{"doi":"10.3389/fdgth.2025.1660887","title":"Performance of vision language models for optic disc swelling identification on fundus photographs","abstract":"Introduction: Vision language models (VLMs) combine image analysis capabilities with large language models (LLMs). Because of their multimodal capabilities, VLMs offer a clinical advantage over image classification models for the diagnosis of optic disc swelling by allowing a consideration of clinical context. In this study, we compare the performance of non-specialty-trained VLMs with different prompts in the classification of optic disc swelling on fundus photographs. Methods: A diagnostic test accuracy study was conducted utilizing an open-sourced dataset. Five different prompts (increasing in context) were used with each of five different VLMs (Llama 3.2-vision, LLaVA-Med, LLaVA, GPT-4o, and DeepSeek-4V), resulting in 25 prompt-model pairs. The performance of VLMs in classifying photographs with and without optic disc swelling was measured using Youden's index (YI), F1 score, and accuracy rate. Results: A total of 779 images of normal optic discs and 295 images of swollen discs were obtained from an open-source image database. Among the 25 prompt-model pairs, valid response rates ranged from 7.8% to 100% (median 93.6%). Diagnostic performance ranged from YI: 0.00 to 0.231 (median 0.042), F1 score: 0.00 to 0.716 (median 0.401), and accuracy rate: 27.5 to 70.5% (median 58.8%). The best-performing prompt-model pair was GPT-4o with role-playing with Chain-of-Thought and few-shot prompting. On average, Llama 3.2-vision performed the best (average YI across prompts 0.181). There was no consistent relationship between the amount of information given in the prompt and the model performance. Conclusions: Non-specialty-trained VLMs could classify photographs of swollen and normal optic discs better than chance, with performance varying by model. Increasing prompt complexity did not consistently improve performance. Specialty-specific VLMs may be necessary to improve ophthalmic image analysis performance.","journal":"Frontiers in Digital Health","year":2025,"id":542166,"datarank":0.16479184330021646,"base_score":1.0986122886681096,"endowment":1.0986122886681096,"self_citation_contribution":0.16479184330021646,"citation_network_contribution":0.0,"self_endowment_contribution":0.16479184330021646,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9562,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1431726,"name":"Tuyet Thao Nguyen","orcid":"0009-0004-5263-1768","position":1,"is_corresponding":false},{"id":327054,"name":"Heather E. Moss","orcid":"0000-0003-4373-447X","position":2,"is_corresponding":false},{"id":1431280,"name":"Kelvin Zhenghao Li","orcid":"0000-0002-9993-5118","position":0,"is_corresponding":true}],"reference_count":11,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:52:55.809501Z","pmid":"40927810","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}