{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T17:47:49Z","timestamp":1789148869548,"version":"build-2803163510"},"reference-count":56,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Papilledema, an ophthalmic finding associated with increased intracranial pressure, is often induced by dermatological medications, including corticosteroids, isotretinoin, and tetracyclines. Early detection is crucial for preventing irreversible optic nerve damage, but access to ophthalmologic expertise is often limited in rural settings. Artificial intelligence (AI) may enable the automated and accurate detection of papilledema from fundus images, thereby supporting timely diagnosis and management. Objective: The primary objective of this study was to explore the diagnostic capability of ChatGPT-4o, a general large language model with multimodal input, in identifying papilledema from fundus photographs. For context, its performance was compared with a ResNet-based convolutional neural network (CNN) specifically fine-tuned for ophthalmic imaging, as well as with the assessments of two human ophthalmologists. The focus was on applications relevant to dermatological care in resource-limited environments. Methods: A dataset of 1094 fundus images (295 papilledema, 799 normal) was preprocessed and partitioned into a training set and a test set. The ResNet model was fine-tuned using discriminative learning rates and a one-cycle learning rate policy. GPT-4o and two human evaluators (a senior ophthalmologist and an ophthalmology resident) independently assessed the test images. Diagnostic metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and Cohen\u2019s Kappa, were calculated for each evaluator. Results: GPT-4o, when applied to papilledema detection, achieved an overall accuracy of 85.9% with substantial agreement beyond chance (Cohen\u2019s Kappa = 0.72), but lower specificity (78.9%) and positive predictive value (73.7%) compared to benchmark models. For context, the ResNet model, fine-tuned for ophthalmic imaging, reached near-perfect accuracy (99.5%, Kappa = 0.99), while two human ophthalmologists achieved accuracies of 96.0% (Kappa \u2248 0.92). Conclusions: This study explored the capability of GPT-4o, a large language model with multimodal input, for detecting papilledema from fundus photographs. GPT-4o achieved moderate diagnostic accuracy and substantial agreement with the ground truth, but it underperformed compared to both a domain-specific ResNet model and human ophthalmologists. These findings underscore the distinction between generalist large language models and specialized diagnostic AI: while GPT-4o is not optimized for ophthalmic imaging, its accessibility, adaptability, and rapid evolution highlight its potential as a future adjunct in clinical screening, particularly in underserved settings. These findings also underscore the need for validation on external datasets and real-world clinical environments before such tools can be broadly implemented.<\/jats:p>","DOI":"10.3390\/diagnostics15192547","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:54:31Z","timestamp":1760028871000},"page":"2547","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Exploring AI\u2019s Potential in Papilledema Diagnosis to Support Dermatological Treatment Decisions in Rural Healthcare"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5154-7984","authenticated-orcid":false,"given":"Jonathan","family":"Shapiro","sequence":"first","affiliation":[{"name":"Maccabi Healthcare Services, Tel Aviv 6817110, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7020-7224","authenticated-orcid":false,"given":"Mor","family":"Atlas","sequence":"additional","affiliation":[{"name":"Business Administration Faculty, Ono Academic College, Kiryat Ono 5510701, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3711-1655","authenticated-orcid":false,"given":"Naomi","family":"Fridman","sequence":"additional","affiliation":[{"name":"NF Algorithms & AI, Tel Aviv 6248906, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4827-7075","authenticated-orcid":false,"given":"Itay","family":"Cohen","sequence":"additional","affiliation":[{"name":"Rutgers School of Public Health, Rutgers University, Piscataway, NJ 08854, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9586-2807","authenticated-orcid":false,"given":"Ziad","family":"Khamaysi","sequence":"additional","affiliation":[{"name":"Department of Dermatology, Rambam Health Care Campus, Haifa 3109601, Israel"},{"name":"The Bruce and Ruth Rappaport Faculty of Medicine, Technion\u2014Israel Institute of Technology, Haifa 3525433, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahdi","family":"Awwad","sequence":"additional","affiliation":[{"name":"Tzafon Medical Center, Ophthalmology Unit, Tiberias 