{"id":"https://openalex.org/W4416144236","doi":"https://doi.org/10.1145/3721201.3725440","title":"Approximate Knowledge Graphs: Privacy-Preserving Healthcare Data Synthesis via LLM-Driven approximation","display_name":"Approximate Knowledge Graphs: Privacy-Preserving Healthcare Data Synthesis via LLM-Driven approximation","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4416144236","doi":"https://doi.org/10.1145/3721201.3725440"},"language":null,"primary_location":{"id":"doi:10.1145/3721201.3725440","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3725440","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725440","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725440","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100713060","display_name":"Shenglin Li","orcid":"https://orcid.org/0009-0002-3608-8369"},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shenglin Li","raw_affiliation_strings":["University of Alabama, Tuscaloosa, AL, USA"],"raw_orcid":"https://orcid.org/0009-0002-3608-8369","affiliations":[{"raw_affiliation_string":"University of Alabama, Tuscaloosa, AL, USA","institution_ids":["https://openalex.org/I17301866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032219874","display_name":"Jiaqi Gong","orcid":"https://orcid.org/0000-0001-9694-2518"},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqi Gong","raw_affiliation_strings":["University of Alabama, Tuscaloosa, AL, USA"],"raw_orcid":"https://orcid.org/0000-0001-9694-2518","affiliations":[{"raw_affiliation_string":"University of Alabama, Tuscaloosa, AL, USA","institution_ids":["https://openalex.org/I17301866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021099776","display_name":"Abel Andr\u00e9s Ram\u00edrez Molina","orcid":"https://orcid.org/0009-0001-4293-6144"},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abel Andres Ramirez Molina","raw_affiliation_strings":["University of Alabama, Tuscaloosa, AL, USA"],"raw_orcid":"https://orcid.org/0009-0001-4293-6144","affiliations":[{"raw_affiliation_string":"University of Alabama, Tuscaloosa, AL, USA","institution_ids":["https://openalex.org/I17301866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17301866"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8738267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"458","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.6582000255584717,"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":0.6582000255584717,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.12610000371932983,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.10989999771118164,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.6546000242233276},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5411999821662903},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.541100025177002},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5386999845504761},{"id":"https://openalex.org/keywords/health-records","display_name":"Health records","score":0.4278999865055084},{"id":"https://openalex.org/keywords/approximation-algorithm","display_name":"Approximation algorithm","score":0.4027000069618225},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.38830000162124634},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3732999861240387},{"id":"https://openalex.org/keywords/health-care","display_name":"Health care","score":0.3626999855041504}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794999837875366},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C3017977704","wikidata":"https://www.wikidata.org/wiki/Q18745135","display_name":"Health data","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C145242015","wikidata":"https://www.wikidata.org/wiki/Q774123","display_name":"Approximation theory","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721201.3725440","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3725440","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725440","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3721201.3725440","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721201.3725440","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721201.3725440","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6472092204","display_name":"Proto-OKN Theme 1: Creating A Cross-Domain Knowledge Graph to Integrate Health and Justice for Rural Resilience","funder_award_id":"2333836","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416144236.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W3015471667","https://openalex.org/W3071470454","https://openalex.org/W3210588961","https://openalex.org/W4297900505","https://openalex.org/W4385754113","https://openalex.org/W4389524299","https://openalex.org/W4392193048","https://openalex.org/W4392552633","https://openalex.org/W4392851477","https://openalex.org/W4394895012","https://openalex.org/W4399628104","https://openalex.org/W4402101243","https://openalex.org/W4402669784","https://openalex.org/W4403600390","https://openalex.org/W4403649757","https://openalex.org/W4403844673","https://openalex.org/W4404021177","https://openalex.org/W4404031831","https://openalex.org/W4404370986","https://openalex.org/W4405105217","https://openalex.org/W4405865167","https://openalex.org/W4412609352"],"related_works":[],"abstract_inverted_index":{"This":[0,105],"research":[1],"presents":[2],"a":[3,31,40,56,78,116],"novel":[4],"framework":[5],"for":[6,72,120],"generating":[7,121],"privacy-preserving":[8],"synthetic":[9,122],"healthcare":[10,150],"data":[11,110,124],"by":[12,77],"integrating":[13],"Large":[14],"Language":[15],"Models":[16],"(LLMs)":[17],"and":[18,109,146],"Knowledge":[19],"Graphs":[20],"(KGs).":[21],"The":[22],"method":[23],"transforms":[24],"raw":[25],"Electronic":[26],"Health":[27],"Records":[28],"(EHRs)":[29],"into":[30],"structured":[32],"KG":[33,144],"using":[34],"LLM-based":[35],"entity":[36],"extraction,":[37],"then":[38],"applies":[39],"calibrated":[41],"approximation":[42,63,139],"parameter":[43,90],"ranging":[44],"from":[45],"1":[46],"(highest":[47],"approximation)":[48],"to":[49,148],"10":[50],"(None":[51],"approximation).":[52],"Experimental":[53],"results":[54],"on":[55],"20,000-patient":[57],"dataset":[58],"demonstrate":[59],"that":[60,125],"more":[61,142],"aggressive":[62],"drastically":[64],"reduces":[65],"re-identification":[66],"risk":[67],"while":[68,100],"retaining":[69],"sufficient":[70],"fidelity":[71],"downstream":[73],"tasks,":[74],"as":[75],"evidenced":[76],"linear":[79],"classification":[80],"model":[81],"predicting":[82],"tumor":[83],"type":[84],"(Benign":[85],"vs.":[86],"Malignant).":[87],"Even":[88],"moderate":[89],"settings":[91],"(5\u20137)":[92],"preserve":[93],"much":[94],"of":[95,115],"the":[96,113,138],"model's":[97],"predictive":[98],"accuracy":[99],"substantially":[101],"mitigating":[102],"privacy":[103,108],"risks.":[104],"balance":[106],"between":[107],"utility":[111],"underscores":[112],"potential":[114],"semi-automated,":[117],"parameterized":[118],"approach":[119],"EHR":[123],"safeguards":[126],"sensitive":[127],"information":[128],"yet":[129],"remains":[130],"clinically":[131],"valuable.":[132],"Future":[133],"work":[134],"will":[135],"further":[136],"refine":[137],"strategy,":[140],"incorporate":[141],"complex":[143],"structures,":[145],"scale":[147],"diverse":[149],"datasets.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-12T00:00:00"}