{"id":"https://openalex.org/W587756968","doi":"https://doi.org/10.1136/amiajnl-2012-001552","title":"Comparing Medline citations using modified N-grams: Table 1","display_name":"Comparing Medline citations using modified N-grams: Table 1","publication_year":2013,"publication_date":"2013-05-29","ids":{"openalex":"https://openalex.org/W587756968","doi":"https://doi.org/10.1136/amiajnl-2012-001552","mag":"587756968","pmid":"https://pubmed.ncbi.nlm.nih.gov/23715801"},"language":"en","primary_location":{"id":"doi:10.1136/amiajnl-2012-001552","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2012-001552","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/1/105/6035547/21-1-105.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/article-pdf/21/1/105/6035547/21-1-105.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005027058","display_name":"Rao Muhammad Adeel Nawab","orcid":"https://orcid.org/0000-0002-1765-8904"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Rao Muhammad Adeel Nawab","raw_affiliation_strings":["Department of Computer Science, COMSATS Institute of Information Technology, Lahore, Pakistan","Department of Computer Science, COMSATS Institute of Information Technology Lahore, Pakistan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS Institute of Information Technology, Lahore, Pakistan","institution_ids":["https://openalex.org/I16076960"]},{"raw_affiliation_string":"Department of Computer Science, COMSATS Institute of Information Technology Lahore, Pakistan#TAB#","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049768940","display_name":"Mark Stevenson","orcid":"https://orcid.org/0000-0003-3166-5876"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mark Stevenson","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113791150","display_name":"Paul Clough","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Clough","raw_affiliation_strings":["Information School, University of Sheffield, Sheffield, UK","(Information School, University of Sheffield , Sheffield, UK)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information School, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"(Information School, University of Sheffield , Sheffield, UK)","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049768940"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":0.2752,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.57451338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"21","issue":"1","first_page":"105","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7146000266075134,"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":0.7146000266075134,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.039900001138448715,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12648","display_name":"Academic Writing and Publishing","score":0.026900000870227814,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.629846453666687},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5799364447593689},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.39478573203086853},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3863324224948883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38103917241096497},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20918112993240356}],"concepts":[{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.629846453666687},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5799364447593689},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.39478573203086853},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3863324224948883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38103917241096497},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20918112993240356},{"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}],"mesh":[{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015713","descriptor_name":"Duplicate Publications as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015713","descriptor_name":"Duplicate Publications as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015713","descriptor_name":"Duplicate Publications as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015714","descriptor_name":"Plagiarism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015714","descriptor_name":"Plagiarism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015714","descriptor_name":"Plagiarism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017432","descriptor_name":"Unified Medical Language System","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055641","descriptor_name":"Mathematical Concepts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055641","descriptor_name":"Mathematical Concepts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055641","descriptor_name":"Mathematical Concepts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1136/amiajnl-2012-001552","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2012-001552","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/1/105/6035547/21-1-105.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:23715801","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23715801","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":"Journal of the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:3912705","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3912705","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1136/amiajnl-2012-001552","is_oa":true,"landing_page_url":"https://doi.org/10.1136/amiajnl-2012-001552","pdf_url":"https://academic.oup.com/jamia/article-pdf/21/1/105/6035547/21-1-105.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311330","display_name":"COMSATS Institute of Information Technology","ror":"https://ror.org/00nqqvk19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W587756968.pdf","grobid_xml":"https://content.openalex.org/works/W587756968.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W94330292","https://openalex.org/W95056951","https://openalex.org/W1494404649","https://openalex.org/W1553433956","https://openalex.org/W1568686608","https://openalex.org/W1570448133","https://openalex.org/W1574901103","https://openalex.org/W1631260214","https://openalex.org/W1967043694","https://openalex.org/W1974336599","https://openalex.org/W2053017876","https://openalex.org/W2083953418","https://openalex.org/W2091073950","https://openalex.org/W2099111195","https://openalex.org/W2099781321","https://openalex.org/W2101105183","https://openalex.org/W2108934940","https://openalex.org/W2111308629","https://openalex.org/W2122402213","https://openalex.org/W2129183744","https://openalex.org/W2132069633","https://openalex.org/W2137846744","https://openalex.org/W2140119717","https://openalex.org/W2154652894","https://openalex.org/W2158331042","https://openalex.org/W2164634022","https://openalex.org/W2167302605","https://openalex.org/W2170494111","https://openalex.org/W2251338372","https://openalex.org/W2251717550","https://openalex.org/W3159819647"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3031052312","https://openalex.org/W4389568370","https://openalex.org/W3032375762","https://openalex.org/W1995515455","https://openalex.org/W2080531066","https://openalex.org/W3108674512","https://openalex.org/W1506200166","https://openalex.org/W1489783725"],"abstract_inverted_index":{"OBJECTIVE:":[0],"We":[1],"aim":[2],"to":[3],"identify":[4],"duplicate":[5,121,134,174],"pairs":[6,25,35,122,137],"of":[7,26,36,47,109,117,143,163,173,200],"Medline":[8,111,135,175],"citations,":[9],"particularly":[10,195],"when":[11,196],"the":[12,48,51,64,74,84,125,171],"documents":[13],"are":[14,28,39,91,156],"not":[15],"identical":[16],"but":[17],"contain":[18],"similar":[19,80],"information.":[20],"MATERIALS":[21],"AND":[22],"METHODS:":[23],"Duplicate":[24],"citations":[27,176],"identified":[29],"by":[30,158,180],"comparing":[31],"word":[32,147],"n-grams":[33,162,182],"in":[34,63,73],"documents.":[37],"N-grams":[38,90],"modified":[40],"using":[41,94,106,191],"two":[42],"approaches":[43],"which":[44],"take":[45],"account":[46],"fact":[49],"that":[50,170,184],"document":[52,136],"may":[53],"have":[54],"been":[55],"altered.":[56],"These":[57],"are:":[58],"(1)":[59],"deletion,":[60],"an":[61,71,139],"item":[62,72],"n-gram":[65,75],"is":[66,76,103],"removed;":[67],"and":[68,149,183],"(2)":[69],"substitution,":[70],"substituted":[77],"with":[78,138],"a":[79,95,99,107,115],"term":[81],"obtained":[82,123,157,190],"from":[83,98,124],"Unified":[85],"Medical":[86],"Language":[87],"System":[88],"Metathesaurus.":[89],"also":[92,188],"weighted":[93],"score":[96,142],"derived":[97],"language":[100],"model.":[101],"Evaluation":[102],"carried":[104],"out":[105],"set":[108,116],"520":[110],"citation":[112],"pairs,":[113],"including":[114],"260":[118],"manually":[119],"verified":[120],"Deja":[126],"Vu":[127],"database.":[128],"RESULTS:":[129],"The":[130,153],"approach":[131],"accurately":[132],"detects":[133],"F1":[140],"measure":[141],"0.99.":[144],"Allowing":[145],"for":[146,161,198],"deletions":[148],"substitution":[150],"improves":[151],"performance.":[152],"best":[154],"results":[155],"combining":[159],"scores":[160],"length":[164],"1-5":[165],"words.":[166],"DISCUSSION:":[167],"Results":[168],"show":[169],"detection":[172],"can":[177,187],"be":[178,189],"improved":[179],"modifying":[181],"high":[185],"performance":[186],"only":[192],"unigrams":[193],"(F1=0.959),":[194],"allowing":[197],"substitutions":[199],"alternative":[201],"phrases.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2016-06-24T00:00:00"}
