{"id":"https://openalex.org/W7113902928","doi":"https://doi.org/10.1145/3765612.3768142","title":"Enhancing Medical AI Safety Through Multi-Agent Evaluation and Iterative Refinement","display_name":"Enhancing Medical AI Safety Through Multi-Agent Evaluation and Iterative Refinement","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7113902928","doi":"https://doi.org/10.1145/3765612.3768142"},"language":null,"primary_location":{"id":"doi:10.1145/3765612.3768142","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3768142","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3768142","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3768142","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zainab Ghafoor","orcid":"https://orcid.org/0009-0006-0893-1370"},"institutions":[{"id":"https://openalex.org/I158011677","display_name":"Sonoma State University","ror":"https://ror.org/04wjxkk25","country_code":"US","type":"education","lineage":["https://openalex.org/I158011677"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zainab Ghafoor","raw_affiliation_strings":["Sonoma State University, Rohnert Park, CA, USA"],"raw_orcid":"https://orcid.org/0009-0006-0893-1370","affiliations":[{"raw_affiliation_string":"Sonoma State University, Rohnert Park, CA, USA","institution_ids":["https://openalex.org/I158011677"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Md Shafiqul Islam","orcid":"https://orcid.org/0009-0006-0110-9501"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Shafiqul Islam","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0009-0006-0110-9501","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Koushik Howlader","orcid":"https://orcid.org/0000-0001-9392-9801"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koushik Howlader","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9392-9801","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Md Rasel Khondokar","orcid":"https://orcid.org/0009-0007-8764-6793"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Rasel Khondokar","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0009-0007-8764-6793","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tanusree Bhattacharjee","orcid":"https://orcid.org/0009-0009-6581-2011"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanusree Bhattacharjee","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0009-0009-6581-2011","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sayantan Chakroborty","orcid":"https://orcid.org/0009-0008-9564-6897"},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Sayantan Chakroborty","raw_affiliation_strings":["University of Dhaka, Dhaka, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0008-9564-6897","affiliations":[{"raw_affiliation_string":"University of Dhaka, Dhaka, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Adrito Roy","orcid":"https://orcid.org/0009-0001-6953-4495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrito Roy","raw_affiliation_strings":["Notre Dame College, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0001-6953-4495","affiliations":[{"raw_affiliation_string":"Notre Dame College, Dhaka, Bangladesh","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ushashi Bhattacharjee","orcid":"https://orcid.org/0009-0006-6183-3833"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ushashi Bhattacharjee","raw_affiliation_strings":["Iowa State University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0009-0006-6183-3833","affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, IA, USA","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tirtho Roy","orcid":"https://orcid.org/0009-0005-9722-2922"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tirtho Roy","raw_affiliation_strings":["Iowa Sate University, Ames, IA, USA"],"raw_orcid":"https://orcid.org/0009-0005-9722-2922","affiliations":[{"raw_affiliation_string":"Iowa Sate University, Ames, IA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5799999833106995,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.5799999833106995,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2720000147819519,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0421999990940094,"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/trustworthiness","display_name":"Trustworthiness","score":0.5817000269889832},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5807999968528748},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.534500002861023},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.478300005197525},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4512999951839447},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4153999984264374},{"id":"https://openalex.org/keywords/patient-safety","display_name":"Patient safety","score":0.39149999618530273},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244999766349792},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5817000269889832},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5807999968528748},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5284000039100647},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C2779328685","wikidata":"https://www.wikidata.org/wiki/Q1475557","display_name":"Patient safety","level":3,"score":0.39149999618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C195910791","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Medical record","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.263700008392334},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3765612.3768142","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3768142","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3768142","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3765612.3768142","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3765612.3768142","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3765612.3768142","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7070884108543396}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7113902928.pdf","grobid_xml":"https://content.openalex.org/works/W7113902928.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"show":[4],"strong":[5],"potential":[6],"in":[7,13,114,148,175],"healthcare":[8],"but":[9],"face":[10],"critical":[11],"challenges":[12],"ethical":[14,100],"and":[15,39,47,55,66,87,104,138,150,165],"safety":[16,29],"compliance.":[17],"We":[18],"present":[19],"a":[20,67,91,106,156,167],"lightweight":[21],"multi-agent":[22,97],"refinement":[23,94],"framework":[24],"that":[25,52],"enhances":[26],"medical":[27,162],"LLM":[28],"through":[30],"structured,":[31],"iterative":[32],"alignment.":[33],"The":[34,96],"system":[35],"pairs":[36],"DeepSeek":[37,110],"R1":[38,111],"Med-PaLM":[40,113,124],"as":[41,49],"generative":[42],"models":[43],"with":[44,123],"LLaMA":[45],"3.1":[46],"Phi-4":[48],"evaluator":[50],"agents":[51],"iteratively":[53],"assess":[54],"refine":[56],"responses":[57],"against":[58],"the":[59,79],"American":[60],"Medical":[61],"Association's":[62],"nine":[63],"Principles":[64],"(AMA-9)":[65],"five-tier":[68],"Safety":[69],"Risk":[70],"Assessment":[71],"(SRA-5).":[72],"Using":[73],"900":[74],"adversarial":[75],"clinical":[76,176],"prompts":[77],"from":[78],"MedSafety-Eval":[80],"subset,":[81],"we":[82],"measure":[83],"convergence,":[84],"violation":[85],"reduction,":[86],"risk":[88],"downgrading":[89],"under":[90],"structured":[92],"five-iteration":[93],"loop.":[95],"pipeline":[98],"reduced":[99],"violations":[101],"by":[102],"89%":[103],"achieved":[105],"92%":[107],"risk-downgrade":[108],"rate.":[109],"outperforms":[112],"convergence":[115],"efficiency":[116],"(94.2%":[117],"convergence;":[118,126],"mean":[119,127],"2.34":[120],"iterations)":[121],"compared":[122],"(91.8%":[125],"2.67":[128],"iterations).":[129],"Domain":[130],"analyses":[131],"reveal":[132],"consistent":[133],"gains":[134],"across":[135],"emergency,":[136],"diagnostic,":[137],"therapeutic":[139],"scenarios,":[140],"while":[141],"non-convergent":[142],"cases":[143],"highlight":[144],"areas":[145],"for":[146,160],"improvement":[147],"legal":[149],"privacy":[151],"domains.":[152],"Our":[153],"approach":[154],"offers":[155],"scalable,":[157],"cost-effective":[158],"protocol":[159],"enhancing":[161],"AI":[163],"trustworthiness":[164],"provides":[166],"practical":[168],"pathway":[169],"toward":[170],"regulator-aligned":[171],"deployment":[172],"of":[173],"LLMs":[174],"settings.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-11T00:00:00"}
