{"id":"https://openalex.org/W2803527915","doi":"https://doi.org/10.2478/dim-2018-0004","title":"Design of a generic, open platform for machine learning-assisted indexing and clustering of articles in PubMed, a biomedical bibliographic database","display_name":"Design of a generic, open platform for machine learning-assisted indexing and clustering of articles in PubMed, a biomedical bibliographic database","publication_year":2018,"publication_date":"2018-05-23","ids":{"openalex":"https://openalex.org/W2803527915","doi":"https://doi.org/10.2478/dim-2018-0004","mag":"2803527915","pmid":"https://pubmed.ncbi.nlm.nih.gov/30766970"},"language":"en","primary_location":{"id":"doi:10.2478/dim-2018-0004","is_oa":true,"landing_page_url":"https://doi.org/10.2478/dim-2018-0004","pdf_url":null,"source":{"id":"https://openalex.org/S4210174804","display_name":"Data and Information Management","issn_l":"2543-9251","issn":["2543-9251"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"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":"Data and Information Management","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.2478/dim-2018-0004","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033859037","display_name":"Neil R. Smalheiser","orcid":null},"institutions":[{"id":"https://openalex.org/I16820183","display_name":"Illinois College","ror":"https://ror.org/02ys5x139","country_code":"US","type":"education","lineage":["https://openalex.org/I16820183"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neil R. Smalheiser","raw_affiliation_strings":["Department of Psychiatry and Psychiatric Institute, University of Illinois College of Medicine, 1601 West Taylor Street, MC912, Chicago, IL 60612 neils@uic.edu +1-708-312-413-4581"],"affiliations":[{"raw_affiliation_string":"Department of Psychiatry and Psychiatric Institute, University of Illinois College of Medicine, 1601 West Taylor Street, MC912, Chicago, IL 60612 neils@uic.edu +1-708-312-413-4581","institution_ids":["https://openalex.org/I39422238","https://openalex.org/I16820183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062561557","display_name":"Aaron Cohen","orcid":"https://orcid.org/0000-0002-4610-9912"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron M. Cohen","raw_affiliation_strings":["Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, Oregon, USA 97239"],"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, Oregon, USA 97239","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033859037"],"corresponding_institution_ids":["https://openalex.org/I16820183","https://openalex.org/I39422238"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.2784,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.56662071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"27","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9783999919891357,"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":0.819179892539978},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7451943159103394},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6868420243263245},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6682809591293335},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5704986453056335},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5315190553665161},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5286412835121155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5117311477661133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4607795774936676},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3210570216178894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819179892539978},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7451943159103394},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6868420243263245},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6682809591293335},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5704986453056335},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5315190553665161},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5286412835121155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5117311477661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4607795774936676},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3210570216178894},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.2478/dim-2018-0004","is_oa":true,"landing_page_url":"https://doi.org/10.2478/dim-2018-0004","pdf_url":null,"source":{"id":"https://openalex.org/S4210174804","display_name":"Data and Information Management","issn_l":"2543-9251","issn":["2543-9251"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"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":"Data and Information Management","raw_type":"journal-article"},{"id":"pmid:30766970","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30766970","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":"Data