{"id":"https://openalex.org/W4360979661","doi":"https://doi.org/10.1007/s11634-023-00537-7","title":"Identification of representative trees in random forests based on a new tree-based distance measure","display_name":"Identification of representative trees in random forests based on a new tree-based distance measure","publication_year":2023,"publication_date":"2023-03-16","ids":{"openalex":"https://openalex.org/W4360979661","doi":"https://doi.org/10.1007/s11634-023-00537-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11634-023-00537-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11634-023-00537-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11634-023-00537-7.pdf","source":{"id":"https://openalex.org/S4210175730","display_name":"Advances in Data Analysis and Classification","issn_l":"1862-5347","issn":["1862-5347","1862-5355"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Data Analysis and Classification","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11634-023-00537-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035463841","display_name":"Bj\u00f6rn\u2010Hergen Laabs","orcid":"https://orcid.org/0000-0002-9265-5738"},"institutions":[{"id":"https://openalex.org/I4210112713","display_name":"University Hospital Schleswig-Holstein","ror":"https://ror.org/01tvm6f46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210112713"]},{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bj\u00f6rn-Hergen Laabs","raw_affiliation_strings":["Institute of Medical Biometry and Statistics, Universit\u00e4tsklinikum Schleswig-Holstein, University of L\u00fcbeck, Campus L\u00fcbeck, Ratzeburger Allee 160, Building V24, 23562, L\u00fcbeck, Germany"],"raw_orcid":"https://orcid.org/0000-0002-9265-5738","affiliations":[{"raw_affiliation_string":"Institute of Medical Biometry and Statistics, Universit\u00e4tsklinikum Schleswig-Holstein, University of L\u00fcbeck, Campus L\u00fcbeck, Ratzeburger Allee 160, Building V24, 23562, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345","https://openalex.org/I4210112713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023320301","display_name":"Ana Westenberger","orcid":"https://orcid.org/0000-0001-8062-6959"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ana Westenberger","raw_affiliation_strings":["Institute of Neurogenetics, University of L\u00fcbeck, Ratzeburger Allee 160, BMF, Building 67, 23562, L\u00fcbeck, S-H, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neurogenetics, University of L\u00fcbeck, Ratzeburger Allee 160, BMF, Building 67, 23562, L\u00fcbeck, S-H, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024750728","display_name":"Inke R. K\u00f6nig","orcid":"https://orcid.org/0000-0003-0504-6465"},"institutions":[{"id":"https://openalex.org/I4210112713","display_name":"University Hospital Schleswig-Holstein","ror":"https://ror.org/01tvm6f46","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210112713"]},{"id":"https://openalex.org/I4210127591","display_name":"German Centre for Cardiovascular Research","ror":"https://ror.org/031t5w623","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127591","https://openalex.org/I4405256427"]},{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Inke R. K\u00f6nig","raw_affiliation_strings":["German Center for Cardiovascular Research (DZHK), Partner Site Hamburg/Kiel/L\u00fcbeck, Ratzeburger Allee 160, 23562, L\u00fcbeck, S-H, Germany","Institute of Medical Biometry and Statistics, Universit\u00e4tsklinikum Schleswig-Holstein, University of L\u00fcbeck, Campus L\u00fcbeck, Ratzeburger Allee 160, Building V24, 23562, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Center for Cardiovascular Research (DZHK), Partner Site Hamburg/Kiel/L\u00fcbeck, Ratzeburger Allee 160, 23562, L\u00fcbeck, S-H, Germany","institution_ids":["https://openalex.org/I4210127591"]},{"raw_affiliation_string":"Institute of Medical Biometry and Statistics, Universit\u00e4tsklinikum Schleswig-Holstein, University of L\u00fcbeck, Campus L\u00fcbeck, Ratzeburger Allee 160, Building V24, 23562, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345","https://openalex.org/I4210112713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035463841"],"corresponding_institution_ids":["https://openalex.org/I4210112713","https://openalex.org/I9341345"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":3.6634,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93104566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"18","issue":"2","first_page":"363","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10885","display_name":"Gene expression and cancer classification","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.7649315595626831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6388022899627686},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6138414144515991},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6090367436408997},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5851064920425415},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5625459551811218},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5412096977233887},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5171427130699158},{"id":"https://openalex.org/keywords/distance-matrices-in-phylogeny","display_name":"Distance matrices in phylogeny","score":0.4729430675506592},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4672270715236664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45917749404907227},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4411211311817169},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4287862181663513},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.4239428639411926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3720857799053192},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28405383229255676},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24836322665214539},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2331681251525879},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.1441079080104828},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.11049070954322815},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09331446886062622}],"concepts":[{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.7649315595626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388022899627686},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6138414144515991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6090367436408997},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5851064920425415},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5625459551811218},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5412096977233887},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5171427130699158},{"id":"https://openalex.org/C5349765","wikidata":"https://www.wikidata.org/wiki/Q5282866","display_name":"Distance