{"id":"https://openalex.org/W4385562548","doi":"https://doi.org/10.1145/3580305.3599427","title":"MedLink: De-Identified Patient Health Record Linkage","display_name":"MedLink: De-Identified Patient Health Record Linkage","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385562548","doi":"https://doi.org/10.1145/3580305.3599427"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5029029234","display_name":"Zhenbang Wu","orcid":"https://orcid.org/0009-0003-2855-7978"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhenbang Wu","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645991","display_name":"Cao Xiao","orcid":"https://orcid.org/0000-0002-3869-6942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao Xiao","raw_affiliation_strings":["Relativity, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Relativity, Chicago, IL, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084279065","display_name":"Jimeng Sun","orcid":"https://orcid.org/0000-0003-1512-6426"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jimeng Sun","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029029234"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.8757,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78545889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2672","last_page":"2682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9998999834060669,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9998999834060669,"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/T12246","display_name":"Chronic Disease Management Strategies","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.7589843273162842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6897435188293457},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.6145896315574646},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.6043010950088501},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5453417301177979},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.5364928841590881},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.532012939453125},{"id":"https://openalex.org/keywords/medical-record","display_name":"Medical record","score":0.48110145330429077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47697100043296814},{"id":"https://openalex.org/keywords/unique-identifier","display_name":"Unique identifier","score":0.4608874022960663},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45512765645980835},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4486072063446045},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4437859058380127},{"id":"https://openalex.org/keywords/medical-classification","display_name":"Medical classification","score":0.43675318360328674},{"id":"https://openalex.org/keywords/diagnosis-code","display_name":"Diagnosis code","score":0.421672523021698},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3959659934043884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33932632207870483},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33046215772628784},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2617700397968292},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.09313809871673584},{"id":"https://openalex.org/keywords/nursing","display_name":"Nursing","score":0.08800619840621948},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08777981996536255}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7589843273162842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6897435188293457},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.6145896315574646},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6043010950088501},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5453417301177979},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.5364928841590881},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.532012939453125},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.48110145330429077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47697100043296814},{"id":"https://openalex.org/C119839945","wikidata":"https://www.wikidata.org/wiki/Q6545185","display_name":"Unique identifier","level":3,"score":0.4608874022960663},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45512765645980835},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4486072063446045},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4437859058380127},{"id":"https://openalex.org/C154874363","wikidata":"https://www.wikidata.org/wiki/Q3518464","display_name":"Medical classification","level":2,"score":0.43675318360328674},{"id":"https://openalex.org/C45827449","wikidata":"https://www.wikidata.org/wiki/Q5270338","display_name":"Diagnosis