and information management","raw_type":null},{"id":"pmh:oai:europepmc.org:5359577","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6372120","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6372120","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6372120","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Inf Manag","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.2478/dim-2018-0004","is_oa":true,"landing_page_url":"https://doi.org/10.2478/dim-2018-0004","pdf_url":null,"source":{"id":"https://openalex.org/S4210174804","display_name":"Data and Information Management","issn_l":"2543-9251","issn":["2543-9251"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"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":"Data and Information Management","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3074211143","display_name":null,"funder_award_id":"P01AG03934","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G987360809","display_name":null,"funder_award_id":"R01LM10817","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1531910981","https://openalex.org/W1570448133","https://openalex.org/W1964879903","https://openalex.org/W1982861695","https://openalex.org/W2074950806","https://openalex.org/W2076018596","https://openalex.org/W2090987348","https://openalex.org/W2098162425","https://openalex.org/W2098824882","https://openalex.org/W2122514515","https://openalex.org/W2123442489","https://openalex.org/W2133990480","https://openalex.org/W2146089916","https://openalex.org/W2184378182","https://openalex.org/W2236252949","https://openalex.org/W2251896332","https://openalex.org/W2318087363","https://openalex.org/W2356882517","https://openalex.org/W2402320467","https://openalex.org/W2413669350","https://openalex.org/W2557491692","https://openalex.org/W2585718388","https://openalex.org/W2610342131","https://openalex.org/W2738694894","https://openalex.org/W2742152190","https://openalex.org/W2751936342","https://openalex.org/W2756905860","https://openalex.org/W2911997683","https://openalex.org/W2914761779","https://openalex.org/W2950133940","https://openalex.org/W2950308091","https://openalex.org/W2963288913","https://openalex.org/W2964279163","https://openalex.org/W3102978735","https://openalex.org/W4255154157","https://openalex.org/W4294170691","https://openalex.org/W6614148910","https://openalex.org/W6637055096","https://openalex.org/W6645960730","https://openalex.org/W6675096717","https://openalex.org/W6678224444","https://openalex.org/W6682691769","https://openalex.org/W6689550495","https://openalex.org/W6691696831","https://openalex.org/W6699279265","https://openalex.org/W6733167577","https://openalex.org/W6742296221"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W4206575749"],"abstract_inverted_index":{"Many":[0],"investigators":[1],"have":[2],"carried":[3],"out":[4],"text":[5,87],"mining":[6],"of":[7,14,20,26,63,72,81,140,166,186],"the":[8,18,24,79,138,155,184],"biomedical":[9,86],"literature":[10],"for":[11,85,96,107,182],"a":[12,82,93,104,115,163,179],"variety":[13,165],"purposes,":[15],"ranging":[16],"from":[17,42,58],"assignment":[19],"indexing":[21],"terms":[22],"to":[23,33,122,147,161,189],"disambiguation":[25],"author":[27],"names.":[28],"A":[29],"common":[30],"approach":[31],"is":[32],"define":[34],"positive":[35],"and":[36,45,60,69,77,100,125,135,172,174],"negative":[37],"training":[38],"examples,":[39],"extract":[40],"features":[41],"article":[43],"metadata,":[44],"employ":[46],"machine":[47,97,148,168],"learning":[48,98,149,169],"algorithms.":[49],"At":[50],"present,":[51],"each":[52,56],"research":[53],"group":[54],"tackles":[55],"problem":[57],"scratch,":[59],"in":[61],"isolation":[62],"other":[64,167],"projects,":[65,99,173],"which":[66,89],"causes":[67],"redundancy":[68],"great":[70],"waste":[71],"effort.":[73],"Here,":[74],"we":[75],"propose":[76],"describe":[78],"design":[80],"generic":[83,156],"platform":[84,157,181],"mining,":[88],"can":[90,101,130,158,175],"serve":[91,102],"as":[92,103,145,178,191],"shared":[94],"resource":[95],"public":[105,180],"repository":[106],"their":[108],"outputs.":[109],"We":[110,151],"will":[111],"initially":[112],"focus":[113],"on":[114],"specific":[116],"goal,":[117],"namely,":[118],"classifying":[119],"articles":[120],"according":[121],"Publication":[123],"Type,":[124],"emphasize":[126],"how":[127,154],"feature":[128],"sets":[129],"be":[131,159,176],"made":[132],"more":[133],"powerful":[134],"robust":[136],"through":[137],"use":[139],"multiple,":[141],"heterogeneous":[142],"similarity":[143],"measures":[144],"input":[146],"models.":[150],"then":[152],"discuss":[153],"extended":[160],"include":[162],"wide":[164],"based":[170],"goals":[171],"used":[177],"disseminating":[183],"results":[185],"NLP":[187],"tools":[188],"end-users":[190],"well.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}