Artificial intelligence for cataract diagnosis and referral using real-world database
DOI:
https://doi.org/10.59681/2175-4411.v17.2025.1441Palavras-chave:
Artificial Intelligence, Diagnosis, CataractResumo
The use of artificial intelligence (AI) for ophthalmology applications has shown g promising results worldwide; however, its performance is dependent on population groups and must be evaluated in real-world scenarios. We evaluated the use of AI for cataract diagnosis and referral to specialists using a real-world database consisting of 2642 eye images from a working telemedicine service in South Brazil. Our AI solution adopts an ensemble model to improve classifier performance. The best results showed an accuracy of 90.6% for cataract diagnosis with a corresponding area under the receiver operating characteristic curve (ROC AUC) of 96.7%. The accuracy for surgical referral was 86.5% with a corresponding ROC AUC of 94.3%. The results indicate that the use of an ensemble of models and training with a heterogeneous real-world clinical database enabled our solution to achieve superior performance compared to other works in the literature when evaluated on real-world data.
Downloads
Referências
Gutierrez L, Lim JS, Foo LL, Ng WY, Yip M, Lim GYS, et al. Application of artificial intelligence in cataract management: current and future directions. Eye Vis. 2022;9(1):1–11. DOI: https://doi.org/10.1186/s40662-021-00273-z
Gunasekeran DV, Wong TY. Artificial intelligence in ophthalmology in 2020: A technology on the cusp for translation and implementation. Asia-Pacific J Ophthalmol. 2020;9(2):61–6. DOI: https://doi.org/10.1097/01.APO.0000656984.56467.2c
Ting DSJ, Foo VHX, Yang LWY, Sia JT, Ang M, Lin H, et al. Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology. British Journal of Ophthalmology. 2021. DOI: https://doi.org/10.1136/bjophthalmol-2019-315651
Lin H, Liu L, Wu X., Artificial Intelligence for Cataract Management. Artificial Intelligence in Ophthalmology. 2021:203–6. DOI: https://doi.org/10.1007/978-3-030-78601-4_16
Tong Y, Lu W, Yu Y, Shen Y. Application of machine learning in ophthalmic imaging modalities. Eye Vis. 2020;7(1). DOI: https://doi.org/10.1186/s40662-020-00183-6
Zhang XQ, Hu Y, Xiao, ZJ, Fang JS, Higashita R, Liu J, Machine learning for cataract classification/grading on ophthalmic imaging modalities: A survey. Mach. Intell. Res. 2022;19(3):184–208. DOI: https://doi.org/10.1007/s11633-022-1329-0
Orfao J, van der Haar D. A Comparison of Computer Vision Methods for the Combined Detection of Glaucoma, Diabetic Retinopathy and Cataracts. In: Lecture Notes in Computer Science. 2021. DOI: https://doi.org/10.1007/978-3-030-80432-9_3
Alam M, Hallak JA. AI-automated referral for patients with visual impairment. Lancet Digit Heal [Internet]. 2021;3(1):e2–3 DOI: https://doi.org/10.1016/S2589-7500(20)30286-7
Wu X, Xu D, Ma T, Li ZH, Ye Z, Wang F, et al. Artificial Intelligence Model for Antiinterference Cataract Automatic Diagnosis: A Diagnostic Accuracy Study. Front Cell Dev Biol. 2022;10(July):1–11. DOI: https://doi.org/10.3389/fcell.2022.906042
Wu X, Huang Y, Liu Z, Lai W, Long E, Zhang K, et al. Universal artificial intelligence platform for collaborative management of cataracts. British Journal of Ophthalmology. 2019;103(11):1553–60. DOI: https://doi.org/10.1136/bjophthalmol-2019-314729
Pratap T, Dhulipalla VR, Kokil P. Computer-aided Cataract Diagnosis with Fundus Retinal Images under Noisy Conditions. IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) 2024:1–18. DOI: https://doi.org/10.1109/IATMSI60426.2024.10502479
Kassoff A, Kassoff J, Mehu M, Buehler JA, Eglow M, Kaufman F, et al. The Age-Related Eye Disease Study (AREDS) system for classifying cataracts from photographs: AREDS Report No. 4. Am J Ophthalmol. 2001;131(2):167–75. DOI: https://doi.org/10.1016/S0002-9394(00)00732-7
Maaliw RR, Alon AS, Lagman AC, Garcia MB, Abante MV, Belleza RC, et al.. Cataract Detection and Grading Using Ensemble Neural Networks and Transfer Learning. IEEE Annual Information Technology, Electronics and Mobile Communication Conference. 2022:1-9. DOI: https://doi.org/10.1109/IEMCON56893.2022.9946550
Tham YC, Anees A, Zhang L, Goh JHL, Rim TH, Nusinovici S, et al. Referral for disease-related visual impairment using retinal photograph-based deep learning: a proof-of-concept, model development study. Lancet Digit Heal [Internet]. 2021;3(1):e29–40. DOI: https://doi.org/10.1016/S2589-7500(20)30271-5
Jiang L, Huang D, Liu M, Yang W. Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels. In: 37th International Conference on Machine Learning, ICML 2020. 2020.
