{"id":"https://openalex.org/W7128738470","doi":"https://doi.org/10.48448/s5qy-2z38","title":"PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis","display_name":"PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128738470","doi":"https://doi.org/10.48448/s5qy-2z38"},"language":"en","primary_location":{"id":"doi:10.48448/s5qy-2z38","doi":"https://doi.org/10.48448/s5qy-2z38","is_oa":true,"landing_page_url":"https://doi.org/10.48448/s5qy-2z38","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/s5qy-2z38","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152767343","display_name":"Uday Agarwal","orcid":"https://orcid.org/0009-0008-5618-7333","observed_orcids":["https://orcid.org/0009-0008-5618-7333"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Uday","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053631508","display_name":"Apoorva Challa","orcid":"https://orcid.org/0000-0002-8886-6460","observed_orcids":["https://orcid.org/0000-0002-8886-6460"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Challa, Apoorva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123292037","display_name":"Shreya K Gowda","orcid":"https://orcid.org/0000-0003-3378-5492","observed_orcids":["https://orcid.org/0000-0003-3378-5492"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gowda, Shreya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123224556","display_name":"Somesh Gupta","orcid":"https://orcid.org/0000-0003-3015-8602","observed_orcids":["https://orcid.org/0000-0003-3015-8602"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Somesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123328740","display_name":"K Lokesh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lokesh, K","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075621328","display_name":"Anand Mishra","orcid":"https://orcid.org/0000-0002-7806-2557","observed_orcids":["https://orcid.org/0000-0002-7806-2557"]},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mishra, Anand","raw_affiliation_strings":["IIT Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009838940","display_name":"Abhirama Subramanyam Penamakuri","orcid":"https://orcid.org/0000-0003-3646-8492","observed_orcids":["https://orcid.org/0000-0003-3646-8492"]},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Penamakuri, Abhirama Subramanyam","raw_affiliation_strings":["IIT Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"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":0.611299991607666,"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":0.611299991607666,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.35179999470710754,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.014000000432133675,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9800000190734863},{"id":"https://openalex.org/keywords/diagnosis","display_name":"diagnosis","score":0.7239999771118164},{"id":"https://openalex.org/keywords/patient-reported-symptoms","display_name":"patient-reported symptoms","score":0.7300000190734863},{"id":"https://openalex.org/keywords/multi-turn-dialogue","display_name":"multi-turn dialogue","score":0.6399999856948853},{"id":"https://openalex.org/keywords/follow-up-question-generation","display_name":"follow-up question generation","score":0.7639999985694885},{"id":"https://openalex.org/keywords/dermatology","display_name":"dermatology","score":0.3149999976158142},{"id":"https://openalex.org/keywords/qwen2-5-vl","display_name":"Qwen2.5-VL","score":0.7789999842643738}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5983999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967000126838684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C3020132585","wikidata":"https://www.wikidata.org/wiki/Q2671652","display_name":"Diagnostic accuracy","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2854999899864197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2583000063896179},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/s5qy-2z38","doi":"https://doi.org/10.48448/s5qy-2z38","is_oa":true,"landing_page_url":"https://doi.org/10.48448/s5qy-2z38","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/s5qy-2z38","doi":"https://doi.org/10.48448/s5qy-2z38","is_oa":true,"landing_page_url":"https://doi.org/10.48448/s5qy-2z38","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8560000061988831,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4407683933","https://openalex.org/W7106802031","https://openalex.org/W4414970838","https://openalex.org/W7155212901","https://openalex.org/W4408492863","https://openalex.org/W4390833194","https://openalex.org/W4394647211","https://openalex.org/W7166819463","https://openalex.org/W4387595887","https://openalex.org/W7131862012"],"abstract_inverted_index":{"Traditionally,":[0],"AI":[1],"research":[2],"in":[3],"medical":[4],"diagnosis":[5],"has":[6,14],"largely":[7],"centered":[8],"on":[9,69,164],"image":[10,71],"analysis.":[11],"While":[12],"this":[13],"led":[15],"to":[16,25,125,157],"notable":[17],"advancements,":[18],"the":[19,70,86,97,127,141,165],"absence":[20],"of":[21,96,154],"patient-reported":[22],"symptoms":[23,99,145],"continues":[24],"hinder":[26],"diagnostic":[27,41,55,134],"accuracy.":[28],"To":[29],"address":[30],"this,":[31],"we":[32,53],"propose":[33],"a":[34,50,62,76,81,92],"Pre-Consultation":[35],"Dialogue":[36],"framework":[37,149],"that":[38],"mimics":[39],"real-world":[40],"procedures,":[42],"where":[43],"doctors":[44],"iteratively":[45],"query":[46],"patients":[47],"before":[48],"reaching":[49],"conclusion.":[51],"Specifically,":[52],"simulate":[54],"dialogues":[56,115],"between":[57],"two":[58],"vision\u2013language":[59],"models":[60],"(VLMs):":[61],"DoctorVLM,":[63],"which":[64,78,121],"generates":[65],"follow-up":[66],"questions":[67],"based":[68],"and":[72,75,119],"dialogue":[73],"history,":[74],"PatientVLM,":[77],"responds":[79],"using":[80,138,147],"symptom":[82],"profile":[83],"derived":[84],"from":[85],"ground-truth":[87],"diagnosis.":[88,108],"We":[89],"additionally":[90],"conducted":[91],"small-scale":[93],"clinical":[94],"validation":[95],"synthetic":[98],"generated":[100,146],"by":[101],"our":[102,148],"framework,":[103],"confirming":[104],"their":[105],"usefulness":[106],"for":[107],"These":[109],"DocVLM\u2013PatientVLM":[110],"interactions":[111],"yield":[112],"realistic,":[113],"multi-turn":[114],"paired":[116],"with":[117,144,160],"images":[118],"diagnoses,":[120],"are":[122],"then":[123],"used":[124],"fine-tune":[126],"DoctorVLM.":[128],"This":[129],"dialogue-based":[130],"training":[131],"substantially":[132],"enhances":[133],"performance.":[135],"For":[136],"instance,":[137],"Qwen2.5-VL-7B":[139],"as":[140],"base":[142],"model,":[143],"achieves":[150],"an":[151],"F1":[152],"score":[153],"81.0%,":[155],"compared":[156],"just":[158],"56.5%":[159],"direct":[161],"image-only":[162],"fine-tuning":[163],"DermaMNIST":[166],"dataset.":[167]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}