800000667572},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.35580000281333923},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.3540000021457672},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.64898/2026.09.17.26363303","doi":"https://doi.org/10.64898/2026.09.17.26363303","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.26363303","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.17.26363303.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},{"id":"pmid:42779962","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42779962","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"medRxiv : the preprint server for health sciences","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13596668","doi":null,"is_oa":true,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42779962/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"medRxiv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.64898/2026.09.17.26363303","doi":"https://doi.org/10.64898/2026.09.17.26363303","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.26363303","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.17.26363303.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000856723","display_name":"Rare Disease Translational Research","funder_award_id":"1ziatr000548-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306085","display_name":"U.S. Department of Health and Human Services","ror":"https://ror.org/033jnv181"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213750705.pdf","grobid_xml":"https://content.openalex.org/works/W7213750705.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1934602670","https://openalex.org/W2023924430","https://openalex.org/W2036935277","https://openalex.org/W2116093010","https://openalex.org/W2517778143","https://openalex.org/W2739351515","https://openalex.org/W2911489562","https://openalex.org/W2973267506","https://openalex.org/W2988630324","https://openalex.org/W3046375318","https://openalex.org/W3106811464","https://openalex.org/W3121555372","https://openalex.org/W4311209537","https://openalex.org/W4379260375","https://openalex.org/W4387321091","https://openalex.org/W4401306886","https://openalex.org/W4415100461","https://openalex.org/W6947991961"],"related_works":["https://openalex.org/W4405750439","https://openalex.org/W4415100461","https://openalex.org/W4390607929","https://openalex.org/W4415251984","https://openalex.org/W4412443110","https://openalex.org/W7220754566","https://openalex.org/W4399141401","https://openalex.org/W7167633149","https://openalex.org/W7154609244","https://openalex.org/W4416591475"],"abstract_inverted_index":{"BACKGROUND:":[0],"Rare":[1],"diseases":[2],"affect":[3],"an":[4,60],"estimated":[5],"300":[6],"million":[7],"people":[8],"worldwide,":[9],"yet":[10],"the":[11,104,127,132,150,154,167],"research":[12,92],"needed":[13],"to":[14,77,189,218],"guide":[15],"diagnosis":[16],"and":[17,49,74,98,102,110,145,149,180],"treatment":[18],"is":[19],"often":[20],"fragmented":[21],"across":[22],"multiple":[23],"unstructured":[24],"literature":[25],"sources.":[26],"Natural":[27],"history":[28],"studies":[29],"(NHS)":[30],"are":[31],"a":[32,57,87,176],"key":[33,79],"source":[34],"of":[35,137,195],"this":[36],"evidence,":[37],"but":[38],"manually":[39],"extracting":[40],"structured":[41,209],"information":[42,61],"from":[43,82,86],"NHS":[44,80,210],"publications":[45],"can":[46,207],"be":[47],"tedious":[48],"does":[50],"not":[51],"scale.":[52],"METHODS:":[53],"We":[54],"have":[55],"developed":[56],"proof-of-concept":[58],"for":[59,143,147,159],"extraction":[62,108],"pipeline":[63],"testing":[64],"three":[65,115],"opensource":[66],"large-language":[67],"models":[68,105,116],"(LLMs)":[69],"--":[70],"Athena-v3-AWQ,":[71],"Google's":[72],"Gemma3-27B,":[73],"Meta's":[75],"Llama-3.1-70B-Instruct,":[76],"extract":[78,208],"characteristics":[81,211],"PubMed":[83],"abstracts":[84,118],"curated":[85],"Chan":[88],"Zuckerberg":[89],"Initiative":[90],"disease":[91,224],"state":[93],"model":[94],"corpus":[95,156],"(302":[96],"gold-standard":[97],"8,338":[99],"full-corpus":[100],"abstracts),":[101,161],"compared":[103],"on":[106,153,166],"efficiency,":[107],"completeness,":[109],"expert-rated":[111,134],"accuracy.":[112],"RESULTS:":[113],"All":[114],"processed":[117],"with":[119,131],"success":[120],"rates":[121],"exceeding":[122],"99%.":[123],"However,":[124],"Gemma":[125],"achieved":[126],"best":[128],"overall":[129],"performance,":[130],"highest":[133],"accuracy":[135],"(68.0%":[136],"outputs":[138],"rated":[139],"\"good\"":[140],"vs.":[141,173],"36.0%":[142],"Llama":[144,163],"10.0%":[146],"Athena)":[148],"fastest":[151],"runtime":[152],"full":[155],"(~16":[157],"minutes":[158],"3,547":[160],"despite":[162],"scoring":[164],"higher":[165],"automated":[168,179],"Token":[169],"F1":[170],"metric":[171],"(0.874":[172],"0.723),":[174],"highlighting":[175],"divergence":[177],"between":[178],"human":[181],"evaluation.":[182],"Athena's":[183],"lower":[184],"performance":[185],"was":[186],"largely":[187],"attributable":[188],"verbatim":[190],"copying":[191],"rather":[192],"than":[193],"synthesis":[194,221],"extracted":[196],"content.":[197],"CONCLUSIONS:":[198],"These":[199],"findings":[200],"illustrate":[201],"how":[202],"locally":[203],"deployed":[204],"open-source":[205],"LLMs":[206],"at":[212],"scale,":[213],"thus":[214],"supporting":[215],"their":[216],"use":[217],"accelerate":[219],"evidence":[220],"in":[222],"rare":[223],"research.":[225]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-21T00:00:00"}