{"id":"https://openalex.org/W4413543564","doi":"https://doi.org/10.3389/fdgth.2025.1660887","title":"Performance of vision language models for optic disc swelling identification on fundus photographs","display_name":"Performance of vision language models for optic disc swelling identification on fundus photographs","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4413543564","doi":"https://doi.org/10.3389/fdgth.2025.1660887","pmid":"https://pubmed.ncbi.nlm.nih.gov/40927810"},"language":"en","primary_location":{"id":"doi:10.3389/fdgth.2025.1660887","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2025.1660887","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1660887/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1660887/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056996128","display_name":"Kelvin Zhenghao Li","orcid":"https://orcid.org/0000-0002-9993-5118"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I2802408685","display_name":"Tan Tock Seng Hospital","ror":"https://ror.org/032d59j24","country_code":"SG","type":"healthcare","lineage":["https://openalex.org/I2802408685"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Kelvin Zhenghao Li","raw_affiliation_strings":["Centre of AI in Medicine, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore","Department of Ophthalmology, Stanford University, Palo Alto, CA, United States","Department of Ophthalmology, Tan Tock Seng Hospital, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of AI in Medicine, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Department of Ophthalmology, Stanford University, Palo Alto, CA, United States","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Ophthalmology, Tan Tock Seng Hospital, Singapore, Singapore","institution_ids":["https://openalex.org/I2802408685"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tuyet Thao Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuyet Thao Nguyen","raw_affiliation_strings":["Department of Ophthalmology, Stanford University, Palo Alto, CA, United States","School of Medicine, University of California Davis, Sacramento, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ophthalmology, Stanford University, Palo Alto, CA, United States","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"School of Medicine, University of California Davis, Sacramento, CA, United States","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089548562","display_name":"Heather E. Moss","orcid":"https://orcid.org/0000-0003-4373-447X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heather E. Moss","raw_affiliation_strings":["Department of Neurology & Neurological Sciences, Stanford University, Palo Alto, CA, United States","Department of Ophthalmology, Stanford University, Palo Alto, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurology & Neurological Sciences, Stanford University, Palo Alto, CA, United States","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Ophthalmology, Stanford University, Palo Alto, CA, United States","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089548562"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":1.3278,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81152454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"7","issue":null,"first_page":"1660887","last_page":"1660887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.9251999855041504,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T11438","display_name":"Retinal Imaging and Analysis","score":0.9251999855041504,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T10170","display_name":"Retinal Diseases and Treatments","score":0.011800000444054604,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"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/T10862","display_name":"AI in cancer detection","score":0.006399999838322401,"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/fundus","display_name":"Fundus (uterus)","score":0.6445985436439514},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5988852977752686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5154455900192261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4412067234516144},{"id":"https://openalex.org/keywords/optic-disc","display_name":"Optic disc","score":0.42845970392227173},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3565704822540283},{"id":"https://openalex.org/keywords/ophthalmology","display_name":"Ophthalmology","score":0.31441450119018555},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.23235878348350525},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09225800633430481},{"id":"https://openalex.org/keywords/retinal","display_name":"Retinal","score":0.0689382255077362},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.04635763168334961}],"concepts":[{"id":"https://openalex.org/C2776391266","wikidata":"https://www.wikidata.org/wiki/Q9612","display_name":"Fundus (uterus)","level":2,"score":0.6445985436439514},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5988852977752686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5154455900192261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4412067234516144},{"id":"https://openalex.org/C2779735895","wikidata":"https://www.wikidata.org/wiki/Q16873995","display_name":"Optic disc","level":3,"score":0.42845970392227173},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3565704822540283},{"id":"https://openalex.org/C118487528","wikidata":"https://www.wikidata.org/wiki/Q161437","display_name":"Ophthalmology","level":1,"score":0.31441450119018555},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.23235878348350525},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09225800633430481},{"id":"https://openalex.org/C2780827179","wikidata":"https://www.wikidata.org/wiki/Q422001","display_name":"Retinal","level":2,"score":0.0689382255077362},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.04635763168334961}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fdgth.2025.1660887","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2025.1660887","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1660887/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},{"id":"pmid:40927810","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40927810","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in