{"id":"https://openalex.org/W7213787178","doi":"https://doi.org/10.64898/2026.09.15.26362961","title":"Leveraging Large Language Models for Colorectal Cancer Symptom Extraction from MIMIC-IV Clinical Notes","display_name":"Leveraging Large Language Models for Colorectal Cancer Symptom Extraction from MIMIC-IV Clinical Notes","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7213787178","doi":"https://doi.org/10.64898/2026.09.15.26362961"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.15.26362961","doi":"https://doi.org/10.64898/2026.09.15.26362961","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.15.26362961","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.15.26362961.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.15.26362961.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039612410","display_name":"Youran Lee","orcid":"https://orcid.org/0000-0001-8831-7229","observed_orcids":["https://orcid.org/0000-0001-8831-7229"]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Youran Lee","raw_affiliation_strings":["School of Nursing, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0001-8831-7229","affiliations":[{"raw_affiliation_string":"School of Nursing, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130580264","display_name":"Ivo Dinov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivo Dinov","raw_affiliation_strings":["Computational Medicine and Bioinformatics, Medical School, University of Michigan, Ann Arbor, MI, USA","School of Nursing, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Medicine and Bioinformatics, Medical School, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"School of Nursing, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151894796","display_name":"Xiaosu Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaosu Hu","raw_affiliation_strings":["Michigan Institute for Data and AI in Society, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Michigan Institute for Data and AI in Society, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136720371","display_name":"Yun Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Jiang","raw_affiliation_strings":["School of Nursing, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Nursing, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039612410"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.7695000171661377,"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":0.7695000171661377,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.11680000275373459,"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":0.041200000792741776,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/colorectal-cancer","display_name":"colorectal cancer","score":0.9900000095367432},{"id":"https://openalex.org/keywords/symptom-extraction","display_name":"symptom extraction","score":0.8730000257492065},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.890999972820282},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.6639999747276306},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.8019999861717224},{"id":"https://openalex.org/keywords/discharge-notes","display_name":"discharge notes","score":0.8140000104904175},{"id":"https://openalex.org/keywords/clinical-text-mining","display_name":"clinical text mining","score":0.5389999747276306},{"id":"https://openalex.org/keywords/negation-handling","display_name":"negation handling","score":0.722000002861023},{"id":"https://openalex.org/keywords/rule-based-information-extraction","display_name":"rule-based extraction","score":0.6140000224113464},{"id":"https://openalex.org/keywords/mimic-iv","display_name":"MIMIC-IV","score":0.8159999847412109},{"id":"https://openalex.org/keywords/symptom-monitoring","display_name":"symptom monitoring","score":0.6460000276565552},{"id":"https://openalex.org/keywords/gemini","display_name":"Gemini","score":0.4480000138282776},{"id":"https://openalex.org/keywords/claude-haiku","display_name":"Claude Haiku","score":0.9200000166893005}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6741999983787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158000230789185},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5090000033378601},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4097999930381775},{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2778435480","wikidata":"https://www.wikidata.org/wiki/Q840387","display_name":"Colonoscopy","level":4,"score":0.3991999924182892},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C526805850","wikidata":"https://www.wikidata.org/wiki/Q188874","display_name":"Colorectal cancer","level":3,"score":0.3750999867916107},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.15.26362961","doi":"https://doi.org/10.64898/2026.09.15.26362961","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.15.26362961","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.15.26362961.