{"id":"https://openalex.org/W2067775439","doi":"https://doi.org/10.4103/2153-3539.115880","title":"Automated extraction of precise protein expression patterns in lymphoma by text mining abstracts of immunohistochemical studies","display_name":"Automated extraction of precise protein expression patterns in lymphoma by text mining abstracts of immunohistochemical studies","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2067775439","doi":"https://doi.org/10.4103/2153-3539.115880","mag":"2067775439","pmid":"https://pubmed.ncbi.nlm.nih.gov/23967385","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3746413"},"language":"en","primary_location":{"id":"doi:10.4103/2153-3539.115880","doi":"https://doi.org/10.4103/2153-3539.115880","is_oa":true,"landing_page_url":"https://doi.org/10.4103/2153-3539.115880","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2153353922006411/pdf","source":{"id":"https://openalex.org/S4210177785","display_name":"Journal of Pathology Informatics","issn_l":"2153-3539","issn":["2153-3539","2229-5089"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","norway-1","oarl","poland-70"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Pathology Informatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.sciencedirect.com/science/article/pii/S2153353922006411/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103548837","display_name":"Jia-Fu Chang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia-Fu Chang","raw_affiliation_strings":["MU Informatics Institute, University of Missouri, Columbia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MU Informatics Institute, University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060329217","display_name":"Mihail Popescu","orcid":"https://orcid.org/0000-0002-6145-8096","observed_orcids":["https://orcid.org/0000-0002-6145-8096"]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihail Popescu","raw_affiliation_strings":["Health Management and Informatics, University of Missouri, Columbia, USA","MU Informatics Institute, University of Missouri, Columbia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health Management and Informatics, University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"MU Informatics Institute, University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110232184","display_name":"Gerald L. Arthur","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gerald L. Arthur","raw_affiliation_strings":["Department of Pathology and Anatomical Sciences, University of Missouri, Columbia, USA","MU Informatics Institute, University of Missouri, Columbia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology and Anatomical Sciences, University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"MU Informatics Institute, University of Missouri, Columbia, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5110232184"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":{"value":2070,"currency":"USD","value_usd":2070},"apc_paid":{"value":2070,"currency":"USD","value_usd":2070},"fwci":0.0,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.09154251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"4","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":9.999999747378752e-05,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-levels","display_name":"protein abundance","score":0.7609999775886536},{"id":"https://openalex.org/keywords/lymphoma","display_name":"lymphoma","score":0.9800000190734863},{"id":"https://openalex.org/keywords/immunohistochemistry","display_name":"immunohistochemistry","score":0.9380000233650208},{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.9129999876022339},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.9890000224113464},{"id":"https://openalex.org/keywords/regular-expressions","display_name":"regular expressions","score":0.5289999842643738},{"id":"https://openalex.org/keywords/rule-based-information-extraction","display_name":"rule-based extraction","score":0.7929999828338623},{"id":"https://openalex.org/keywords/immunophenotype","display_name":"immunophenotype","score":0.6380000114440918},{"id":"https://openalex.org/keywords/disease-subclassification","display_name":"disease subclassification","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546223402023315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5843538641929626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5779704451560974},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5735064744949341},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5595178008079529},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5388379693031311},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5326910018920898},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4748028814792633},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.45654797554016113},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.4203016757965088},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.40669649839401245},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.38973885774612427},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.17020541429519653},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.4103/2153-3539.115880","doi":"https://doi.org/10.4103/2153-3539.115880","is_oa":true,"landing_page_url":"https://doi.org/10.4103/2153-3539.115880","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2153353922006411/pdf","source":{"id":"https://openalex.org/S4210177785","display_name":"Journal of Pathology Informatics","issn_l":"2153-3539","issn":["2153-3539","2229-5089"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","norway-1","oarl","poland-70"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Pathology Informatics","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:2739950","doi":null,"is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC3746413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3746413","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3746413","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Pathol