{"id":"https://openalex.org/W142736962","doi":"https://doi.org/10.3233/978-1-61499-289-9-52","title":"Taming EHR data: Using Semantic Similarity to reduce Dimensionality","display_name":"Taming EHR data: Using Semantic Similarity to reduce Dimensionality","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W142736962","doi":"https://doi.org/10.3233/978-1-61499-289-9-52","mag":"142736962","pmid":"https://pubmed.ncbi.nlm.nih.gov/23920514"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-289-9-52","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-289-9-52","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","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/A5073006660","display_name":"Leila R Kalankesh","orcid":"https://orcid.org/0000-0002-4832-3170"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kalankesh Leila","raw_affiliation_strings":["School of Computer Science, University of Manchester, Manchester M13 9PL, UK"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester M13 9PL, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102823160","display_name":"James Weatherall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weatherall James","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068910485","display_name":"Thamer Ba Dhafari","orcid":"https://orcid.org/0000-0002-8653-7874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ba-Dhfari Thamer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011177296","display_name":"Iain Buchan","orcid":"https://orcid.org/0000-0003-3392-1650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buchan Iain","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016572574","display_name":"Andy Brass","orcid":"https://orcid.org/0000-0002-0389-7058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brass Andy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073006660"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.5667,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67125602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"192","issue":null,"first_page":"52","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9987000226974487,"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":0.9987000226974487,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9965999722480774,"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/T11719","display_name":"Data Quality and Management","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146704196929932},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6203909516334534},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5934222340583801},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.554267168045044},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47966837882995605},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4741601049900055},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4644133746623993},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4466356635093689},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.4214613735675812},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.41925734281539917},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38763895630836487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27674514055252075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146704196929932},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6203909516334534},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5934222340583801},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.554267168045044},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47966837882995605},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4741601049900055},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4644133746623993},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4466356635093689},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.4214613735675812},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.41925734281539917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38763895630836487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27674514055252075},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":"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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006113","descriptor_name":"United Kingdom","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":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011320","descriptor_name":"Primary Health Care","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","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":"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":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.3233/978-1-61499-289-9-52","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-289-9-52","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:23920514","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23920514","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},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/53424f71-8273-4950-8e7c-15c382eb097c","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/53424f71-8273-4950-8e7c-15c382eb097c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kalankesh, L, Weatherall, J, Ba-Dhfari, T, Buchan, I & Brass, A 2013, Taming EHR data: Using semantic similarity to reduce dimensionality. in Studies in Health Technology and Informatics|Stud. Health Technol. Informatics. vol. 192, pp. 52-56, 14th World Congress on Medical and Health Informatics, MEDINFO 2013, Copenhagen, 1/07/13. https://doi.org/10.3233/978-1-61499-289-9-52","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/92ca581b-6977-4c35-88bd-21b99128bc92","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/92ca581b-6977-4c35-88bd-21b99128bc92","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kalankesh, L, Weatherall, J, Ba-Dhfari, T, Buchan, I & Brass, A 2013, 'Taming EHR data: Using semantic similarity to reduce dimensionality', Studies in Health Technology and Informatics, vol. 192, no. 1-2, pp. 52-56. https://doi.org/10.3233/978-1-61499-289-9-52","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7346109562","display_name":null,"funder_award_id":"MC_PC_13042","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W164479219","https://openalex.org/W1647729745","https://openalex.org/W1659833910","https://openalex.org/W2033945449","https://openalex.org/W2038721957","https://openalex.org/W2057651652","https://openalex.org/W2072640685","https://openalex.org/W2079665010","https://openalex.org/W2084168100","https://openalex.org/W2120539430","https://openalex.org/W2121239054","https://openalex.org/W2123982464","https://openalex.org/W2127563440","https://openalex.org/W2128135822","https://openalex.org/W2167950733","https://openalex.org/W2580330696"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W2068608913","https://openalex.org/W4405554013","https://openalex.org/W2561617217","https://openalex.org/W2025378473","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2355801475","https://openalex.org/W2003333417","https://openalex.org/W2156434174"],"abstract_inverted_index":{"Medical":[0],"care":[1,69,122,140],"data":[2,34,41,51,101,119,141,163],"is":[3],"a":[4,61,87],"valuable":[5],"resource":[6],"that":[7,63,135],"can":[8,35,142],"be":[9,36,143],"used":[10,144],"for":[11,18],"many":[12],"purposes":[13],"including":[14],"managing":[15],"and":[16,30,81,93,105,165],"planning":[17],"future":[19],"health":[20],"needs":[21],"as":[22,24],"well":[23],"clinical":[25],"research.":[26],"However,":[27],"the":[28,46,65,100,111,158],"heterogeneity":[29],"complexity":[31],"of":[32,45,49,67,89,128,131],"medical":[33,166],"an":[37,103,149],"obstacle":[38],"in":[39,71,123,138,155],"applying":[40],"mining":[42,80],"techniques.":[43],"Much":[44],"potential":[47],"value":[48],"this":[50,56,132],"therefore":[52],"goes":[53],"untapped.":[54],"In":[55],"paper":[57],"we":[58,113],"have":[59],"developed":[60],"methodology":[62,84,133],"reduces":[64],"dimensionality":[66],"primary":[68,121,139],"data,":[70],"order":[72],"to":[73,78,98,116,145,160],"make":[74],"it":[75],"more":[76],"amenable":[77],"visualisation,":[79],"clustering.":[82],"The":[83,126],"involves":[85],"employing":[86],"combination":[88],"ontology-based":[90],"semantic":[91],"similarity":[92],"principal":[94],"component":[95],"analysis":[96],"(PCA)":[97],"map":[99,146],"into":[102,148],"appropriate":[104],"informative":[106,150],"low":[107,151],"dimensional":[108,152],"space.":[109],"Throughout":[110],"study,":[112],"had":[114],"access":[115],"anonymised":[117],"patient":[118],"from":[120],"Salford,":[124],"UK.":[125],"results":[127],"our":[129],"application":[130],"show":[134],"diagnosis":[136],"codes":[137],"patients":[147],"space,":[153],"which":[154],"turn":[156],"provides":[157],"opportunity":[159],"support":[161],"further":[162],"exploration":[164],"hypothesis":[167],"formulation.":[168]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}