code","level":3,"score":0.421672523021698},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3959659934043884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33932632207870483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33046215772628784},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2617700397968292},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.09313809871673584},{"id":"https://openalex.org/C159110408","wikidata":"https://www.wikidata.org/wiki/Q121176","display_name":"Nursing","level":1,"score":0.08800619840621948},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08777981996536255},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599427","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2065240770","https://openalex.org/W2073471108","https://openalex.org/W2105976862","https://openalex.org/W2163756102","https://openalex.org/W2284851926","https://openalex.org/W2481271618","https://openalex.org/W2518582440","https://openalex.org/W2557074642","https://openalex.org/W2597505554","https://openalex.org/W2690721124","https://openalex.org/W2742491462","https://openalex.org/W2775078427","https://openalex.org/W2805089815","https://openalex.org/W2892188507","https://openalex.org/W2898236192","https://openalex.org/W2910013677","https://openalex.org/W2912269676","https://openalex.org/W2946978350","https://openalex.org/W2964068143","https://openalex.org/W2997494090","https://openalex.org/W2997653844","https://openalex.org/W2998409174","https://openalex.org/W3004227146","https://openalex.org/W3080098168","https://openalex.org/W3099700870","https://openalex.org/W3101973032","https://openalex.org/W3112116031","https://openalex.org/W3160137267","https://openalex.org/W3177373898","https://openalex.org/W3199686039","https://openalex.org/W4252076394","https://openalex.org/W4287079430","https://openalex.org/W7075680736"],"related_works":["https://openalex.org/W2413568490","https://openalex.org/W1913624564","https://openalex.org/W3130054399","https://openalex.org/W4301062032","https://openalex.org/W2548183822","https://openalex.org/W4294243532","https://openalex.org/W2911599090","https://openalex.org/W2989796854","https://openalex.org/W2141965543","https://openalex.org/W4301207775"],"abstract_inverted_index":{"A":[0],"comprehensive":[1],"patient":[2,8,22,38,59,71,82,186,196],"health":[3,23,60,64,115,122,138,153,207],"history":[4],"is":[5,179],"essential":[6],"for":[7,151,181],"care":[9,201],"and":[10,48,108,124,145,178,204],"healthcare":[11,20],"research.":[12],"However,":[13],"due":[14],"to":[15,140,162,243],"the":[16,81,86,90,104,110,126,152,166,199,215],"distributed":[17],"nature":[18],"of":[19,88,112],"services,":[21],"records":[24,61,123],"are":[25],"often":[26],"scattered":[27],"across":[28],"multiple":[29],"systems.":[30],"Existing":[31],"record":[32,105],"linkage":[33,83,234],"approaches":[34],"primarily":[35],"rely":[36],"on":[37,69,94,165,184,194],"identifiers,":[39],"which":[40],"have":[41],"inherent":[42],"limitations":[43],"such":[44],"as":[45,100,117],"privacy":[46],"invasion":[47],"identifier":[49],"discrepancies.":[50],"To":[51,131],"tackle":[52],"this":[53],"problem,":[54],"we":[55],"propose":[56],"linking":[57],"de-identified":[58],"by":[62,218,241],"matching":[63,106],"patterns":[65,116],"without":[66],"strictly":[67],"relying":[68],"sensitive":[70],"identifiers.":[72],"Our":[73],"model":[74],"MedLink":[75,135,155,173,190,213,236],"solves":[76],"two":[77],"challenges":[78],"faced":[79],"with":[80,223,231],"task:":[84],"(1)":[85],"challenge":[87,111],"identifying":[89,113],"same":[91],"patients":[92],"based":[93],"data":[95],"collected":[96],"in":[97,220],"different":[98],"timelines":[99],"disease":[101],"progression":[102],"makes":[103],"difficult,":[107],"(2)":[109],"distinct":[114],"common":[118],"medical":[119],"codes":[120,143,147,170],"dominate":[121],"overshadow":[125],"more":[127,164],"informative":[128,169],"low-prevalence":[129,167],"codes.":[130],"address":[132],"these":[133],"challenges,":[134],"utilizes":[136],"bi-directional":[137],"prediction":[139],"predict":[141],"future":[142],"forwardly":[144],"past":[146],"backwardly,":[148],"thus":[149],"accounting":[150],"progression.":[154],"also":[156],"has":[157],"a":[158,205],"prevalence-aware":[159],"retrieval":[160],"design":[161],"focus":[163],"but":[168],"during":[171],"learning.":[172],"can":[174,237],"be":[175],"trained":[176],"end-to-end":[177],"lightweight":[180],"efficient":[182],"inference":[183],"large":[185,206],"databases.":[187],"We":[188],"evaluate":[189],"against":[191],"leading":[192],"baselines":[193],"real-world":[195],"datasets,":[197],"including":[198],"critical":[200],"dataset":[202],"MIMIC-III":[203],"claims":[208],"dataset.":[209],"Results":[210],"show":[211],"that":[212],"outperforms":[214],"best":[216],"baseline":[217],"4%":[219],"top-1":[221],"accuracy":[222],"only":[224],"8%":[225],"memory":[226],"cost.":[227],"Additionally,":[228],"when":[229],"combined":[230],"existing":[232],"identifier-based":[233],"approaches,":[235],"improve":[238],"their":[239],"performance":[240],"up":[242],"15%.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}