1521000, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9110-7506","authenticated-orcid":false,"given":"Naomi","family":"Silverstein","sequence":"additional","affiliation":[{"name":"Technion Institute of Technology, Haifa 3200003, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1140-1040","authenticated-orcid":false,"given":"Tom","family":"Kozlovsky","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Edith Wolfson Medical Center, Holon 5822012, Israel"},{"name":"Gray School of Medicine, Tel-Aviv University, Tel Aviv 6997801, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2960-2809","authenticated-orcid":false,"given":"Idit","family":"Maharshak","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Edith Wolfson Medical Center, Holon 5822012, Israel"},{"name":"Gray School of Medicine, Tel-Aviv University, Tel Aviv 6997801, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"ref_1","first-page":"e24915","article-title":"Optic Disc Edema and Elevated Intracranial Pressure (ICP): A Comprehensive Review of Papilledema","volume":"14","author":"Reier","year":"2022","journal-title":"Cureus"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Orylska-Ratynska, M., Placek, W., and Owczarczyk-Saczonek, A. (2022). Tetracyclines-An Important Therapeutic Tool for Dermatologists. Int. J. Environ. Res. Public Health, 19.","DOI":"10.20944\/preprints202205.0056.v1"},{"key":"ref_3","unstructured":"Yasir, M., Goyal, A., and Sonthalia, S. (2025). Corticosteroid Adverse Effects. StatPearls, StatPearls."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/s40257-019-00485-z","article-title":"Drug-Induced Intracranial Hypertension: A Systematic Review and Critical Assessment of Drug-Induced Causes","volume":"21","author":"Tan","year":"2020","journal-title":"Am. J. Clin. Dermatol."},{"key":"ref_5","first-page":"47","article-title":"Papilledema: Epidemiology, etiology, and clinical management","volume":"7","author":"Rigi","year":"2015","journal-title":"Eye Brain"},{"key":"ref_6","unstructured":"Gabros, S., Nessel, T.A., and Zito, P.M. (2025). Topical Corticosteroids. StatPearls, StatPearls."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e242455","DOI":"10.1136\/bcr-2021-242455","article-title":"Benign intracranial hypertension associated with inhaled corticosteroids in a child with asthma","volume":"14","author":"Trayer","year":"2021","journal-title":"BMJ Case Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4553","DOI":"10.1007\/s10072-023-07039-6","article-title":"Intracranial hypertension after rosacea treatment with isotretinoin","volume":"44","author":"Reifenrath","year":"2023","journal-title":"Neurol. Sci."},{"key":"ref_9","unstructured":"Pile, H.D., Patel, P., and Sadiq, N.M. (2025). Isotretinoin. StatPearls, StatPearls."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"29","DOI":"10.2165\/00128071-200506010-00004","article-title":"Medication-induced intracranial hypertension in dermatology","volume":"6","author":"Friedman","year":"2005","journal-title":"Am. J. Clin. Dermatol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1212\/WNL.45.1.6","article-title":"Idiopathic intracranial hypertension associated with tetracycline use in fraternal twins: Case reports and review","volume":"45","author":"Gardner","year":"1995","journal-title":"Neurology"},{"key":"ref_12","unstructured":"Shutter, M.C., and Akhondi, H. (2025). Tetracycline. StatPearls, StatPearls."},{"key":"ref_13","first-page":"14","article-title":"Nonantibiotic Properties of Tetracyclines in Rosacea and Their Clinical Implications","volume":"14","author":"Webster","year":"2021","journal-title":"J. Clin. Aesthet. Dermatol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"354","DOI":"10.18502\/jovr.v19i3.15893","article-title":"Application of Artificial Intelligence in Ophthalmology: An Updated Comprehensive Review","volume":"19","author":"Hashemian","year":"2024","journal-title":"J. Ophthalmic Vis. Res."},{"key":"ref_15","first-page":"264","article-title":"Promising Artificial Intelligence-Machine Learning-Deep Learning Algorithms in Ophthalmology","volume":"8","author":"Balyen","year":"2019","journal-title":"Asia Pac. J. Ophthalmol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.ajo.2024.02.012","article-title":"Diagnostic Accuracy of Artificial Intelligence-Based Automated Diabetic Retinopathy Screening in Real-World Settings: A Systematic Review and Meta-Analysis","volume":"263","author":"Joseph","year":"2024","journal-title":"Am. J. Ophthalmol."