{"id":"https://openalex.org/W7220374152","doi":"https://doi.org/10.64898/2026.10.03.26364667","title":"Extraction of clinical information from faxed medical records using a small local large language model pipeline on consumer hardware","display_name":"Extraction of clinical information from faxed medical records using a small local large language model pipeline on consumer hardware","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220374152","doi":"https://doi.org/10.64898/2026.10.03.26364667"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.03.26364667","doi":"https://doi.org/10.64898/2026.10.03.26364667","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.03.26364667","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.64898/2026.10.03.26364667","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066293261","display_name":"Zhouwen Tang","orcid":"https://orcid.org/0000-0001-7600-1008","observed_orcids":["https://orcid.org/0000-0001-7600-1008"]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhouwen Tang","raw_affiliation_strings":["Division of Gastroenterology, Dell Medical School, The University of Texas at Austin, Austin, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0001-7600-1008","affiliations":[{"raw_affiliation_string":"Division of Gastroenterology, Dell Medical School, The University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066293261"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.49559998512268066,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.49559998512268066,"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":0.20509999990463257,"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/T10350","display_name":"Electronic Health Records Systems","score":0.09520000219345093,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/clinical-information-extraction","display_name":"clinical information extraction","score":0.7990000247955322},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7360000014305115},{"id":"https://openalex.org/keywords/consumer-grade-hardware","display_name":"consumer hardware","score":0.6850000023841858},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.8119999766349792},{"id":"https://openalex.org/keywords/structured-information-extraction","display_name":"structured data extraction","score":0.7870000004768372},{"id":"https://openalex.org/keywords/protected-health-information","display_name":"protected health information","score":0.7760000228881836},{"id":"https://openalex.org/keywords/continuity-of-care","display_name":"continuity of care","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773000001907349},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7250000238418579},{"id":"https://openalex.org/C2776135927","wikidata":"https://www.wikidata.org/wiki/Q5242559","display_name":"Referral","level":2,"score":0.5432000160217285},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5056999921798706},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37470000982284546},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C3115412","wikidata":"https://www.wikidata.org/wiki/Q1194708","display_name":"Bitmap","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2754000127315521},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C3019150057","wikidata":"https://www.wikidata.org/wiki/Q92779279","display_name":"Medical information","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.03.26364667","doi":"https://doi.org/10.64898/2026.10.03.26364667","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.03.26364667","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.03.26364667","doi":"https://doi.org/10.64898/2026.10.03.26364667","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.03.26364667","pdf_url":null,"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","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2751687090","https://openalex.org/W4412796692","https://openalex.org/W4414533555","https://openalex.org/W7161977466","https://openalex.org/W7164566809","https://openalex.org/W7168766369","https://openalex.org/W7172380221"],"related_works":["https://openalex.org/W4389490684","https://openalex.org/W4402713323","https://openalex.org/W7127084488","https://openalex.org/W4401697199","https://openalex.org/W4412443869","https://openalex.org/W7134895951","https://openalex.org/W7162668292","https://openalex.org/W4402167740","https://openalex.org/W7220816326","https://openalex.org/W4392648998"],"abstract_inverted_index":{"ABSTRACT":[0],"Objective":[1],"Specialty":[2],"referral":[3,64,75],"packets":[4,76],"often":[5],"arrive":[6],"by":[7],"fax":[8],"and":[9,14,67,102,123,152,160],"clinicians":[10],"must":[11,41],"manually":[12],"read":[13],"organize":[15,33],"a":[16,86],"large":[17,28],"amount":[18],"of":[19,25,143,171],"disparate":[20],"information":[21,39,61,196],"to":[22],"affect":[23],"continuity":[24],"care.":[26],"Commercial":[27],"language":[29],"models":[30],"(LLMs)":[31],"can":[32,57],"packet":[34,94],"information,":[35],"but":[36],"protected":[37],"health":[38],"(PHI)":[40],"be":[42],"secured.":[43],"We":[44,69],"evaluated":[45],"whether":[46],"an":[47,96,107],"open-weight":[48,108,187],"pipeline":[49,91,188],"running":[50],"entirely":[51],"on":[52,131,189],"one":[53],"consumer":[54,190],"graphics":[55],"card":[56],"accurately":[58,192],"extract":[59],"clinical":[60,195],"from":[62,77,197],"faxed":[63,199],"packets.":[65,134],"Materials":[66],"Methods":[68],"generated":[70],"200":[71],"synthetic":[72,198],"colorectal":[73],"cancer":[74],"simulated":[78],"patient":[79,114],"records,":[80],"rendered":[81],"them":[82],"as":[83],"faxes":[84],"without":[85],"text":[87],"layer.":[88],"A":[89],"local":[90],"transcribed":[92],"each":[93],"with":[95,106],"optical":[97],"character":[98],"recognition":[99],"model":[100],"(OvisOCR2)":[101],"extracted":[103,139,173,193],"structured":[104],"data":[105],"LLM":[109],"(Qwen3.8-27B).":[110],"Twenty":[111],"outcomes":[112],"spanning":[113],"identifiers,":[115],"laboratory":[116],"results,":[117],"dates,":[118],"diagnoses,":[119],"procedures,":[120],"medications,":[121],"imaging,":[122],"event":[124],"chronology":[125],"were":[126,138,175],"scored":[127],"against":[128],"ground":[129],"truth":[130],"140":[132],"validation":[133],"Results":[135],"Laboratory":[136],"values":[137],"exactly":[140],"in":[141,147,150,154],"98.9%":[142],"7879":[144],"instances,":[145],"dates":[146],"99.7%,":[148],"diagnoses":[149],"100%,":[151],"procedures":[153],"92.9%.":[155],"Timeline":[156],"recall":[157],"was":[158,165,180],"96.7%":[159],"precision":[161],"99.4%.":[162],"Weighted":[163],"accuracy":[164],"0.990":[166],"(95%":[167],"CI":[168],"0.987\u20130.992).":[169],"None":[170],"11,993":[172],"facts":[174],"fabricated.":[176],"Median":[177],"processing":[178],"time":[179],"90":[181],"seconds":[182],"per":[183],"packet.":[184],"Conclusion":[185],"An":[186],"hardware":[191],"multi-domain":[194],"referrals.":[200]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-06T00:00:00"}