{"id":"https://openalex.org/W4390992004","doi":"https://doi.org/10.1109/bibm58861.2023.10386028","title":"Handling Imbalanced and Poorly Separated Data: a Multi-Stage Multi-Group Machine Learning Approach","display_name":"Handling Imbalanced and Poorly Separated Data: a Multi-Stage Multi-Group Machine Learning Approach","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390992004","doi":"https://doi.org/10.1109/bibm58861.2023.10386028"},"language":"en","primary_location":{"id":"doi:10.1109/bibm58861.2023.10386028","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10386028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5050619335","display_name":"Eva K. Lee","orcid":"https://orcid.org/0000-0003-0415-4640"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I132943300","display_name":"Emory Healthcare","ror":"https://ror.org/00yksxf10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I132943300"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eva K. Lee","raw_affiliation_strings":["Center for Operations Research in Medicine and Healthcare The Data and Analytics Innovation Institute,Atlanta,USA","Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, USA","Center for Operations Research in Medicine and Healthcare The Data and Analytics Innovation Institute, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Center for Operations Research in Medicine and Healthcare The Data and Analytics Innovation Institute,Atlanta,USA","institution_ids":["https://openalex.org/I132943300"]},{"raw_affiliation_string":"Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Operations Research in Medicine and Healthcare The Data and Analytics Innovation Institute, Atlanta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033255876","display_name":"Fan Yuan","orcid":"https://orcid.org/0009-0009-6990-6701"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Yuan","raw_affiliation_strings":["Georgia Institute of Technology,Industrial and Systems Engineering,Atlanta,USA","Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Industrial and Systems Engineering,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012170158","display_name":"Barton J. Mann","orcid":null},"institutions":[{"id":"https://openalex.org/I2800745293","display_name":"American Orthopaedic Society for Sports Medicine","ror":"https://ror.org/03vaf0k11","country_code":"US","type":"other","lineage":["https://openalex.org/I2800745293"]},{"id":"https://openalex.org/I1300722092","display_name":"American College of Sports Medicine","ror":"https://ror.org/02ddzr818","country_code":"US","type":"facility","lineage":["https://openalex.org/I1300722092"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barton J. Mann","raw_affiliation_strings":["The American Orthopedic Society for Sports Medicine,The American Orthopedic Society for Sports Medicine,Chicago,USA","The American Orthopedic Society for Sports Medicine, The American Orthopedic Society for Sports Medicine, Chicago, USA"],"affiliations":[{"raw_affiliation_string":"The American Orthopedic Society for Sports Medicine,The American Orthopedic Society for Sports Medicine,Chicago,USA","institution_ids":["https://openalex.org/I2800745293","https://openalex.org/I1300722092"]},{"raw_affiliation_string":"The American Orthopedic Society for Sports Medicine, The American Orthopedic Society for Sports Medicine, Chicago, USA","institution_ids":["https://openalex.org/I2800745293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080066727","display_name":"Brent M. Egan","orcid":"https://orcid.org/0000-0002-1470-5875"},"institutions":[{"id":"https://openalex.org/I173654999","display_name":"American Medical Association","ror":"https://ror.org/03p6gt485","country_code":"US","type":"other","lineage":["https://openalex.org/I173654999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Egan","raw_affiliation_strings":["American Medical Association,Cardiovascular Health,South Carolina,USA","Cardiovascular Health, American Medical Association, South Carolina, USA"],"affiliations":[{"raw_affiliation_string":"American Medical Association,Cardiovascular Health,South Carolina,USA","institution_ids":["https://openalex.org/I173654999"]},{"raw_affiliation_string":"Cardiovascular Health, American Medical Association, South Carolina, USA","institution_ids":["https://openalex.org/I173654999"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050619335"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I132943300"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19095333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"4336","last_page":"4343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9897000193595886,"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":0.9836999773979187,"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":0.6867539882659912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.555478572845459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5122329592704773},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.49703720211982727},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.44328880310058594},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