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Olawade, D.B., Weerasinghe, K., Mathugamage, M., Odetayo, A., Aderinto, N., Teke, J., and Boussios, S. (2025). Enhancing Ophthalmic Diagnosis and Treatment with Artificial Intelligence. Medicina, 61.","DOI":"10.3390\/medicina61030433"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Tonti, E., Tonti, S., Mancini, F., Bonini, C., Spadea, L., D\u2019Esposito, F., Gagliano, C., Musa, M., and Zeppieri, M. (2024). Artificial Intelligence and Advanced Technology in Glaucoma: A Review. J. Pers. Med., 14.","DOI":"10.3390\/jpm14101062"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"101095","DOI":"10.1016\/j.xcrm.2023.101095","article-title":"Artificial intelligence in ophthalmology: The path to the real-world clinic","volume":"4","author":"Li","year":"2023","journal-title":"Cell Rep. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e188","DOI":"10.7861\/fhj.2021-0095","article-title":"Artificial intelligence in healthcare: Transforming the practice of medicine","volume":"8","author":"Bajwa","year":"2021","journal-title":"Future Healthc. J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"100951","DOI":"10.1016\/j.xcrm.2023.100951","article-title":"Solving data quality issues of fundus images in real-world settings by ophthalmic AI","volume":"4","author":"Li","year":"2023","journal-title":"Cell Rep. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3825","DOI":"10.2147\/JMDH.S441790","article-title":"Are Different Versions of ChatGPT\u2019s Ability Comparable to the Clinical Diagnosis Presented in Case Reports? A Descriptive Study","volume":"16","author":"Chen","year":"2023","journal-title":"J. Multidiscip. Healthc."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1097\/WNO.0000000000002223","article-title":"A Deep Learning Approach for Accurate Discrimination Between Optic Disc Drusen and Papilledema on Fundus Photographs","volume":"44","author":"Sathianvichitr","year":"2024","journal-title":"J. Neuroophthalmol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3066","DOI":"10.1002\/jemt.23865","article-title":"Automatic detection of papilledema through fundus retinal images using deep learning","volume":"84","author":"Saba","year":"2021","journal-title":"Microsc. Res. Tech."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1056\/NEJMoa1917130","article-title":"Artificial Intelligence to Detect Papilledema from Ocular Fundus Photographs","volume":"382","author":"Milea","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1097\/IAE.0000000000004351","article-title":"Retinal imaging analysis performed by ChatGPT-4O and Gemini Advanced: The turning point of the revolution?","volume":"45","author":"Carla","year":"2025","journal-title":"Retina"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"100078","DOI":"10.1016\/j.aopr.2022.100078","article-title":"Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives","volume":"2","author":"Jin","year":"2022","journal-title":"Adv. Ophthalmol. Pract. Res."},{"key":"ref_29","first-page":"3469","article-title":"Artificial intelligence and deep learning in ophthalmology\u2014Present and future (Review)","volume":"20","author":"Moraru","year":"2020","journal-title":"Exp. Ther. Med."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Goktas, P., and Grzybowski, A. (2024). Assessing the Impact of ChatGPT in Dermatology: A Comprehensive Rapid Review. J. Clin. Med., 13.","DOI":"10.3390\/jcm13195909"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1367","DOI":"10.1093\/ced\/llae184","article-title":"An evaluation of ChatGPT compared with dermatological surgeons\u2019 choices of reconstruction for surgical defects after Mohs surgery","volume":"49","year":"2024","journal-title":"Clin. Exp. Dermatol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1111\/ijd.16913","article-title":"OpenAI\u2019s GPT-4 performs to a high degree on board-style dermatology questions","volume":"63","author":"Elias","year":"2024","journal-title":"Int. J. Dermatol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Ahn, J.M., Kim, S., Ahn, K.S., Cho, S.H., and Kim, U.S. (2019). Accuracy of machine learning for differentiation between optic neuropathies and pseudopapilledema. BMC Ophthalmol., 19.","DOI":"10.1186\/s12886-019-1184-0"},{"key":"ref_34","unstructured":"OpenMEDLab (2025, February 21). Awesome-Medical-Dataset: Papilledema.md (Resources Folder). GitHub Repository: Openmedlab\/Awesome-Medical-Dataset. Available online: https:\/\/github.com\/openmedlab\/Awesome-Medical-Dataset\/blob\/main\/resources\/Papilledema.md."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Shibata, N., Tanito, M., Mitsuhashi, K., Fujino, Y., Matsuura, M., Murata, H., and Asaoka, R. (2018). Development of a deep residual learning algorithm to screen for glaucoma from fundus photography. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-33013-w"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Howard, J., and Ruder, S. (2018, January 15\u201320). Universal Language Model Fine-tuning for Text Classification. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia.","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref_39","unstructured":"Smith, L.N. (2018). A disciplined approach to neural network hyper-parameters: Part 1\u2014Learning rate, batch size, momentum, and weight decay. arXiv."},{"key":"ref_40","first-page":"360","article-title":"Understanding interobserver agreement: The kappa statistic","volume":"37","author":"Viera","year":"2005","journal-title":"Fam. Med."},{"key":"ref_41","first-page":"e73660","article-title":"Evaluating ChatGPT\u2019s Diagnostic Accuracy in Detecting Fundus Images","volume":"16","author":"Gupta","year":"2024","journal-title":"Cureus"},{"key":"ref_42","first-page":"311","article-title":"The use of a ChatGPT-4-based chatbot in teledermatology: A retrospective exploratory study","volume":"23","author":"Shapiro","year":"2025","journal-title":"J. Dtsch. Dermatol. Ges."},{"key":"ref_43","unstructured":"Wang, S., Hu, M., Li, Q., Safari, M., and Yang, X. (2025). Capabilities of GPT-5 on Multimodal Medical Reasoning. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"AlRyalat, S.A., Musleh, A.M., and Kahook, M.Y. (2024). Evaluating the strengths and limitations of multimodal ChatGPT-4 in detecting glaucoma using fundus images. Front. Ophthalmol., 4.","DOI":"10.3389\/fopht.2024.1387190"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1097\/APO.0000000000000512","article-title":"Artificial Intelligence Meets Neuro-Ophthalmology","volume":"11","author":"Leong","year":"2022","journal-title":"Asia Pac. J. Ophthalmol."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ahn, S.J., and Kim, Y.H. (2024). Clinical Applications and Future Directions of Smartphone Fundus Imaging. Diagnostics, 14.","DOI":"10.3390\/diagnostics14131395"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Wintergerst, M.W.M., Brinkmann, C.K., Holz, F.G., and Finger, R.P. (2018). Undilated versus dilated monoscopic smartphone-based fundus photography for optic nerve head evaluation. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-28585-6"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1097\/ICU.0000000000000987","article-title":"Recent evidence of economic evaluation of artificial intelligence in ophthalmology","volume":"34","author":"Ruamviboonsuk","year":"2023","journal-title":"Curr. Opin. Ophthalmol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"e230970","DOI":"10.1148\/radiol.230970","article-title":"A Context-based Chatbot Surpasses Trained Radiologists and Generic ChatGPT in Following the ACR Appropriateness Guidelines","volume":"308","author":"Rau","year":"2023","journal-title":"Radiology"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Savelka, J., and Ashley, K.D. (2023). The unreasonable effectiveness of large language models in zero-shot semantic annotation of legal texts. Front. Artif. Intell., 6.","DOI":"10.3389\/frai.2023.1279794"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"4750","DOI":"10.1038\/s41467-024-48972-0","article-title":"Fairer AI in ophthalmology via implicit fairness learning for mitigating sexism and ageism","volume":"15","author":"Tan","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_52","first-page":"55958","article-title":"Smartphone Fundus Photography","volume":"125","author":"Nakatsuka","year":"2017","journal-title":"J. Vis. Exp."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"663","DOI":"10.4103\/0301-4738.194325","article-title":"Do it yourself smartphone fundus camera\u2014DIYretCAM","volume":"64","author":"Raju","year":"2016","journal-title":"Indian J. Ophthalmol."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1988","DOI":"10.1038\/s41433-021-01804-7","article-title":"Selfie fundus imaging for diabetic retinopathy screening","volume":"36","author":"Kumari","year":"2022","journal-title":"Eye"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1136\/leader-2023-000904","article-title":"Global perspectives on governing healthcare AI: Prioritising safety, equity and collaboration","volume":"9","year":"2025","journal-title":"BMJ Lead"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1111\/his.14356","article-title":"The human-in-the-loop: An evaluation of pathologists\u2019 interaction with artificial intelligence in clinical practice","volume":"79","author":"Boden","year":"2021","journal-title":"Histopathology"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/19\/2547\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T09:59:27Z","timestamp":1760090367000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/19\/2547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":56,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["diagnostics15192547"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15192547","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]}}}