{"id":"https://openalex.org/W4366992038","doi":"https://doi.org/10.1186/s13040-023-00330-4","title":"A self-inspected adaptive SMOTE algorithm (SASMOTE) for highly imbalanced data classification in healthcare","display_name":"A self-inspected adaptive SMOTE algorithm (SASMOTE) for highly imbalanced data classification in healthcare","publication_year":2023,"publication_date":"2023-04-25","ids":{"openalex":"https://openalex.org/W4366992038","doi":"https://doi.org/10.1186/s13040-023-00330-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/37098549"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-023-00330-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-023-00330-4","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-023-00330-4","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-023-00330-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028138830","display_name":"Tanapol Kosolwattana","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tanapol Kosolwattana","raw_affiliation_strings":["Department of Industrial Engineering, University of Houston, Houston, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Houston, Houston, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003491617","display_name":"Chenang Liu","orcid":"https://orcid.org/0000-0002-6571-0682"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenang Liu","raw_affiliation_strings":["School of Industrial Engineering & Management, Oklahoma State University, Stillwater, USA"],"affiliations":[{"raw_affiliation_string":"School of Industrial Engineering & Management, Oklahoma State University, Stillwater, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045722403","display_name":"Renjie Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renjie Hu","raw_affiliation_strings":["Department of Information and Logistics Technology, University of Houston, Houston, USA"],"affiliations":[{"raw_affiliation_string":"Department of Information and Logistics Technology, University of Houston, Houston, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006266154","display_name":"Shizhong Han","orcid":"https://orcid.org/0000-0002-5114-6742"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"id":"https://openalex.org/I4210151493","display_name":"Lieber Institute for Brain Development","ror":"https://ror.org/04q36wn27","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210151493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shizhong Han","raw_affiliation_strings":["Department of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, USA","Lieber Institute for Brain Development, Baltimore, USA"],"affiliations":[{"raw_affiliation_string":"Department of Psychiatry and Behavioral Sciences, Johns Hopkins School of Medicine, Baltimore, USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Lieber Institute for Brain Development, Baltimore, USA","institution_ids":["https://openalex.org/I4210151493"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029801768","display_name":"Hua Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua Chen","raw_affiliation_strings":["Department of Pharmaceutical Health Outcomes and Policy, University of Houston, Houston, USA"],"affiliations":[{"raw_affiliation_string":"Department of Pharmaceutical Health Outcomes and Policy, University of Houston, Houston, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101505037","display_name":"Ying Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Lin","raw_affiliation_strings":["Department of Industrial Engineering, University of Houston, Houston, USA. ylin58@uh.edu","Department of Industrial Engineering, University of Houston, Houston, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, University of Houston, Houston, USA. ylin58@uh.edu","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"Department of Industrial Engineering, University of Houston, Houston, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5028138830"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":13.7312,"has_fulltext":true,"cited_by_count":78,"citation_normalized_percentile":{"value":0.99221637,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"15","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9991000294685364,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9945999979972839,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9190000295639038,"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":0.7068259716033936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5389417409896851},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.46570688486099243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41637617349624634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3470948338508606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3331069350242615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7068259716033936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5389417409896851},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.46570688486099243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41637617349624634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3470948338508606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3331069350242615},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13040-023-00330-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-023-00330-4","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-023-00330-4","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:37098549","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37098549","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":"BioData mining","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10131309","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10131309","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10131309/pdf/13040_2023_Article_330.