{"id":"https://openalex.org/W4390549933","doi":"https://doi.org/10.1109/sita60746.2023.10373591","title":"Data Preprocessing For Machine Learning Applications in Healthcare: A Review","display_name":"Data Preprocessing For Machine Learning Applications in Healthcare: A Review","publication_year":2023,"publication_date":"2023-11-22","ids":{"openalex":"https://openalex.org/W4390549933","doi":"https://doi.org/10.1109/sita60746.2023.10373591"},"language":"en","primary_location":{"id":"doi:10.1109/sita60746.2023.10373591","is_oa":true,"landing_page_url":"https://doi.org/10.1109/sita60746.2023.10373591","pdf_url":"https://ieeexplore.ieee.org/ielx7/10373588/10373590/10373591.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/10373588/10373590/10373591.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009063572","display_name":"Ismail Chahid","orcid":"https://orcid.org/0000-0002-1313-8098"},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Ismail Chahid","raw_affiliation_strings":["Mohammed First University,Lari Laboratory Faculty of Science,Oujda,Morocco","Lari Laboratory Faculty of Science, Mohammed First University, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohammed First University,Lari Laboratory Faculty of Science,Oujda,Morocco","institution_ids":["https://openalex.org/I4210108110"]},{"raw_affiliation_string":"Lari Laboratory Faculty of Science, Mohammed First University, Oujda, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004637297","display_name":"Aissa Kerkour Elmiad","orcid":"https://orcid.org/0000-0002-0795-4072"},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Aissa Kerkour Elmiad","raw_affiliation_strings":["Mohammed First University,Lari Laboratory Faculty of Science,Oujda,Morocco","Lari Laboratory Faculty of Science, Mohammed First University, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohammed First University,Lari Laboratory Faculty of Science,Oujda,Morocco","institution_ids":["https://openalex.org/I4210108110"]},{"raw_affiliation_string":"Lari Laboratory Faculty of Science, Mohammed First University, Oujda, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055665476","display_name":"Mohamed El Badaoui","orcid":"https://orcid.org/0000-0002-1251-2180"},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Mohammed Badaoui","raw_affiliation_strings":["Mohammed First University,Lari Laboratory Faculty of Science,Oujda,Morocco","Lari Laboratory Faculty of Science, Mohammed First University, Oujda, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohammed First University,Lari Laboratory Faculty of Science,Oujda,Morocco","institution_ids":["https://openalex.org/I4210108110"]},{"raw_affiliation_string":"Lari Laboratory Faculty of Science, Mohammed First University, Oujda, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210108110"],"apc_list":null,"apc_paid":null,"fwci":6.9013,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97464789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9988999962806702,"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":0.9988999962806702,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9889000058174133,"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/preprocessor","display_name":"Preprocessor","score":0.7973010540008545},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7881256937980652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822742462158203},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6032292246818542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5584017634391785},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5322138071060181},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.5119977593421936},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5042711496353149},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4912845492362976},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.48727619647979736},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4850391745567322},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4203421175479889},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38182806968688965},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3319241404533386},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07130211591720581}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7973010540008545},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7881256937980652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822742462158203},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6032292246818542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5584017634391785},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5322138071060181},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.5119977593421936},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5042711496353149},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4912845492362976},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.48727619647979736},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4850391745567322},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4203421175479889},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38182806968688965},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3319241404533386},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07130211591720581},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sita60746.2023.10373591","is_oa":true,"landing_page_url":"https://doi.org/10.1109/sita60746.2023.10373591","pdf_url":"https://ieeexplore.ieee.org/ielx7/10373588/10373590/10373591.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/sita60746.2023.10373591","is_oa":true,"landing_page_url":"https://doi.org/10.1109/sita60746.2023.10373591","pdf_url":"https://ieeexplore.ieee.org/ielx7/10373588/10373590/10373591.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390549933.pdf","grobid_xml":"https://content.openalex.org/works/W4390549933.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1901616594","https://openalex.org/W1971935224","https://openalex.org/W2157117929","https://openalex.org/W2169818249","https://openalex.org/W2345195116","https://openalex.org/W2951635356","https://openalex.org/W3109000640","https://openalex.org/W3155739706","https://openalex.org/W3170657538","https://openalex.org/W3204402824","https://openalex.org/W4220862305","https://openalex.org/W4226323522","https://openalex.org/W4281630308","https://openalex.org/W6601742559"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Data":[0],"preprocessing":[1,56,93],"plays":[2],"a":[3],"critical":[4],"role":[5],"in":[6,16,72],"the":[7,17,23,61],"success":[8],"of":[9,25,54],"machine":[10,38],"learning":[11,14,39],"and":[12,19,35,63,82,87],"deep":[13],"models":[15],"medical":[18,62,91],"healthcare":[20,26,64],"field.":[21],"As":[22],"availability":[24],"data":[27,55,73,76,78,80,83,92],"continues":[28],"to":[29,49,60,90],"grow,":[30],"ensuring":[31],"its":[32],"quality,":[33],"reliability,":[34],"suitability":[36],"for":[37],"tasks":[40],"becomes":[41],"essential.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"will":[47,67],"try":[48],"provide":[50],"an":[51],"in-depth":[52],"exploration":[53],"techniques":[57],"specifically":[58],"tailored":[59],"domain.":[65],"We":[66],"cover":[68],"various":[69],"steps":[70],"involved":[71],"preprocessing,":[74],"including":[75],"types,":[77],"cleaning,":[79],"transforming,":[81],"normalization.":[84],"Additionally,":[85],"challenges":[86],"considerations":[88],"unique":[89],"are":[94],"discussed.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
