{"id":"https://openalex.org/W7134173474","doi":"https://doi.org/10.1109/bigdata66926.2025.11402329","title":"An Investigation of Data Granularity in RAG Pipelines for Personalized Medicine","display_name":"An Investigation of Data Granularity in RAG Pipelines for Personalized Medicine","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134173474","doi":"https://doi.org/10.1109/bigdata66926.2025.11402329"},"language":null,"primary_location":{"id":"doi:10.1109/bigdata66926.2025.11402329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11402329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5128351627","display_name":"Paritosh Pandey","orcid":null},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paritosh Pandey","raw_affiliation_strings":["College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114701375","display_name":"Shirley Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shirley Tian","raw_affiliation_strings":["College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128344133","display_name":"Shaoen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoen Wu","raw_affiliation_strings":["College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103189799","display_name":"Linh Le","orcid":"https://orcid.org/0000-0002-0087-3448"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linh Le","raw_affiliation_strings":["College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Software Engineering, Kennesaw State University,Marietta,GA,USA,30060","institution_ids":["https://openalex.org/I172980758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172980758"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4187","last_page":"4192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.08389999717473984,"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":0.08389999717473984,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.08380000293254852,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.08370000123977661,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalized-medicine","display_name":"Personalized medicine","score":0.6542999744415283},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6050000190734863},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.3977000117301941},{"id":"https://openalex.org/keywords/precision-medicine","display_name":"Precision medicine","score":0.3580000102519989}],"concepts":[{"id":"https://openalex.org/C32220436","wikidata":"https://www.wikidata.org/wiki/Q2072214","display_name":"Personalized medicine","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344000101089478},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6050000190734863},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3930000066757202},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11402329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11402329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.kennesaw.edu:masterstheses-1103","is_oa":false,"landing_page_url":"https://digitalcommons.kennesaw.edu/masterstheses/93","pdf_url":null,"source":{"id":"https://openalex.org/S4377196456","display_name":"DigitalCommons - Kennesaw State University (Kennesaw State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172980758","host_organization_name":"Kennesaw State University","host_organization_lineage":["https://openalex.org/I172980758"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Master's Theses","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2295598076","https://openalex.org/W2970641574","https://openalex.org/W3109650690","https://openalex.org/W3197233987","https://openalex.org/W4206850841","https://openalex.org/W4386141641","https://openalex.org/W4395462076","https://openalex.org/W4396830927","https://openalex.org/W4399660853","https://openalex.org/W4400128031","https://openalex.org/W4406726559","https://openalex.org/W4406813548","https://openalex.org/W4408158033","https://openalex.org/W4409645678"],"related_works":[],"abstract_inverted_index":{"Generative":[0,76],"AI,":[1],"exemplified":[2],"by":[3],"large":[4],"language":[5],"models":[6],"like":[7],"the":[8,62,161,170,187],"OpenAI":[9],"GPT":[10],"and":[11,50,132,141,157,180],"Meta":[12],"LLaMA":[13],"families,":[14],"can":[15],"produce":[16],"diverse":[17],"content":[18],"in":[19,31,127],"response":[20,138],"to":[21,29,36,39,64,102,117],"prompts.":[22],"This":[23,110],"capability":[24,162],"offers":[25],"a":[26,74,91,98,107,115,122,174],"promising":[27,175],"solution":[28],"challenges":[30],"precision":[32],"medicine,":[33],"which":[34],"seeks":[35],"tailor":[37],"treatments":[38],"individual":[40],"clinical":[41],"profiles":[42],"but":[43],"often":[44],"struggles":[45],"with":[46,97],"data":[47,80,136],"collection,":[48],"cost,":[49],"privacy":[51],"concerns.":[52],"By":[53],"generating":[54,164],"realistic,":[55],"privacy-preserving":[56],"patient":[57],"data,":[58],"generative":[59],"AI":[60,77,194],"has":[61],"potential":[63],"transform":[65],"patient-centric":[66],"healthcare.":[67],"With":[68],"such":[69,134],"motivation,":[70],"this":[71],"research":[72],"develops":[73],"comprehensive":[75],"pipeline":[78,89],"emphasizing":[79],"granularity":[81],"for":[82,189],"accurate":[83],"prediction":[84],"of":[85,163],"personalized":[86,119],"treatments.":[87],"The":[88],"features":[90],"central":[92],"Large":[93],"Language":[94],"Model":[95],"interacting":[96],"Machine":[99],"Learning":[100],"agent":[101],"determine":[103],"key":[104],"factors":[105],"affecting":[106],"patient\u2019s":[108],"condition.":[109],"information":[111],"is":[112,173],"compiled":[113],"into":[114],"query":[116],"retrieve":[118],"suggestions":[120],"from":[121],"guideline":[123],"database.":[124],"We":[125],"exam-":[126],"model":[128],"development,":[129],"experimental":[130],"processes,":[131],"concerns":[133],"as":[135],"quality,":[137],"evaluation,":[139],"trust,":[140],"reliability.":[142],"Then,":[143],"we":[144],"apply":[145],"our":[146],"developed":[147],"framework":[148,172],"on":[149,160],"three":[150],"chronic":[151],"diseases,":[152],"namely":[153],"diabetes,":[154],"heart":[155],"disease,":[156],"mental":[158],"illness,":[159],"tailored":[165],"treatment":[166,184],"recommendations.":[167],"Experiments":[168],"show":[169],"proposed":[171],"step":[176],"toward":[177],"explainable,":[178],"personalized,":[179],"clinically":[181],"aligned":[182],"AI-driven":[183],"planning,":[185],"laying":[186],"foundation":[188],"future":[190],"trustworthy,":[191],"patient-focused":[192],"medical":[193],"systems.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-09T00:00:00"}