10074841976165771},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06393635272979736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6867539882659912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555478572845459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5122329592704773},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.49703720211982727},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.44328880310058594},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10074841976165771},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06393635272979736},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm58861.2023.10386028","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10386028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W798021849","https://openalex.org/W1938683852","https://openalex.org/W1986718110","https://openalex.org/W2004338242","https://openalex.org/W2014915963","https://openalex.org/W2037452557","https://openalex.org/W2042442229","https://openalex.org/W2060319312","https://openalex.org/W2063978378","https://openalex.org/W2071686284","https://openalex.org/W2094768566","https://openalex.org/W2101945462","https://openalex.org/W2108488764","https://openalex.org/W2119862467","https://openalex.org/W2125213524","https://openalex.org/W2125324072","https://openalex.org/W2128759000","https://openalex.org/W2151332754","https://openalex.org/W2158492410","https://openalex.org/W2341527569","https://openalex.org/W2527824850","https://openalex.org/W2556426145","https://openalex.org/W2564156548","https://openalex.org/W2613712744","https://openalex.org/W2788630355","https://openalex.org/W2795314092","https://openalex.org/W2887355428","https://openalex.org/W2894885260","https://openalex.org/W2902802452","https://openalex.org/W2977347353","https://openalex.org/W3026915425","https://openalex.org/W3047926930","https://openalex.org/W3086548118","https://openalex.org/W3091492557","https://openalex.org/W3095012295","https://openalex.org/W3145682784","https://openalex.org/W4206802603","https://openalex.org/W4210242902","https://openalex.org/W4220711407","https://openalex.org/W4223929858","https://openalex.org/W4312531712","https://openalex.org/W4320063284","https://openalex.org/W6601949177","https://openalex.org/W6627825671","https://openalex.org/W6683548728","https://openalex.org/W6704626538","https://openalex.org/W6771659168","https://openalex.org/W6784000060"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Poorly":[0],"separated":[1,53,180,202],"data":[2,5,54,181,205],"and":[3,17,155,182,203,207],"imbalanced":[4,81,183,204],"present":[6],"major":[7],"challenges":[8],"to":[9,58,77,91,122,138,164],"classifiers":[10,188],"which":[11,32,186],"often":[12],"result":[13],"in":[14,19,31,152,185],"lower":[15],"accuracy":[16,192],"reliability":[18],"making":[20],"predictions.":[21],"In":[22],"this":[23,132],"paper,":[24],"we":[25],"introduce":[26],"the":[27,72,87,96,101,124,127,171,200],"multi-stage":[28,133,197],"classification":[29],"construct":[30],"\u2018difficult-to-classify\u2019":[33],"observations":[34],"are":[35,56],"placed":[36],"into":[37,86,95],"a":[38,47,62,104],"reserved":[39,88],"judgment":[40],"region":[41,90],"for":[42,51,148,170],"delayed":[43],"future":[44],"classification.":[45],"Such":[46],"design":[48],"is":[49,119],"well-suited":[50],"poorly":[52,179,201],"that":[55,160],"difficult":[57],"classify":[59],"without":[60],"committing":[61],"high":[63],"percentage":[64],"of":[65,80,126,167,173],"misclassification":[66,69],"errors.":[67],"The":[68,196],"constraints":[70],"within":[71],"classifier":[73,102],"can":[74],"be":[75],"finetuned":[76],"allow":[78],"management":[79],"data,":[82],"guiding":[83],"minority":[84],"entities":[85],"judgement":[89],"avoid":[92],"being":[93],"misclassified":[94],"majority":[97],"groups.":[98],"We":[99,130],"wrap":[100],"with":[103,211],"fast":[105],"feature":[106],"selection":[107],"heuristic":[108,128],"based":[109],"on":[110],"particle":[111],"swarm":[112],"optimization.":[113],"An":[114],"exact":[115],"combinatorial":[116],"branch-and-bound":[117],"algorithm":[118],"also":[120],"implemented":[121],"measure":[123],"quality":[125],"solutions.":[129],"apply":[131],"multi-group":[134],"machine":[135],"learning":[136],"framework":[137],"two":[139],"real-life":[140],"medical":[141],"problems:":[142],"(a)":[143],"multi-site":[144],"treatment":[145,172],"outcome":[146],"prediction":[147,191,216],"best":[149],"practice":[150],"discovery":[151],"cardiovascular":[153],"disease,":[154],"(b)":[156],"uncovering":[157],"patient":[158],"characteristics":[159],"predict":[161],"optimal":[162],"response":[163],"intra-articular":[165],"injections":[166],"hyaluronic":[168],"acid":[169],"knee":[174],"osteoarthritis.":[175],"Both":[176],"problems":[177],"involve":[178],"groups":[184],"traditional":[187],"yield":[189],"low":[190],"(47%":[193],"-":[194,213],"66%).":[195],"BB-PSO/DAMIP":[198],"manages":[199],"well":[206],"returns":[208],"interpretable":[209],"results":[210],"82%":[212],"97%":[214],"blind":[215],"accuracy.":[217]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}