Inform","raw_type":"Text"},{"id":"pmid:23967385","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23967385","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":"Journal of pathology informatics","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:602e330d89d84c59ad0d065336392fc2","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/602e330d89d84c59ad0d065336392fc2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Pathology Informatics, Vol 4, Iss 1, Pp 20-20 (2013)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.4103/2153-3539.115880","doi":"https://doi.org/10.4103/2153-3539.115880","is_oa":true,"landing_page_url":"https://doi.org/10.4103/2153-3539.115880","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2153353922006411/pdf","source":{"id":"https://openalex.org/S4210177785","display_name":"Journal of Pathology Informatics","issn_l":"2153-3539","issn":["2153-3539","2229-5089"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","norway-1","oarl","poland-70"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Pathology Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.4043000042438507}],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309568","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2067775439.pdf","grobid_xml":"https://content.openalex.org/works/W2067775439.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W42742550","https://openalex.org/W68438997","https://openalex.org/W1976316416","https://openalex.org/W1980127292","https://openalex.org/W1982938880","https://openalex.org/W2015138852","https://openalex.org/W2022383931","https://openalex.org/W2032991527","https://openalex.org/W2076424959","https://openalex.org/W2087779040","https://openalex.org/W2100592161","https://openalex.org/W2101289003","https://openalex.org/W2107344625","https://openalex.org/W2111925240","https://openalex.org/W2123796147","https://openalex.org/W2131285447","https://openalex.org/W2139865360","https://openalex.org/W2147818576","https://openalex.org/W2162349028","https://openalex.org/W2169818249","https://openalex.org/W2173359884","https://openalex.org/W2221183959","https://openalex.org/W2914853499","https://openalex.org/W4211208250"],"related_works":["https://openalex.org/W4386209850","https://openalex.org/W4417228555","https://openalex.org/W2495120132","https://openalex.org/W7075273393","https://openalex.org/W2173884055","https://openalex.org/W2118997832","https://openalex.org/W4308522603","https://openalex.org/W4409546167","https://openalex.org/W3043553871","https://openalex.org/W3209863938"],"abstract_inverted_index":{"BACKGROUND:":[0],"In":[1,188],"general,":[2],"surgical":[3],"pathology":[4,27,208,232,262],"reviews":[5],"report":[6],"protein":[7,68,96],"expression":[8,34,69,97],"by":[9,37,99,236],"tumors":[10],"in":[11,91,175,258],"a":[12,64,168,195,211,225],"semi-quantitative":[13],"manner,":[14],"that":[15],"is,":[16],"-,":[17],"-/+,":[18],"+/-,":[19],"+.":[20],"At":[21],"the":[22,25,52,100,111,116,122,158,192,231],"same":[23],"time,":[24],"experimental":[26,89,207],"literature":[28,209],"provides":[29],"multiple":[30],"examples":[31],"of":[32,42,44,55,84,87,93,95,118,121,137,160,171,177,186,194,214,228,239],"precise":[33],"levels":[35,70],"determined":[36],"immunohistochemical":[38],"(IHC)":[39],"tissue":[40],"examination":[41],"populations":[43],"tumors.":[45],"Natural":[46],"language":[47],"processing":[48],"(NLP)":[49],"techniques":[50,245,250],"enable":[51],"automated":[53],"extraction":[54,136,159],"such":[56,161],"information":[57,162],"through":[58,75],"text":[59,126,248],"mining.":[60],"We":[61,166],"propose":[62],"establishing":[63],"database":[65],"linking":[66],"quantitative":[67],"with":[71,110,183],"specific":[72],"tumor":[73,101],"classifications":[74],"NLP.":[76],"MATERIALS":[77],"AND":[78],"METHODS:":[79],"Our":[80,152],"method":[81],"takes":[82],"advantage":[83],"typical":[85],"forms":[86,141,259],"representing":[88],"findings":[90,120],"terms":[92],"percentages":[94,106],"manifest":[98],"population":[102],"under":[103],"study.":[104],"Characteristically,":[105],"are":[107],"represented":[108,235],"straightforwardly":[109],"%":[112],"symbol":[113],"or":[114],"as":[115,173,234],"number":[117],"positive":[119],"total":[123],"population.":[124],"Such":[125],"is":[127,155],"readily":[128],"recognized":[129],"using":[130,145],"regular":[131],"expressions":[132],"and":[133,148,180,201,241,255],"templates":[134],"permitting":[135],"sentences":[138],"containing":[139],"these":[140],"for":[142,199,251,261],"further":[143],"analysis":[144],"grammatical":[146],"structures":[147],"rule-based":[149],"algorithms.":[150],"RESULTS:":[151],"pilot":[153],"study":[154],"limited":[156],"to":[157,164],"related":[163],"lymphomas.":[165],"achieved":[167],"satisfactory":[169],"level":[170],"retrieval":[172],"reflected":[174],"scores":[176],"69.91%":[178],"precision":[179],"57.25%":[181],"recall":[182],"an":[184],"F-score":[185],"62.95%.":[187],"addition,":[189],"we":[190],"demonstrate":[191],"utility":[193],"web-based":[196],"curation":[197],"tool":[198],"confirming":[200],"correcting":[202],"our":[203],"findings.":[204],"CONCLUSIONS:":[205],"The":[206],"represents":[210],"rich":[212],"source":[213],"pathobiological":[215],"information,":[216],"which":[217],"has":[218,223],"been":[219,224],"relatively":[220],"underutilized.":[221],"There":[222],"combinatorial":[226],"explosion":[227],"knowledge":[229,254],"within":[230],"domain":[233],"increasing":[237],"numbers":[238],"immunophenotypes":[240],"disease":[242],"subclassifications.":[243],"NLP":[244],"support":[246,264],"practical":[247],"mining":[249],"extracting":[252],"this":[253],"organizing":[256],"it":[257],"appropriate":[260],"decision":[263],"systems.":[265]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}
