{"id":"https://openalex.org/W7225314974","doi":"https://doi.org/10.70267/cai.v3n5.163170","title":"A Reproducible Evaluation Workflow for Quantitative Benchmarking of Medical Data Quality Tools","display_name":"A Reproducible Evaluation Workflow for Quantitative Benchmarking of Medical Data Quality Tools","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225314974","doi":"https://doi.org/10.70267/cai.v3n5.163170"},"language":"en","primary_location":{"id":"doi:10.70267/cai.v3n5.163170","doi":"https://doi.org/10.70267/cai.v3n5.163170","is_oa":true,"landing_page_url":"https://doi.org/10.70267/cai.v3n5.163170","pdf_url":"https://journals.zeuspress.org/index.php/CAI/article/download/1737/1648","source":{"id":"https://openalex.org/S4404662459","display_name":"Computers and artificial intelligence.","issn_l":"3006-371X","issn":["3006-371X","3006-3728"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://journals.zeuspress.org/index.php/CAI/article/download/1737/1648","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160814719","display_name":"Xuanhao Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4396570571","display_name":"Xinjiang University of Science and Technology","ror":"https://ror.org/01ndzg854","country_code":"CN","type":"education","lineage":["https://openalex.org/I4396570571"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuanhao Shen","raw_affiliation_strings":["Xinjiang University of Science and Technology, Korla, Xinjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University of Science and Technology, Korla, Xinjiang, China","institution_ids":["https://openalex.org/I4396570571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160814719"],"corresponding_institution_ids":["https://openalex.org/I4396570571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"5","first_page":"163","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9023000001907349,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9023000001907349,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10350","display_name":"Electronic Health Records Systems","score":0.03819999843835831,"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/T14400","display_name":"Medical Coding and Health Information","score":0.03020000085234642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/medical-data-quality","display_name":"medical data quality","score":0.8389999866485596},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.8889999985694885},{"id":"https://openalex.org/keywords/data-quality-assurance","display_name":"data quality assurance","score":0.6449999809265137},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5619999766349792},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.7099999785423279},{"id":"https://openalex.org/keywords/defect-injection","display_name":"defect injection","score":0.6589999794960022},{"id":"https://openalex.org/keywords/missing-data","display_name":"missing data","score":0.6880000233650208},{"id":"https://openalex.org/keywords/unit-consistency","display_name":"unit consistency","score":0.7149999737739563},{"id":"https://openalex.org/keywords/great-expectations","display_name":"Great Expectations","score":0.7860000133514404}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8210999965667725},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7056000232696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6245999932289124},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.5730000138282776},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5616000294685364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5378000140190125},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.44510000944137573},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C71405471","wikidata":"https://www.wikidata.org/wiki/Q757012","display_name":"Quality management","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.70267/cai.v3n5.163170","doi":"https://doi.org/10.70267/cai.v3n5.163170","is_oa":true,"landing_page_url":"https://doi.org/10.70267/cai.v3n5.163170","pdf_url":"https://journals.zeuspress.org/index.php/CAI/article/download/1737/1648","source":{"id":"https://openalex.org/S4404662459","display_name":"Computers and artificial intelligence.","issn_l":"3006-371X","issn":["3006-371X","3006-3728"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.70267/cai.v3n5.163170","doi":"https://doi.org/10.70267/cai.v3n5.163170","is_oa":true,"landing_page_url":"https://doi.org/10.70267/cai.v3n5.163170","pdf_url":"https://journals.zeuspress.org/index.php/CAI/article/download/1737/1648","source":{"id":"https://openalex.org/S4404662459","display_name":"Computers and artificial intelligence.","issn_l":"3006-371X","issn":["3006-371X","3006-3728"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers and Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.766700029373169,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325419","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225314974.pdf","grobid_xml":"https://content.openalex.org/works/W7225314974.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4367310177","https://openalex.org/W4417183405","https://openalex.org/W7127146397","https://openalex.org/W2588241782","https://openalex.org/W4415880250","https://openalex.org/W4382753509","https://openalex.org/W4320482217","https://openalex.org/W2557559657","https://openalex.org/W4408406005","https://openalex.org/W7165760726"],"abstract_inverted_index":{"Propagating":[0],"data":[1,30,44,169],"defects":[2],"in":[3,22,89],"Electronic":[4],"Health":[5],"Records":[6],"(EHRs)":[7],"undermine":[8],"the":[9,16,26,64,98,152],"reliability":[10],"of":[11,18,29,73,77,155],"clinical":[12],"AI":[13],"models.":[14],"However,":[15],"absence":[17],"ground-truth":[19],"defect":[20,51,93],"labels":[21],"real-world":[23],"datasets":[24],"hinders":[25],"standardized":[27],"evaluation":[28,38],"quality":[31,45,90,170],"tools.":[32],"This":[33,158],"study":[34],"establishes":[35],"a":[36,41,71,86,161],"robust":[37],"workflow":[39],"for":[40,166],"multimodal":[42],"medical":[43,168],"assurance":[46],"system":[47,65,138],"[A],":[48],"comprising":[49],"controlled":[50],"injection,":[52],"real-dataset":[53],"profiling,":[54],"cross-tool":[55],"benchmarking,":[56],"and":[57,75,132,149],"ablation":[58],"studies.":[59],"Experimental":[60],"results":[61],"demonstrate":[62],"that":[63,118],"achieves":[66],"high":[67],"detection":[68,156],"efficacy,":[69],"with":[70,107],"recall":[72],"98.00%":[74],"precision":[76],"91.91%.":[78],"The":[79],"system\u2019s":[80],"discriminative":[81],"power":[82],"is":[83],"validated":[84],"by":[85],"monotonic":[87],"decline":[88],"scores":[91],"as":[92,151],"ratios":[94],"increase.":[95],"Validation":[96],"on":[97],"UCI":[99],"Diabetes":[100],"130":[101],"dataset":[102],"showed":[103],"missing-rate":[104],"statistics":[105],"consistent":[106],"existing":[108],"literature":[109],"(maximum":[110],"deviation":[111],"<":[112],"0.05%).":[113],"Crucially,":[114],"comparative":[115],"analysis":[116],"reveals":[117],"general-purpose":[119],"tools":[120],"(Great":[121],"Expectations,":[122],"DeepChecks,":[123],"ydata-profiling)":[124],"lack":[125],"native":[126],"medical-semantic":[127],"capabilities":[128],"(e.g.,":[129],"unit":[130],"consistency)":[131],"require":[133],"clean":[134],"baselines,":[135],"whereas":[136],"our":[137],"operates":[139],"effectively":[140],"without":[141],"such":[142],"dependencies.":[143],"Ablation":[144],"studies":[145],"further":[146],"identify":[147],"completeness":[148],"accuracy":[150],"primary":[153],"drivers":[154],"performance.":[157],"work":[159],"offers":[160],"reproducible,":[162],"quantitative":[163],"benchmarking":[164],"framework":[165],"advancing":[167],"assessment.":[171]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}