{"id":"https://openalex.org/W4401824086","doi":"https://doi.org/10.3233/shti240382","title":"Unsupervised Extraction of Body-Text from Clinical PDF Documents","display_name":"Unsupervised Extraction of Body-Text from Clinical PDF Documents","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401824086","doi":"https://doi.org/10.3233/shti240382","pmid":"https://pubmed.ncbi.nlm.nih.gov/39176711"},"language":"en","primary_location":{"id":"doi:10.3233/shti240382","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240382","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240382","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240382","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106681578","display_name":"Adel Bensahla","orcid":null},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Adel Bensahla","raw_affiliation_strings":["Department of Radiology and Medical Informatics, University of Geneva, Switzerland","Division of Medical Information Sciences, Geneva University Hospitals, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, University of Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]},{"raw_affiliation_string":"Division of Medical Information Sciences, Geneva University Hospitals, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084199339","display_name":"Jamil Zaghir","orcid":"https://orcid.org/0000-0002-8209-6098"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jamil Zaghir","raw_affiliation_strings":["Department of Radiology and Medical Informatics, University of Geneva, Switzerland","Division of Medical Information Sciences, Geneva University Hospitals, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, University of Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]},{"raw_affiliation_string":"Division of Medical Information Sciences, Geneva University Hospitals, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083072992","display_name":"Christophe Gaudet-Blavignac","orcid":"https://orcid.org/0000-0001-6527-5898"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christophe Gaudet-Blavignac","raw_affiliation_strings":["Department of Radiology and Medical Informatics, University of Geneva, Switzerland","Division of Medical Information Sciences, Geneva University Hospitals, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, University of Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]},{"raw_affiliation_string":"Division of Medical Information Sciences, Geneva University Hospitals, Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016557721","display_name":"Christian Lovis","orcid":"https://orcid.org/0000-0002-2681-8076"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christian Lovis","raw_affiliation_strings":["Department of Radiology and Medical Informatics, University of Geneva, Switzerland","Division of Medical Information Sciences, Geneva University Hospitals, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Medical Informatics, University of Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]},{"raw_affiliation_string":"Division of Medical Information Sciences, Geneva University Hospitals, Switzerland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5106681578"],"corresponding_institution_ids":["https://openalex.org/I114457229"],"apc_list":null,"apc_paid":null,"fwci":3.7706,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92805755,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"316","issue":null,"first_page":"214","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9718999862670898,"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":0.9718999862670898,"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":0.9631999731063843,"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":0.9466000199317932,"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":0.7902040481567383},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5662513971328735},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5586684346199036},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5109726190567017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4856373369693756},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.45686671137809753},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4393472671508789},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4095415472984314},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.362693190574646},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3580330014228821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902040481567383},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5662513971328735},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5586684346199036},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5109726190567017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4856373369693756},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.45686671137809753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4393472671508789},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4095415472984314},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.362693190574646},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3580330014228821},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069558","descriptor_name":"Unsupervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti240382","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240382","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240382","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:39176711","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39176711","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":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti240382","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/shti240382","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240382","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401824086.pdf","grobid_xml":"https://content.openalex.org/works/W4401824086.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1972467623","https://openalex.org/W2007986693","https://openalex.org/W3109569233","https://openalex.org/W4401824086"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2118758177","https://openalex.org/W4330338194","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"Automatic":[0],"extraction":[1],"of":[2,32],"body-text":[3,28],"within":[4],"clinical":[5],"PDF":[6],"documents":[7],"is":[8],"necessary":[9],"to":[10,26,60,66,72],"enhance":[11],"downstream":[12],"NLP":[13],"tasks":[14],"but":[15],"remains":[16],"a":[17],"challenge.":[18],"This":[19],"study":[20],"presents":[21],"an":[22],"unsupervised":[23],"algorithm":[24],"designed":[25],"extract":[27],"leveraging":[29],"large":[30],"volume":[31],"data.":[33],"Using":[34],"DBSCAN":[35],"clustering":[36],"over":[37],"aggregate":[38],"pages,":[39],"our":[40],"method":[41],"extracts":[42],"and":[43,50,68,88],"organize":[44],"text":[45],"blocks":[46],"using":[47,89],"their":[48],"content":[49],"coordinates.":[51],"Evaluation":[52],"results":[53],"demonstrate":[54],"precision":[55],"scores":[56,63],"ranging":[57],"from":[58,64,70],"0.82":[59],"0.98,":[61],"recall":[62],"0.62":[65],"0.94,":[67],"F1-scores":[69],"0.71":[71],"0.96":[73],"across":[74],"various":[75],"medical":[76],"specialty":[77],"sources.":[78],"Future":[79],"work":[80],"includes":[81],"dynamic":[82],"parameter":[83],"adjustments":[84],"for":[85],"improved":[86],"accuracy":[87],"larger":[90],"datasets.":[91]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