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:01f80239ddd7418fb1740080527958fc","is_oa":true,"landing_page_url":"https://doaj.org/article/01f80239ddd7418fb1740080527958fc","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 16, Iss 1, Pp 1-14 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13040-023-00330-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-023-00330-4","pdf_url":"https://biodatamining.biomedcentral.com/counter/pdf/10.1186/s13040-023-00330-4","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","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":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G555933685","display_name":null,"funder_award_id":"R01MH121394","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"}],"funders":[{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4366992038.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W150045479","https://openalex.org/W1602160603","https://openalex.org/W1967158716","https://openalex.org/W1993220166","https://openalex.org/W2015452969","https://openalex.org/W2023639956","https://openalex.org/W2029866800","https://openalex.org/W2033184625","https://openalex.org/W2053724458","https://openalex.org/W2079115533","https://openalex.org/W2089367555","https://openalex.org/W2101156862","https://openalex.org/W2109509105","https://openalex.org/W2120491756","https://openalex.org/W2125003829","https://openalex.org/W2148143831","https://openalex.org/W2557684744","https://openalex.org/W2620563544","https://openalex.org/W2798421489","https://openalex.org/W2800788706","https://openalex.org/W2804566321","https://openalex.org/W2891018693","https://openalex.org/W2964077297","https://openalex.org/W3085184829","https://openalex.org/W3100280481","https://openalex.org/W3134537993","https://openalex.org/W3209845259","https://openalex.org/W4353095426"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"In":[0],"many":[1],"healthcare":[2,223],"applications,":[3],"datasets":[4],"for":[5,38],"classification":[6,41],"may":[7,54],"be":[8,55],"highly":[9,140,221],"imbalanced":[10,39,222],"due":[11],"to":[12,88,97,101,132,191,205,212],"the":[13,46,61,66,90,104,110,113,125,135,145,151,181,186,206,214],"rare":[14],"occurrence":[15],"of":[16,68,112,150,199,216],"target":[17],"events":[18],"such":[19],"as":[20,33],"disease":[21,177],"onset.":[22],"The":[23,148],"SMOTE":[24,53,77],"(Synthetic":[25],"Minority":[26],"Over-sampling":[27],"Technique)":[28],"algorithm":[29,87,153,188],"has":[30],"been":[31],"developed":[32],"an":[34,82,116],"effective":[35],"resampling":[36],"method":[37],"data":[40],"by":[42,52],"oversampling":[43],"samples":[44,50,99,137],"from":[45],"minority":[47,105],"class.":[48,63,106,147],"However,":[49],"generated":[51,69,114,136],"ambiguous,":[56],"low-quality":[57],"and":[58,142,160,173],"non-separable":[59],"with":[60,144,156],"majority":[62,146],"To":[64,107],"enhance":[65,109,213],"quality":[67,111,183],"samples,":[70,115,185],"we":[71],"proposed":[72,126,152,187],"a":[73],"novel":[74],"self-inspected":[75],"adaptive":[76,83],"(SASMOTE)":[78],"model":[79],"that":[80,138],"leverages":[81],"nearest":[84,92],"neighborhood":[85],"selection":[86],"identify":[89],"\"visible\"":[91],"neighbors,":[93],"which":[94,209],"are":[95,139],"used":[96],"generate":[98],"likely":[100],"fall":[102],"into":[103],"further":[108],"uncertainty":[117],"elimination":[118],"via":[119],"self-inspection":[120],"approach":[121],"is":[122,131,154,189,210],"introduced":[123],"in":[124,167],"SASMOTE":[127],"model.":[128],"Its":[129],"objective":[130],"filter":[133],"out":[134],"uncertain":[141],"inseparable":[143],"effectiveness":[149],"compared":[155,204],"existing":[157],"SMOTE-based":[158],"algorithms":[159],"demonstrated":[161],"through":[162],"two":[163],"real-world":[164],"case":[165],"studies":[166],"healthcare,":[168],"including":[169],"risk":[170],"gene":[171],"discovery":[172],"fatal":[174],"congenital":[175],"heart":[176],"prediction.":[178],"By":[179],"generating":[180],"higher":[182],"synthetic":[184],"able":[190],"help":[192],"achieve":[193],"better":[194],"prediction":[195],"performance":[196],"(in":[197],"terms":[198],"F1":[200],"score)":[201],"on":[202,220],"average":[203],"other":[207],"methods,":[208],"promising":[211],"usability":[215],"machine":[217],"learning":[218],"models":[219],"data.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":7}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}