{"id":"https://openalex.org/W4288049623","doi":"https://doi.org/10.1145/3524383.3524439","title":"Data Preparation: A Comparative Analysis of the Fill-in Methods for Handling Missing Data in Clinical Laboratory Datasets","display_name":"Data Preparation: A Comparative Analysis of the Fill-in Methods for Handling Missing Data in Clinical Laboratory Datasets","publication_year":2022,"publication_date":"2022-02-26","ids":{"openalex":"https://openalex.org/W4288049623","doi":"https://doi.org/10.1145/3524383.3524439"},"language":"en","primary_location":{"id":"doi:10.1145/3524383.3524439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524383.3524439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Big Data and Education","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/A5000757683","display_name":"Melody Angelique Camba Rivera","orcid":null},"institutions":[{"id":"https://openalex.org/I99714305","display_name":"Silliman University","ror":"https://ror.org/01ry6r150","country_code":"PH","type":"education","lineage":["https://openalex.org/I99714305"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Melody Angelique Camba Rivera","raw_affiliation_strings":["College of Computer Studies, Silliman University, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Studies, Silliman University, Philippines","institution_ids":["https://openalex.org/I99714305"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008863173","display_name":"Jennifer T. Carpio","orcid":null},"institutions":[{"id":"https://openalex.org/I3129998261","display_name":"University of Makati","ror":"https://ror.org/00473rv55","country_code":"PH","type":"education","lineage":["https://openalex.org/I3129998261"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Jennifer Torres Carpio","raw_affiliation_strings":["University of Makati, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Makati, Philippines","institution_ids":["https://openalex.org/I3129998261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010018203","display_name":"Albert A. Vinluan","orcid":"https://orcid.org/0009-0001-4570-1391"},"institutions":[{"id":"https://openalex.org/I148212101","display_name":"New Era University","ror":"https://ror.org/05pc6nk51","country_code":"PH","type":"education","lineage":["https://openalex.org/I148212101"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Albert Alcause Vinluan","raw_affiliation_strings":["New Era University, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Era University, Philippines","institution_ids":["https://openalex.org/I148212101"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0866,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42505701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"412","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.972000002861023,"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"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.972000002861023,"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"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9642999768257141,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9574999809265137,"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/missing-data","display_name":"Missing data","score":0.900538444519043},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.7180502414703369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6984037756919861},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6522210836410522},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34638670086860657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19868019223213196}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.900538444519043},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.7180502414703369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984037756919861},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6522210836410522},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34638670086860657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19868019223213196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524383.3524439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524383.3524439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Big Data and Education","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2395405573","https://openalex.org/W2558231871","https://openalex.org/W2595582532","https://openalex.org/W2766807015","https://openalex.org/W2772803673","https://openalex.org/W2800989161","https://openalex.org/W2903698441","https://openalex.org/W2947334711","https://openalex.org/W2980806155","https://openalex.org/W3080967847","https://openalex.org/W3096847176"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516","https://openalex.org/W2581984549"],"abstract_inverted_index":{"Missing":[0],"data":[1,20,51],"has":[2],"been":[3,22],"a":[4,118,174],"challenge":[5],"for":[6,185],"research":[7],"work,":[8],"especially":[9],"in":[10,123,176],"the":[11,32,39,62,67,72,106,124,130,137,144,154],"medical":[12],"field.":[13],"Several":[14],"methods":[15],"to":[16,29,65,121],"deal":[17],"with":[18,109,143,147],"missing":[19,50,110,125],"have":[21],"recommended,":[23],"from":[24,94],"removing":[25],"rows":[26],"or":[27],"columns":[28],"imputation.":[30],"Determining":[31],"appropriate":[33],"method":[34,120],"will":[35,45,52,115,140],"need":[36],"identification":[37],"of":[38,61,77],"data's":[40],"missingness":[41],"mechanism.":[42],"This":[43],"study-in-progress":[44],"compare":[46],"several":[47],"datasets":[48,146],"whose":[49],"be":[53,116,141,162],"imputed":[54,148],"using":[55],"different":[56],"fill-in":[57],"methods.":[58],"The":[59],"purpose":[60],"comparison":[63],"is":[64],"determine":[66],"dataset":[68,108,113,139],"that":[69,160],"can":[70],"produce":[71],"most":[73],"distinct":[74],"latent":[75],"classes":[76],"non-communicable":[78],"disease":[79],"(NCD)":[80],"comorbidity":[81,180],"when":[82],"passed":[83,128],"through":[84,129],"Latent":[85],"Class":[86],"Analysis":[87],"(LCA).":[88],"Data":[89],"were":[90,100],"extracted":[91],"and":[92,104,134,157,168,182],"integrated":[93],"two":[95],"clinical":[96],"laboratories.":[97],"Dataset":[98],"copies":[99],"produced":[101],"after":[102],"de-identifying":[103],"cleaning":[105],"original":[107,138],"values.":[111,126,149],"Each":[112],"copy":[114],"assigned":[117],"specific":[119],"fill":[122],"When":[127],"LCA":[131,155],"model":[132,156],"selection":[133],"evaluation":[135],"processes,":[136],"compared":[142],"other":[145],"Future":[150],"work":[151],"includes":[152],"choosing":[153],"developing":[158,177],"software":[159],"could":[161],"used":[163],"by":[164],"primary":[165],"care":[166],"physicians":[167],"local":[169],"government":[170],"health":[171],"centers":[172],"as":[173],"basis":[175],"personalized":[178],"NCD":[179],"treatment":[181],"management":[183],"plans":[184],"their":[186],"patients.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