matrices in phylogeny","level":2,"score":0.4729430675506592},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4672270715236664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45917749404907227},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4411211311817169},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4287862181663513},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4239428639411926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3720857799053192},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28405383229255676},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24836322665214539},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2331681251525879},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.1441079080104828},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.11049070954322815},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09331446886062622},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11634-023-00537-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11634-023-00537-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11634-023-00537-7.pdf","source":{"id":"https://openalex.org/S4210175730","display_name":"Advances in Data Analysis and Classification","issn_l":"1862-5347","issn":["1862-5347","1862-5355"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Data Analysis and Classification","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:spr:advdac:v:18:y:2024:i:2:d:10.1007_s11634-023-00537-7","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s11634-023-00537-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s11634-023-00537-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11634-023-00537-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11634-023-00537-7.pdf","source":{"id":"https://openalex.org/S4210175730","display_name":"Advances in Data Analysis and Classification","issn_l":"1862-5347","issn":["1862-5347","1862-5355"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Data Analysis and Classification","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G6521337214","display_name":null,"funder_award_id":"FOR 2488","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4360979661.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1875061881","https://openalex.org/W1984510790","https://openalex.org/W2049966877","https://openalex.org/W2051483504","https://openalex.org/W2052825782","https://openalex.org/W2104543942","https://openalex.org/W2123998733","https://openalex.org/W2128018695","https://openalex.org/W2157395790","https://openalex.org/W2330820318","https://openalex.org/W2549551440","https://openalex.org/W2626923045","https://openalex.org/W2722517739","https://openalex.org/W2773105219","https://openalex.org/W2782176193","https://openalex.org/W2802643674","https://openalex.org/W2803082463","https://openalex.org/W2889306081","https://openalex.org/W2911964244","https://openalex.org/W2937786795","https://openalex.org/W2953079191","https://openalex.org/W2986932567","https://openalex.org/W3043513630","https://openalex.org/W3102027041","https://openalex.org/W3126961613","https://openalex.org/W3165152327","https://openalex.org/W4212883601","https://openalex.org/W4288076644","https://openalex.org/W4388012970"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2321234655","https://openalex.org/W2065444835","https://openalex.org/W4366990902","https://openalex.org/W4317732970","https://openalex.org/W4388550696","https://openalex.org/W4321636153","https://openalex.org/W4313289487"],"abstract_inverted_index":{"Abstract":[0],"In":[1,163],"life":[2],"sciences,":[3],"random":[4,34],"forests":[5,35],"are":[6,87,188],"often":[7],"used":[8],"to":[9,22,47,56,59,78,93,144,170,192],"train":[10],"predictive":[11],"models.":[12],"However,":[13],"gaining":[14],"any":[15],"explanatory":[16],"insight":[17],"into":[18,36],"the":[19,31,64,90,103,120,133,146,172,194,209,227],"mechanics":[20],"leading":[21],"a":[23,41,48,99,111,152,159,197],"specific":[24,67],"outcome":[25],"is":[26,54],"rather":[27],"complex,":[28],"which":[29,97,116],"impedes":[30],"implementation":[32],"of":[33,44,66,102,119,154,174,208],"clinical":[37,160],"practice.":[38],"By":[39],"simplifying":[40],"complex":[42],"ensemble":[43],"decision":[45],"trees":[46,74,86,187],"single":[49],"most":[50],"representative":[51,73,85,186],"tree,":[52],"it":[53,143],"assumed":[55],"be":[57],"possible":[58],"observe":[60],"common":[61],"tree":[62,122],"structures,":[63],"importance":[65],"features":[68],"and":[69,141,221],"variable":[70,178],"interactions.":[71],"Thus,":[72,108],"could":[75],"also":[76,203],"help":[77],"understand":[79],"interactions":[80],"between":[81,105],"genetic":[82,155,210],"variants.":[83],"Intuitively,":[84],"those":[88],"with":[89,132],"minimal":[91],"distance":[92,104,114,217],"all":[94,215],"other":[95,125],"trees,":[96],"requires":[98],"proper":[100],"definition":[101],"two":[106],"trees.":[107],"we":[109,167,213],"developed":[110],"new":[112,130],"tree-based":[113],"measure,":[115],"incorporates":[117],"more":[118],"underlying":[121],"structure":[123],"than":[124],"metrics.":[126],"We":[127],"compared":[128,216],"our":[129,164,175],"method":[131],"existing":[134],"metrics":[135],"in":[136,158,219,226],"an":[137],"extensive":[138],"simulation":[139,165],"study":[140,166],"applied":[142],"predict":[145],"age":[147],"at":[148],"onset":[149],"based":[150],"on":[151],"set":[153],"risk":[156],"factors":[157],"data":[161,182],"set.":[162],"were":[168],"able":[169,191],"show":[171],"advantages":[173],"weighted":[176],"splitting":[177],"approach.":[179],"Our":[180],"real":[181],"application":[183],"revealed":[184],"that":[185],"not":[189],"only":[190],"replicate":[193],"results":[195],"from":[196],"recent":[198],"genome-wide":[199],"association":[200],"study,":[201],"but":[202],"can":[204],"give":[205],"additional":[206],"explanations":[207],"mechanisms.":[211],"Finally,":[212],"implemented":[214],"measures":[218],"R":[220,228],"made":[222],"them":[223],"publicly":[224],"available":[225],"package":[229],"timbR":[230],"(":[231],"https://github.com/imbs-hl/timbR":[232],").":[233]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}