{"id":"https://openalex.org/W4401825156","doi":"https://doi.org/10.3233/shti240520","title":"Pre-Processing of Categorical Features Within Medical Analysis Systems","display_name":"Pre-Processing of Categorical Features Within Medical Analysis Systems","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401825156","doi":"https://doi.org/10.3233/shti240520","pmid":"https://pubmed.ncbi.nlm.nih.gov/39176901"},"language":"en","primary_location":{"id":"doi:10.3233/shti240520","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti240520","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240520","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/SHTI240520","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106681960","display_name":"Marc Hermes","orcid":null},"institutions":[{"id":"https://openalex.org/I202367325","display_name":"Oldenburger Institut f\u00fcr Informatik","ror":"https://ror.org/003sav189","country_code":"DE","type":"facility","lineage":["https://openalex.org/I202367325"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Hermes","raw_affiliation_strings":["Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany","institution_ids":["https://openalex.org/I202367325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083180525","display_name":"Timo Wolters","orcid":null},"institutions":[{"id":"https://openalex.org/I202367325","display_name":"Oldenburger Institut f\u00fcr Informatik","ror":"https://ror.org/003sav189","country_code":"DE","type":"facility","lineage":["https://openalex.org/I202367325"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Wolters","raw_affiliation_strings":["Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany","institution_ids":["https://openalex.org/I202367325"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108973428","display_name":"Nico Schult","orcid":null},"institutions":[{"id":"https://openalex.org/I202367325","display_name":"Oldenburger Institut f\u00fcr Informatik","ror":"https://ror.org/003sav189","country_code":"DE","type":"facility","lineage":["https://openalex.org/I202367325"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nico Schult","raw_affiliation_strings":["Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany","institution_ids":["https://openalex.org/I202367325"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060354161","display_name":"Andreas Hein","orcid":"https://orcid.org/0000-0001-8846-2282"},"institutions":[{"id":"https://openalex.org/I202367325","display_name":"Oldenburger Institut f\u00fcr Informatik","ror":"https://ror.org/003sav189","country_code":"DE","type":"facility","lineage":["https://openalex.org/I202367325"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Hein","raw_affiliation_strings":["Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division Health, OFFIS \u2013 Institute for Information Technology, Escherweg 2, Oldenburg, Germany","institution_ids":["https://openalex.org/I202367325"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I202367325"],"apc_list":null,"apc_paid":null,"fwci":0.9004,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80196035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"316","issue":null,"first_page":"741","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9997000098228455,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9833999872207642,"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":0.8201634287834167},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7877464294433594},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7112863659858704},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5567886233329773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5382999777793884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4935725927352905},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4789769649505615},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4685044586658478},{"id":"https://openalex.org/keywords/cohesion","display_name":"Cohesion (chemistry)","score":0.43582063913345337},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34402191638946533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33758580684661865},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3137819170951843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201634287834167},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7877464294433594},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7112863659858704},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5567886233329773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382999777793884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4935725927352905},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4789769649505615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4685044586658478},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.43582063913345337},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34402191638946533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33758580684661865},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3137819170951843},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti240520","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti240520","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240520","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:39176901","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39176901","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/shti240520","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti240520","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI240520","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":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401825156.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W161970714","https://openalex.org/W2052803671","https://openalex.org/W2106316877","https://openalex.org/W2161633277","https://openalex.org/W2517346518","https://openalex.org/W2626498001","https://openalex.org/W3003804390","https://openalex.org/W3159243351","https://openalex.org/W4231510805","https://openalex.org/W4321122166"],"related_works":["https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"The":[0,188],"complexity":[1],"of":[2,25,101,108,121,126,190,232],"the":[3,12,23,55,81,86,99,106,122,142,169,195,212,230],"cancer":[4],"problem":[5,241],"domain":[6],"presents":[7],"challenges":[8],"not":[9],"only":[10],"to":[11,22,32,72,79,116,133,153,168],"medical":[13,38,88],"analysis":[14,39,89,237],"systems":[15,238],"tasked":[16],"with":[17,148,178],"its":[18],"analysis,":[19],"but":[20],"also":[21],"users":[24,34,57,234],"such":[26,50],"systems.":[27,63],"While":[28],"it":[29,164],"is":[30,43,96,200],"desirable":[31],"assist":[33],"in":[35,54,146,229,235,239],"operating":[36,236],"these":[37,62,102,127,159],"systems,":[40],"prior":[41],"groundwork":[42],"required":[44],"before":[45],"this":[46,65,175],"can":[47],"be":[48],"achieved,":[49],"as":[51,165],"recognising":[52],"patterns":[53,76],"way":[56],"create":[58],"certain":[59],"analyses":[60],"within":[61,85],"In":[64],"paper,":[66],"we":[67,104,131],"use":[68,134,163,209],"machine":[69,170],"learning":[70,171],"algorithms":[71],"analyse":[73],"user":[74,83,128,144],"behaviour":[75],"and":[77,162,185,227],"attempt":[78],"predict":[80],"next":[82],"interaction":[84],"CARESS":[87],"system.":[90],"Since":[91],"an":[92,221],"appropriate":[93],"pre-processing":[94,176,215],"scheme":[95,177,199],"essential":[97],"for":[98,207,224],"performance":[100],"algorithms,":[103],"propose":[105,132],"usage":[107],"a":[109,135,155,201],"Natural":[110],"Language":[111],"Processing":[112],"(NLP)-":[113],"inspired":[114],"approach":[115],"preserve":[117],"some":[118],"semantic":[119],"cohesion":[120],"mostly":[123],"categorical":[124],"features":[125],"interactions.":[129],"Furthermore,":[130],"sliding":[136,196],"window":[137,197],"that":[138,181,194,204],"contains":[139],"information":[140],"about":[141],"latest":[143],"interactions":[145,161],"combination":[147],"Latent":[149],"Dirichlet":[150],"Allocation":[151],"(LDA)":[152],"extract":[154],"latent":[156],"topic":[157],"from":[158],"last":[160],"additional":[166],"input":[167],"models.":[172],"We":[173],"compare":[174],"other":[179,213],"approaches":[180],"utilise":[182],"one-hot":[183],"encoding":[184],"feature":[186],"hashing.":[187],"results":[189,219],"our":[191,208,218],"experiments":[192],"show":[193],"LDA":[198],"promising":[202],"solution,":[203],"performs":[205],"better":[206],"case":[210],"than":[211],"evaluated":[214],"schemes.":[216],"Overall,":[217],"provide":[220],"important":[222],"piece":[223],"further":[225],"research":[226],"development":[228],"area":[231],"assisting":[233],"complex":[240],"domains.":[242]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}