{"id":"https://openalex.org/W7118176114","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315338","title":"Scaling Arabic Medical Chatbots Using Synthetic Data: Enhancing Generative AI with Synthetic Patient Records","display_name":"Scaling Arabic Medical Chatbots Using Synthetic Data: Enhancing Generative AI with Synthetic Patient Records","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118176114","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315338"},"language":null,"primary_location":{"id":"doi:10.1109/aiccsa66935.2025.11315338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","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":null,"display_name":"Abdulrahman Allam","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Abdulrahman Allam","raw_affiliation_strings":["MSA University,Dept. of Computer Science,Giza,Egypt"],"affiliations":[{"raw_affiliation_string":"MSA University,Dept. of Computer Science,Giza,Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012088054","display_name":"Seif Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Seif Ahmed","raw_affiliation_strings":["MSA University,Dept. of Computer Science,Giza,Egypt"],"affiliations":[{"raw_affiliation_string":"MSA University,Dept. of Computer Science,Giza,Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030894498","display_name":"Ali Hamdi","orcid":"https://orcid.org/0000-0002-2301-6588"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ali Hamdi","raw_affiliation_strings":["MSA University,Dept. of Computer Science,Giza,Egypt"],"affiliations":[{"raw_affiliation_string":"MSA University,Dept. of Computer Science,Giza,Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121648537","display_name":"Khaled Shaban","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Khaled Shaban","raw_affiliation_strings":["Qatar University,Dept. of Computer Science,Doha,Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar University,Dept. of Computer Science,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145487455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61583161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.40799999237060547,"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":0.40799999237060547,"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/T12128","display_name":"AI in Service Interactions","score":0.23819999396800995,"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/T10028","display_name":"Topic Modeling","score":0.08889999985694885,"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/chatbot","display_name":"Chatbot","score":0.8495000004768372},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6021999716758728},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5992000102996826},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5006999969482422},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47600001096725464},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43700000643730164},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4262999892234802}],"concepts":[{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.8495000004768372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6486999988555908},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5715000033378601},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4115000069141388},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.2599000036716461}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa66935.2025.11315338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","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":19,"referenced_works":["https://openalex.org/W119975642","https://openalex.org/W1608737606","https://openalex.org/W2921914364","https://openalex.org/W3015124543","https://openalex.org/W3135544356","https://openalex.org/W4205219607","https://openalex.org/W4289520498","https://openalex.org/W4308751002","https://openalex.org/W4322102006","https://openalex.org/W4366290727","https://openalex.org/W4386141641","https://openalex.org/W4388725043","https://openalex.org/W4393085819","https://openalex.org/W4393407168","https://openalex.org/W4399034049","https://openalex.org/W4401386758","https://openalex.org/W4405440758","https://openalex.org/W4406029520","https://openalex.org/W4412531741"],"related_works":[],"abstract_inverted_index":{"The":[0,142],"development":[1],"of":[2,13,24,86,128,165],"medical":[3,179],"chatbots":[4],"in":[5,83,177],"Arabic":[6,26,190],"is":[7],"significantly":[8],"constrained":[9],"by":[10],"the":[11,57,84,87,101,126,163,182],"scarcity":[12],"large-scale,":[14],"highquality":[15],"annotated":[16],"datasets.":[17],"While":[18],"prior":[19],"efforts":[20],"compiled":[21],"a":[22,49,169],"dataset":[23],"20,000":[25],"patient-doctor":[27],"interactions":[28],"from":[29],"social":[30],"media":[31],"to":[32,55,60,150],"fine-tune":[33],"large":[34],"language":[35,175],"models":[36,176],"(LLMs),":[37],"model":[38],"scalability":[39],"and":[40,68,76,98,110,112,119,138,153,188],"generalization":[41],"remained":[42],"limited.":[43],"In":[44],"this":[45],"study,":[46],"we":[47,131],"propose":[48],"scalable":[50],"synthetic":[51,79,91,129,166],"data":[52,140,147],"augmentation":[53,167],"strategy":[54],"expand":[56],"training":[58,102],"corpus":[59],"100,000":[61],"records.":[62],"Using":[63],"advanced":[64],"generative":[65],"AI":[66],"systems-ChatGPT-4o":[67],"Gemini":[69],"2.5":[70],"Pro-we":[71],"generated":[72],"80,000":[73],"contextually":[74],"relevant":[75],"medically":[77],"coherent":[78],"question-answer":[80],"pairs":[81],"grounded":[82],"structure":[85],"original":[88],"dataset.":[89],"These":[90],"samples":[92],"were":[93],"semantically":[94],"filtered,":[95],"manually":[96],"validated,":[97],"integrated":[99],"into":[100],"pipeline.":[103],"We":[104],"fine-tuned":[105],"five":[106],"LLMs,":[107],"including":[108],"Mistral-7B":[109],"AraGPT2,":[111],"evaluated":[113],"their":[114],"performance":[115],"using":[116],"BERTScore":[117],"metrics":[118],"expert-driven":[120],"qualitative":[121],"assessments.":[122],"To":[123],"further":[124],"analyze":[125],"effectiveness":[127],"sources,":[130],"conducted":[132],"an":[133],"ablation":[134],"study":[135],"comparing":[136],"ChatGPT-4o":[137,146],"Gemini-generated":[139],"independently.":[141],"results":[143],"showed":[144],"that":[145],"consistently":[148],"led":[149],"higher":[151],"F1-scores":[152],"fewer":[154],"hallucinations":[155],"across":[156],"all":[157],"models.":[158],"Overall,":[159],"our":[160],"findings":[161],"demonstrate":[162],"viability":[164],"as":[168],"practical":[170],"solution":[171],"for":[172,184],"enhancing":[173],"domain-specific":[174],"low-resource":[178],"NLP,":[180],"paving":[181],"way":[183],"more":[185],"inclusive,":[186],"scalable,":[187],"accurate":[189],"healthcare":[191],"chatbot":[192],"systems.":[193]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-01-05T00:00:00"}