Yahata E, Winnikow EP, Suyama R, Simoes PW. Explainability in Machine Learning Predictive Models in Breast Cancer. Journal of Health Informatics, 2022;15(Especial). DOI: https://doi.org/10.59681/2175-4411.v15.iEspecial.2023.1090
Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett. 2006;27(8):861–74. DOI: https://doi.org/10.1016/j.patrec.2005.10.010
Chauhan K, Kashish, Dagar K, Yadav RK. Cataract detection from eye fundus image using an ensemble of transfer learning models. Intern Conference on Advance Computing and Innovative Technologies in Engineering. 2022:2194-98. DOI: https://doi.org/10.1109/ICACITE53722.2022.9823638
Chollet F. Deep Learning with Python Manning. 2018.
Gao X, Wong DWK, Ng TT, Cheung CYL, Cheng CY, Wong TY. Automatic grading of cortical and PSC cataracts using retroillumination lens images. Lect Notes Comput Sci . 2013;7725 LNCS(PART 2):256–67. DOI: https://doi.org/10.1007/978-3-642-37444-9_20
de Araujo AL, Moreira TC, Rados DRV, Gross PB, Bastos CGM, Katz N, et al. The use of telemedicine to support Brazilian primary care physicians in managing eye conditions: The Teleoftalmo project. PLoS One. 2020;15(4):1–12. DOI: https://doi.org/10.1371/journal.pone.0231034
Carneiro T, Da Nobrega RVM, Nepomuceno T, Bian G Bin, De Albuquerque VHC, Filho PPR. Performance Analysis of Google Colaboratory as a Tool for Accelerating Deep Learning Applications. IEEE Access. 2018;6:61677–85. DOI: https://doi.org/10.1109/ACCESS.2018.2874767
Ramlan LA, Zaki WMDW, Mutalib HÁ, Hussain A, Mustapha A. Cataract Detection using Pupil Patch Classification and Ruled-based System in Anterior Segment Photographed Images. Symposium on Computer Applications & Industrial Electronics. 2023: 124-9. DOI: https://doi.org/10.1109/ISCAIE57739.2023.10165004
Kaur N, Gupta G. Cataract Disease Diagnosis Using SURF Features and Pre-Trained Variants of an EfficientNet Model: Comparative Analysis. Inter Conf Comp, Autom and Know Manag (ICCAKM) 2023:1-6. DOI: https://doi.org/10.1109/ICCAKM58659.2023.10449495
Shimizu, E, Tanji M, Nakayama S, Ishikawa T, Agata N, Yokoiwa R , Nishimura H, et al. AI-based diagnosis of nuclear cataract from slit-lamp videos. Sci Rep 13, 22046 (2023). DOI: https://doi.org/10.1038/s41598-023-49563-7
Downloads
Publicado
Como Citar
Edição
Secção
Licença
Direitos de Autor (c) 2025 Marcelo Negreiros, Ronaldo Husemann, Valter Roesler, Aline L. de Araujo, Dimitris Rucks Varvaki Rados , Felipe C. Cabral, Natan Katz
Este trabalho encontra-se publicado com a Licença Internacional Creative Commons Atribuição-NãoComercial-CompartilhaIgual 4.0.
A submissão de um artigo ao Journal of Health Informatics é entendida como exclusiva e que não está sendo considerada para publicação em outra revista (Declaração de Exclusividade). A permissão dos autores para a publicação de seu artigo no J. Health Inform. implica na exclusiva autorização concedida aos editores para incluí-lo na revista. Ao submeter um artigo, ao autor será solicitada a permissão de um Termo de Transferência de Direitos de Publicação. Uma mensagem eletrônica será enviada ao autor correspondente confirmando o recibo do manuscrito e o aceite da Declaração de Direito de Publicação.