digital health","raw_type":"Journal Article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/218638","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/218638","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:047f3c5afcd0485ba40b3b6ffef1e6f5","is_oa":true,"landing_page_url":"https://doaj.org/article/047f3c5afcd0485ba40b3b6ffef1e6f5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Digital Health, Vol 7 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12415036","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12415036/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Digit Health","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fdgth.2025.1660887","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2025.1660887","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1660887/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2583988712","display_name":null,"funder_award_id":"NIH P30 EY026877","funder_id":"https://openalex.org/F4320306811","funder_display_name":"Research to Prevent Blindness"},{"id":"https://openalex.org/G2664382403","display_name":"Imaging Structure and Function Core","funder_award_id":"2p30ey026877-06","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306811","display_name":"Research to Prevent Blindness","ror":"https://ror.org/04drjs621"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413543564.pdf","grobid_xml":"https://content.openalex.org/works/W4413543564.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2968308977","https://openalex.org/W3015487562","https://openalex.org/W4366330503","https://openalex.org/W4379259189","https://openalex.org/W4394579747","https://openalex.org/W4398244260","https://openalex.org/W4404792888","https://openalex.org/W4405434026","https://openalex.org/W4405484500","https://openalex.org/W4407806596","https://openalex.org/W4409370707"],"related_works":["https://openalex.org/W3015524434","https://openalex.org/W4390581830","https://openalex.org/W4315785006","https://openalex.org/W1572525974","https://openalex.org/W2374520121","https://openalex.org/W4319777531","https://openalex.org/W2942135640","https://openalex.org/W4390608506","https://openalex.org/W2358036240","https://openalex.org/W2139787942"],"abstract_inverted_index":{"Introduction:":[0],"Vision":[1],"language":[2,11],"models":[3,12,27],"(VLMs)":[4],"combine":[5],"image":[6,25,148,269],"analysis":[7,270],"capabilities":[8],"with":[9,52,85,110,196,198,248],"large":[10],"(LLMs).":[13],"Because":[14],"of":[15,31,39,49,58,87,105,130,133,140,223,239],"their":[16],"multimodal":[17],"capabilities,":[18],"VLMs":[19,51,90,106,235,262],"offer":[20],"a":[21,37],"clinical":[22,40],"advantage":[23],"over":[24],"classification":[26,57],"for":[28],"the":[29,47,56,151,208,221,227,230],"diagnosis":[30],"optic":[32,59,113,135,243],"disc":[33,60,114],"swelling":[34,61,115],"by":[35,251],"allowing":[36],"consideration":[38],"context.":[41],"In":[42],"this":[43],"study,":[44],"we":[45],"compare":[46],"performance":[48,104,166,249],"non-specialty-trained":[50],"different":[53,78,89],"prompts":[54,79,213],"in":[55,81,99,107,226],"on":[62],"fundus":[63],"photographs.":[64],"Methods:":[65],"A":[66,128],"diagnostic":[67],"test":[68],"accuracy":[69,125,183],"study":[70],"was":[71,116,194,216],"conducted":[72],"utilizing":[73],"an":[74,146],"open-sourced":[75],"dataset.":[76],"Five":[77],"(increasing":[80],"context)":[82],"were":[83,143],"used":[84],"each":[86],"five":[88],"(Llama":[91],"3.2-vision,":[92],"LLaVA-Med,":[93],"LLaVA,":[94],"GPT-4o,":[95],"and":[96,111,124,137,182,200,229,241],"DeepSeek-4V),":[97],"resulting":[98],"25":[100,152],"prompt-model":[101,153,192],"pairs.":[102],"The":[103,190],"classifying":[108],"photographs":[109,238],"without":[112],"measured":[117],"using":[118],"Youden's":[119],"index":[120],"(YI),":[121],"F1":[122,175],"score,":[123],"rate.":[126],"Results:":[127],"total":[129],"779":[131],"images":[132,139],"normal":[134,242],"discs":[136,142,244],"295":[138],"swollen":[141,240],"obtained":[144],"from":[145,159,168],"open-source":[147],"database.":[149],"Among":[150],"pairs,":[154],"valid":[155],"response":[156],"rates":[157],"ranged":[158,167],"7.8%":[160],"to":[161,171,178,186,266],"100%":[162],"(median":[163,173,180,188],"93.6%).":[164],"Diagnostic":[165],"YI:":[169],"0.00":[170,177],"0.231":[172],"0.042),":[174],"score:":[176],"0.716":[179],"0.401),":[181],"rate:":[184],"27.5":[185],"70.5%":[187],"58.8%).":[189],"best-performing":[191],"pair":[193],"GPT-4o":[195],"role-playing":[197],"Chain-of-Thought":[199],"few-shot":[201],"prompting.":[202],"On":[203],"average,":[204],"Llama":[205],"3.2-vision":[206],"performed":[207],"best":[209],"(average":[210],"YI":[211],"across":[212],"0.181).":[214],"There":[215],"no":[217],"consistent":[218],"relationship":[219],"between":[220],"amount":[222],"information":[224],"given":[225],"prompt":[228,254],"model":[231],"performance.":[232,260,271],"Conclusions:":[233],"Non-specialty-trained":[234],"could":[236],"classify":[237],"better":[245],"than":[246],"chance,":[247],"varying":[250],"model.":[252],"Increasing":[253],"complexity":[255],"did":[256],"not":[257],"consistently":[258],"improve":[259,267],"Specialty-specific":[261],"may":[263],"be":[264],"necessary":[265],"ophthalmic":[268]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}