{"id":"https://openalex.org/W7168364151","doi":"https://doi.org/10.48550/arxiv.2607.12886","title":"A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study","display_name":"A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7168364151","doi":"https://doi.org/10.48550/arxiv.2607.12886"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.12886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140899559","display_name":"Cameron Cagan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cagan, Cameron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140840872","display_name":"Pedram Fard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fard, Pedram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140822935","display_name":"Jiazi Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Jiazi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140887124","display_name":"Jingya Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Jingya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140847415","display_name":"Shawn N. Murphy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murphy, Shawn N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140949730","display_name":"Hossein Estiri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Estiri, Hossein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.6080999970436096,"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"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.6080999970436096,"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/T10028","display_name":"Topic Modeling","score":0.10119999945163727,"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/T12574","display_name":"Clinical Reasoning and Diagnostic Skills","score":0.05490000173449516,"subfield":{"id":"https://openalex.org/subfields/2714","display_name":"Family Practice"},"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/lexicon","display_name":"Lexicon","score":0.8156999945640564},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6773999929428101},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5669000148773193},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.545199990272522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.39500001072883606},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3474999964237213},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8156999945640564},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6773999929428101},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6086999773979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5928000211715698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5719000101089478},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.12886","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6338698267936707}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Clinical":[0],"notes":[1,73,100],"contain":[2],"many":[3],"of":[4,120,124,145,164,177,202,221],"the":[5,132,138,154,214],"signs":[6,94],"and":[7,50,77,83,95,106,122,129,134,223],"symptoms":[8,96],"that":[9,29,37,47,237,247],"bring":[10],"patients":[11],"to":[12,184,225,252],"care,":[13],"yet":[14],"this":[15],"information":[16],"rarely":[17],"reaches":[18],"structured":[19],"fields.":[20],"Existing":[21],"extraction":[22,52,245],"approaches":[23],"either":[24],"rely":[25],"on":[26,34,64,74,140,213,257],"context-insensitive":[27],"rules":[28],"generate":[30],"false":[31],"positives":[32],"or":[33,61,136],"supervised":[35],"models":[36],"require":[38],"substantial":[39],"fine-tuning.":[40,62],"We":[41,85],"present":[42],"Pythia,":[43],"a":[44,65,89,168,178,199],"multi-agent":[45],"system":[46],"autonomously":[48],"writes":[49],"optimizes":[51],"prompts":[53,79,246],"for":[54,113,131,143,228],"clinical":[55,72,99],"concepts":[56,152,229],"without":[57],"manual":[58],"prompt":[59,240],"engineering":[60],"Running":[63],"locally":[66],"hosted":[67],"open-weights":[68],"model,":[69],"Pythia":[70,87,116,160],"keeps":[71],"local":[75,258],"infrastructure":[76],"selects":[78],"using":[80],"development-set":[81],"sensitivity":[82,119,192,220,227],"specificity.":[84],"compared":[86,126],"with":[88,127,186],"curated":[90],"lexicon":[91,139,155],"across":[92,189],"72":[93],"from":[97,182,250],"400":[98],"representing":[101],"387":[102],"patients.":[103],"Development":[104],"(n=300)":[105],"validation":[107,185,253],"(n=100)":[108],"sets":[109],"were":[110],"partitioned":[111],"independently":[112],"each":[114],"concept.":[115],"achieved":[117,218],"mean":[118,162,200,219],"0.76":[121,130],"specificity":[123,163],"0.95,":[125],"0.82":[128],"lexicon,":[133],"matched":[135],"exceeded":[137],"both":[141],"metrics":[142],"20":[144],"62":[146],"directly":[147],"comparable":[148],"concepts.":[149],"For":[150],"14":[151],"where":[153],"labeled":[156],"every":[157],"note":[158],"positive,":[159],"recovered":[161],"0.97":[165],"by":[166],"requiring":[167],"present-tense,":[169],"patient-attributed":[170],"finding":[171],"rather":[172],"than":[173],"any":[174],"textual":[175],"mention":[176],"term.":[179],"Specificity":[180],"transferred":[181],"development":[183,216,251],"minimal":[187],"degradation":[188],"prevalences,":[190],"whereas":[191],"transfer":[193],"weakened":[194],"below":[195,204,230],"5%":[196,232],"prevalence,":[197],"reaching":[198],"gap":[201],"0.25":[203],"2%":[205],"prevalence.":[206,233],"A":[207],"BERT":[208],"classifier":[209],"fine-tuned":[210],"per":[211],"concept":[212],"same":[215],"set":[217],"0.23":[222],"collapsed":[224],"zero":[226],"roughly":[231],"These":[234],"findings":[235],"suggest":[236],"autonomous,":[238],"fine-tuning-free":[239],"optimization":[241],"can":[242],"produce":[243],"symptom":[244],"generalize":[248],"effectively":[249],"while":[254],"remaining":[255],"deployable":[256],"infrastructure.":[259]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}