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.15.26362961","doi":"https://doi.org/10.64898/2026.09.15.26362961","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.15.26362961","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/20/2026.09.15.26362961.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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.9537000060081482}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213787178.pdf","grobid_xml":"https://content.openalex.org/works/W7213787178.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1983897914","https://openalex.org/W4396242195","https://openalex.org/W4403586520","https://openalex.org/W7124316889","https://openalex.org/W7164043444"],"related_works":["https://openalex.org/W7213420606","https://openalex.org/W4409226175","https://openalex.org/W4398239341","https://openalex.org/W4414371131","https://openalex.org/W4416139950","https://openalex.org/W7125711972","https://openalex.org/W4410761024","https://openalex.org/W7156031490","https://openalex.org/W7211877264","https://openalex.org/W4402906808"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Much":[2],"of":[3],"the":[4,83,89],"symptom":[5,205,242],"burden":[6],"in":[7,14,74],"colorectal":[8],"cancer":[9],"(CRC)":[10],"patients":[11,73],"is":[12,21],"documented":[13],"unstructured":[15],"discharge-note":[16],"narrative,":[17],"and":[18,31,47,88,101,105,140,168,200,236],"manual":[19,233],"extraction":[20,226],"not":[22,38,211],"scalable.":[23],"Whether":[24],"large":[25],"language":[26],"models":[27],"(LLMs)":[28],"outperform":[29,198],"rule-based":[30,118,165,199],"named":[32],"entity":[33],"recognition":[34],"(NER)":[35],"methods":[36,50],"has":[37],"been":[39],"rigorously":[40],"benchmarked.":[41],"Objective":[42],"To":[43],"benchmark":[44],"rule-based,":[45],"NER,":[46,100],"zero-shot":[48,102],"LLM":[49,178,215,225],"for":[51,203,222,240],"extracting":[52],"46":[53],"cancer-related":[54],"symptoms":[55],"from":[56,71,82],"CRC":[57,72,204],"discharge":[58,69],"notes":[59,70],"against":[60,123],"an":[61],"adjudicated":[62,128],"ground":[63],"truth.":[64],"Methods":[65],"We":[66],"analyzed":[67],"2,704":[68],"MIMIC-IV.":[75],"A":[76],"46-symptom":[77],"target":[78],"list":[79],"was":[80],"built":[81],"Memorial":[84],"Symptom":[85],"Assessment":[86],"Scale":[87],"EORTC":[90],"QLQ-CR29.":[91],"Four":[92],"approaches":[93,202],"--":[94,109],"dictionary-based":[95],"rule":[96,246],"matching,":[97],"pretrained":[98],"clinical":[99],"Claude":[103,156],"Haiku":[104,157],"Gemini":[106,143],"3.5":[107,144],"Flash":[108,145],"plus":[110],"two":[111,130],"hybrid":[112],"variants":[113],"(LLM":[114],"output":[115],"with":[116],"post-hoc":[117,207],"negation":[119,174,208],"filtering)":[120],"were":[121],"evaluated":[122],"a":[124,228],"200-note":[125],"gold":[126],"standard":[127],"by":[129,155,186],"raters":[131],"(pooled":[132],"kappa=0.71,":[133],"macro":[134],"kappa=0.49),":[135],"using":[136],"Macro/Micro":[137],"F1,":[138],"precision,":[139],"recall.":[141],"Results":[142],"performed":[146],"best":[147],"(Macro":[148,158,166,170],"F1=0.70,":[149],"Micro":[150],"F1=0.86,":[151],"Macro":[152,160,181,184],"Precision=0.74),":[153],"followed":[154],"F1=0.63,":[159],"Recall=0.71);":[161],"both":[162],"substantially":[163,197],"outperformed":[164],"F1=0.44)":[167],"NER":[169,201],"F1=0.38)":[171],"methods.":[172],"Post-hoc":[173],"filtering":[175],"paradoxically":[176],"degraded":[177],"performance":[179],"(Gemini+Hybrid":[180],"F1=0.58;":[182],"Claude+Hybrid":[183],"F1=0.54)":[185],"overriding":[187],"correct":[188],"predictions":[189],"through":[190],"rigid,":[191],"fixed-window":[192],"matching.":[193],"Conclusions":[194],"Zero-shot":[195,224],"LLMs":[196],"extraction;":[206],"correction":[209],"should":[210],"be":[212],"applied":[213],"to":[214,232],"outputs":[216],"without":[217,244],"syntactic":[218],"scope":[219],"validation.":[220],"Implications":[221],"Practice:":[223],"offers":[227],"scalable,":[229],"accurate":[230],"alternative":[231],"chart":[234],"review":[235],"traditional":[237],"NLP":[238],"pipelines":[239],"oncology":[241],"surveillance,":[243],"institution-specific":[245],"development":[247],"or":[248],"model":[249],"training.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-21T00:00:00"}