{"id":"https://openalex.org/W2169909923","doi":"https://doi.org/10.1177/1460458213494032","title":"University of California, Irvine\u2013Pathology Extraction Pipeline: The pathology extraction pipeline for information extraction from pathology reports","display_name":"University of California, Irvine\u2013Pathology Extraction Pipeline: The pathology extraction pipeline for information extraction from pathology reports","publication_year":2014,"publication_date":"2014-08-25","ids":{"openalex":"https://openalex.org/W2169909923","doi":"https://doi.org/10.1177/1460458213494032","mag":"2169909923","pmid":"https://pubmed.ncbi.nlm.nih.gov/25155030"},"language":"en","primary_location":{"id":"doi:10.1177/1460458213494032","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1460458213494032","pdf_url":null,"source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034548846","display_name":"Naveen Ashish","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Naveen Ashish","raw_affiliation_strings":["University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110399045","display_name":"Lisa Dahm","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lisa Dahm","raw_affiliation_strings":["University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063901441","display_name":"Charles Boicey","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Boicey","raw_affiliation_strings":["University of California, Irvine, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034548846"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":{"value":1500,"currency":"USD","value_usd":1500},"apc_paid":null,"fwci":0.9941,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.76007314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":"4","first_page":"288","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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":0.9943000078201294,"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/computer-science","display_name":"Computer science","score":0.7581419944763184},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7537944316864014},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.540203869342804},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.48786377906799316},{"id":"https://openalex.org/keywords/digital-pathology","display_name":"Digital pathology","score":0.47313064336776733},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.4169095456600189},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.3624361753463745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36087167263031006},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3242941200733185},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.19339972734451294},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.1647413969039917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581419944763184},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7537944316864014},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.540203869342804},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.48786377906799316},{"id":"https://openalex.org/C2777522853","wikidata":"https://www.wikidata.org/wiki/Q5276128","display_name":"Digital pathology","level":2,"score":0.47313064336776733},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.4169095456600189},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.3624361753463745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36087167263031006},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3242941200733185},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.19339972734451294},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.1647413969039917},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000046","descriptor_name":"Academic Medical Centers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000046","descriptor_name":"Academic Medical Centers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000046","descriptor_name":"Academic Medical Centers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002140","descriptor_name":"California","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002140","descriptor_name":"California","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002140","descriptor_name":"California","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006785","descriptor_name":"Hospitals, University","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006785","descriptor_name":"Hospitals, University","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006785","descriptor_name":"Hospitals, University","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D010338","descriptor_name":"Pathology, Clinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010338","descriptor_name":"Pathology, Clinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010338","descriptor_name":"Pathology, Clinical","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D018511","descriptor_name":"Systems Integration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018511","descriptor_name":"Systems Integration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018511","descriptor_name":"Systems Integration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020000","descriptor_name":"Decision Support Systems, Clinical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020000","descriptor_name":"Decision Support Systems, Clinical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020000","descriptor_name":"Decision Support Systems, Clinical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055317","descriptor_name":"Evidence-Based Practice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055317","descriptor_name":"Evidence-Based Practice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055317","descriptor_name":"Evidence-Based Practice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1177/1460458213494032","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1460458213494032","pdf_url":null,"source":{"id":"https://openalex.org/S201800618","display_name":"Health Informatics Journal","issn_l":"1460-4582","issn":["1460-4582","1741-2811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Health Informatics Journal","raw_type":"journal-article"},{"id":"pmid:25155030","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25155030","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,"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":"Health informatics journal","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1508977358","https://openalex.org/W1541954861","https://openalex.org/W1982938880","https://openalex.org/W2037038404","https://openalex.org/W2076424959","https://openalex.org/W2087779040","https://openalex.org/W2097960255","https://openalex.org/W2104655020","https://openalex.org/W2106950427","https://openalex.org/W2114388055","https://openalex.org/W2126344780","https://openalex.org/W2146089916","https://openalex.org/W2166861608","https://openalex.org/W2169818249","https://openalex.org/W2613433911"],"related_works":["https://openalex.org/W2378767206","https://openalex.org/W1540871478","https://openalex.org/W328308450","https://openalex.org/W282641168","https://openalex.org/W2376963063","https://openalex.org/W2066396794","https://openalex.org/W2366734808","https://openalex.org/W2002476357","https://openalex.org/W2391444248","https://openalex.org/W2390716080"],"abstract_inverted_index":{"We":[0,117],"describe":[1],"Pathology":[2],"Extraction":[3],"Pipeline":[4],"(PEP)--a":[5],"new":[6],"Open":[7],"Health":[8],"Natural":[9],"Language":[10],"Processing":[11],"pipeline":[12,45,126,155],"that":[13,85,99],"we":[14,37],"have":[15,38],"developed":[16],"for":[17,92,127,141,159],"information":[18,128],"extraction":[19,50,93,102,129],"from":[20,72,107],"pathology":[21,54,74,114,157],"reports,":[22],"with":[23],"the":[24,28,101,108,122,151,154],"goal":[25],"of":[26,90,124,153],"populating":[27],"extracted":[29],"data":[30,34,68],"into":[31],"a":[32,96,113,131],"research":[33],"warehouse.":[35],"Specifically,":[36],"built":[39],"upon":[40],"Medical":[41],"Knowledge":[42],"Analysis":[43],"Tool":[44],"(MedKATp),":[46],"which":[47],"is":[48],"an":[49,82],"framework":[51],"focused":[52],"on":[53,64],"reports.":[55],"Our":[56],"particular":[57],"contributions":[58],"include":[59],"additional":[60],"customization":[61],"and":[62,70,95,148],"development":[63],"MedKATp":[65,91],"to":[66,105,138,145],"extract":[67],"elements":[69],"relationships":[71],"cancer":[73,161],"reports":[75,115,158],"in":[76,112,130],"richer":[77],"detail":[78],"than":[79],"at":[80],"present,":[81],"abstraction":[83],"layer":[84],"provides":[86],"significantly":[87],"easier":[88],"configuration":[89],"tasks,":[94],"machine-learning-based":[97],"approach":[98,140],"makes":[100],"more":[103],"resilient":[104],"deviations":[106],"common":[109],"reporting":[110],"format":[111,146],"corpus.":[116],"present":[118],"experimental":[119],"results":[120],"demonstrating":[121,134,150],"effectiveness":[123],"our":[125,139],"real-world":[132],"task,":[133],"performance":[135],"improvement":[136],"due":[137],"increasing":[142],"extractor":[143],"resilience":[144],"deviation,":[147],"finally":[149],"scalability":[152],"across":[156],"different":[160],"types.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}
