{"id":"https://openalex.org/W209945127","doi":null,"title":"Improving machine learning performance by removing redundant cases in medical data sets.","display_name":"Improving machine learning performance by removing redundant cases in medical data sets.","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W209945127","mag":"209945127","pmid":"https://pubmed.ncbi.nlm.nih.gov/9929274","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/2232167"},"language":"en","primary_location":{"id":"pmh:oai:pubmedcentral.nih.gov:2232167","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2232167","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proc AMIA Symp","raw_type":"Text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2232167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084415954","display_name":"Lucila Ohno-machado A","orcid":"https://orcid.org/0000-0002-8005-7327","observed_orcids":["https://orcid.org/0000-0002-8005-7327"]},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I121934306","https://openalex.org/I1283280774","https://openalex.org/I48633490"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L Ohno-Machado","raw_affiliation_strings":["Decision Systems Group, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. machado@dsg.harvard.edu","Decision Systems Group, Brigham & Women's Hospital, Harvard Medical School, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Decision Systems Group, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. machado@dsg.harvard.edu","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Decision Systems Group, Brigham & Women's Hospital, Harvard Medical School, Boston, MA, USA","institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025062637","display_name":"Hamish Fraser","orcid":"https://orcid.org/0000-0003-4383-2854","observed_orcids":["https://orcid.org/0000-0003-4383-2854"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H S Fraser","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004184219","display_name":"Aleksander \u00d8hrn","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A Ohrn","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1061,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9345363,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"523","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.8320000171661377,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.8320000171661377,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.16359999775886536,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0010000000474974513,"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/training-set-reduction","display_name":"training data reduction","score":0.7599999904632568},{"id":"https://openalex.org/keywords/neural-network-training","display_name":"neural network training","score":0.7450000047683716},{"id":"https://openalex.org/keywords/training-time-reduction","display_name":"training time reduction","score":0.6629999876022339},{"id":"https://openalex.org/keywords/myocardial-infarction-classification","display_name":"myocardial infarction classification","score":0.8370000123977661},{"id":"https://openalex.org/keywords/medical-classification","display_name":"medical classification","score":0.6850000023841858},{"id":"https://openalex.org/keywords/roc-curve","display_name":"ROC curve","score":0.42899999022483826},{"id":"https://openalex.org/keywords/model-retraining","display_name":"model retraining","score":0.5640000104904175}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7433404922485352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6462886333465576},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.6180728673934937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.567035436630249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5380489230155945},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5306569337844849},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5130711793899536},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5110646486282349},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4449194371700287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42697712779045105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3965877294540405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1611708700656891},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","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":"D009203","descriptor_name":"Myocardial Infarction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011897","descriptor_name":"Random Allocation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012372","descriptor_name":"ROC Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019992","descriptor_name":"Databases as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"pmh:oai:pubmedcentral.nih.gov:2232167","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2232167","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proc AMIA Symp","raw_type":"Text"},{"id":"pmid:9929274","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9929274","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,"listed_in":[],"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":"Proceedings. AMIA Symposium","raw_type":"Journal Article"},{"id":"mag:209945127","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/9929274","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:2232167","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2232167","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proc AMIA Symp","raw_type":"Text"},"sustainable_development_goals":[{"score":0.8560000061988831,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1840075983","display_name":"ARTIFICIAL INTELLIGENCE CARDIOVASCULAR REASONING","funder_award_id":"R01HL033041","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G7732953174","display_name":"COMPONENT BASED TOOLS FOR CONNECTIONIST CLASSIFICATION","funder_award_id":"R01LM006538","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1554663460","https://openalex.org/W1975004696","https://openalex.org/W2117812871","https://openalex.org/W2154642048","https://openalex.org/W2157825442"],"related_works":["https://openalex.org/W4414788132","https://openalex.org/W155856866","https://openalex.org/W141826324","https://openalex.org/W1899549042","https://openalex.org/W4210463075","https://openalex.org/W1967278609","https://openalex.org/W1561979193","https://openalex.org/W7222794992","https://openalex.org/W3171352319","https://openalex.org/W2477116617"],"abstract_inverted_index":{"Neural":[0],"network":[1,151],"models":[2,18],"and":[3,23,96,124],"other":[4],"machine":[5],"learning":[6],"methods":[7],"have":[8],"successfully":[9],"been":[10],"applied":[11],"to":[12,147],"several":[13],"medical":[14],"classification":[15,72,105],"problems.":[16],"These":[17],"can":[19],"be":[20,49,59,67],"periodically":[21],"refined":[22],"retrained":[24],"as":[25,128,130],"new":[26],"cases":[27,48,57,65,134],"become":[28],"available.":[29],"Since":[30],"training":[31,53],"neural":[32,150],"networks":[33],"by":[34,108],"backpropagation":[35],"is":[36,40,74,100,153],"time":[37,145],"consuming,":[38],"it":[39],"desirable":[41],"that":[42,71,98],"a":[43,85],"minimum":[44],"number":[45],"of":[46,63,88,92,122,132,144],"representative":[47],"kept":[50],"in":[51,104,111,141],"the":[52,109,114,133,142,149],"set":[54,87],"(i.e.,":[55],"redundant":[56,64],"should":[58,66],"removed).":[60],"The":[61],"removal":[62,83],"carefully":[68],"monitored":[69],"so":[70],"performance":[73,106],"not":[75],"significantly":[76],"affected.":[77],"We":[78],"made":[79],"experiments":[80],"on":[81,84,117],"data":[82,86],"700":[89],"patients":[90],"suspected":[91],"having":[93],"myocardial":[94],"infarction":[95],"show":[97],"there":[99],"no":[101],"statistical":[102],"difference":[103],"(measured":[107],"differences":[110],"areas":[112],"under":[113],"ROC":[115],"curve":[116],"two":[118],"previously":[119],"unknown":[120],"sets":[121],"553":[123],"500":[125],"cases)":[126],"when":[127],"many":[129],"86%":[131],"are":[135],"randomly":[136],"removed.":[137],"A":[138],"proportional":[139],"reduction":[140],"amount":[143],"required":[146],"train":[148],"model":[152],"achieved.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}