Aplicación de redes neuronales artificiales para la detección binaria del síndrome del ojo rojo
Palabras clave:
Hiperemia ocular, Aprendizaje profundo, visión computacional, clasificación binariaResumen
El síndrome del ojo rojo es uno de los motivos más frecuentes de consulta en atención primaria, y su diagnóstico temprano resulta complejo por la similitud clínica entre diversas etiologías. En este estudio se desarrolló y evaluó un enfoque de detección binaria (“ojo rojo” vs. “normal”) comparando arquitecturas CNN, modelos basados en Transformers y un modelo híbrido. Se empleó un conjunto de 2 298 imágenes reorganizadas en dos clases, entrenadas bajo condiciones homogéneas mediante transfer learning e hiperparámetros fijos. Los experimentos se ejecutaron en Python 3.10.0 con PyTorch 2.7.1+cu118, torchvision 0.22.1+cu118, timm 1.0.17, scikit-learn 1.6.1, NumPy 1.26.4, Albumentations 2.0.8 y Matplotlib 3.8.2, sobre hardware con GPU NVIDIA RTX 4060 (8 GB). Los resultados evidenciaron alto desempeño en todos los modelos (F1 > 0.92, MCC > 0.90 y AUC ≥ 0.98). El modelo híbrido alcanzó el mejor rendimiento global (AUC = 0.996, MCC = 0.925, F1 = 0.924 y exactitud = 94.20 %). La prueba de McNemar indicó que no existen diferencias estadísticamente significativas entre el modelo híbrido y el mejor modelo individual (ResNet).
Citas
Bitto, A. K. (2024). Image Dataset on Eye Diseases Classification (Uveitis, Conjunctivitis, Cataract, Eyelid) with Symptoms and SMOTE Validation. Mendeley Data, 2. https://doi.org/10.17632/n9zp473wfw.2
Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21(1). https://doi.org/10.1186/s12864-019-6413-7
Dag, Y., Seyfi Aydın, & Ebrar Kumantas. (2024). The profile of patients attending to the general emergency department with ocular complaints within the last year: is it a true ocular emergency? BMC Ophthalmology, 24(1). https://doi.org/10.1186/s12886-024-03608-1
Devikala, S., Vinoth, S., Shaby, S. M., Govindaraju, A. B., Vidhya, K., & Vijayalakshmi, K. (2025). A Multi-Component Attention Graph Convolutional Neural Network Optimized by the Gooseneck Barnacle Algorithm for High-Precision ECG Arrhythmia Classification in Sensor-Based Biomedical Systems. Biomedical Signal Processing and Control, 113, 108866. https://doi.org/10.1016/j.bspc.2025.108866
Hasan, M. M., Phu, J., Wang, H., Sowmya, A., Kalloniatis, M., & Meijering, E. (2025). OCT-based diagnosis of glaucoma and glaucoma stages using explainable machine learning. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-87219-w
Hui, J., Ang, E., Srinivasan, S., Lei, X., Loh, J., Quek, T. C., Xue, C., Xu, X., Liu, Y., Cheng, C.-Y., Rajapakse, J. C., & Tham, Y.-C. (2024). Comparative Analysis of Vision Transformers and Conventional Convolutional Neural Networks in Detecting Referable Diabetic Retinopathy. Ophthalmology Science, 4(6), 100552–100552. https://doi.org/10.1016/j.xops.2024.100552
Le, N. T., Le Truong, T., Deelertpaiboon, S., Srisiri, W., Pongsachareonnont, P. F., Suwajanakorn, D., Mavichak, A., Itthipanichpong, R., Asdornwised, W., Benjapolakul, W., Chaitusaney, S., & Kaewplung, P. (2024). ViT‐AMD: A New Deep Learning Model for Age‐Related Macular Degeneration Diagnosis From Fundus Images. International Journal of Intelligent Systems, 2024(1). https://doi.org/10.1155/2024/3026500
Li, Z., Jiang, J., Chen, K., Chen, Q., Zheng, Q., Liu, X., Weng, H., Wu, S., & Chen, W. (2021). Preventing corneal blindness caused by keratitis using artificial intelligence. Nature Communications, 12(1). https://doi.org/10.1038/s41467-021-24116-6
Molina Arias, M. (2024). Un intruso de otro mundo: F1-score. Revista Electrónica AnestesiaR, 16(4), 3. https://doi.org/10.30445//rear.v16i4.1258
Müller, D., Soto-Rey, I., & Kramer, F. (2022). Towards a guideline for evaluation metrics in medical image segmentation. BMC Research Notes, 15(1). https://doi.org/10.1186/s13104-022-06096-y
Ong, Z. Z., Sadek, Y., Qureshi, R., Liu, S.-H., Li, T., Liu, X., Takwoingi, Y., Sounderajah, V., Ashrafian, H., Ting, D. S. W., Mehta, J. S., Rauz, S., Said, D. G., Dua, H. S., Burton, M. J., & Ting, D. S. J. (2024). Diagnostic performance of deep learning for infectious keratitis: a systematic review and meta-analysis. EClinicalMedicine, 77, 102887. https://doi.org/10.1016/j.eclinm.2024.102887
Pan, Y., Liu, J., Cai, Y., Yang, X., Zhang, Z., Long, H., Zhao, K., Yu, X., Zeng, C., Duan, J., Xiao, P., Li, J., Cai, F., Yang, X., & Tan, Z. (2023). Fundus image classification using Inception V3 and ResNet-50 for the early diagnostics of fundus diseases. Frontiers in Physiology, 14. https://doi.org/10.3389/fphys.2023.1126780
Rainio, O., Teuho, J., & Klén, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-56706-x
Rajatha, & Ashoka, D. V. (2025). EffiViT: Hybrid CNN-Transformer for Retinal Imaging. Computers in Biology and Medicine, 191, 110164. https://doi.org/10.1016/j.compbiomed.2025.110164
Reifs Jiménez, D., Casanova-Lozano, L., Grau-Carrión, S., & Reig-Bolaño, R. (2025). Artificial Intelligence Methods for Diagnostic and Decision-Making Assistance in Chronic Wounds: A Systematic Review. Journal of Medical Systems, 49(1). https://doi.org/10.1007/s10916-025-02153-8
Sargolzaeimoghaddam, M., Maral Sargolzaeimoghaddam, Kothari, Z., Sebhat, A. M., & Soleimani, M. (2025). Review of ophthalmic emergencies in primary care: a comprehensive approach to red eye. Annals of Eye Science, 10, 20–20. https://doi.org/10.21037/aes-25-10
Tamimi, A., Allawi, M. N., & Kishore Hanumantharayappa. (2023). Characterization of red eye cases presented to the eye emergency clinic at a tertiary care hospital during COVID-19 Pandemic. Oman Journal of Ophthalmology, 16(2), 220–226. https://doi.org/10.4103/ojo.ojo_224_22
Ueno, Y., Oda, M., Yamaguchi, T., Fukuoka, H., Nejima, R., Kitaguchi, Y., Miyake, M., Akiyama, M., Miyata, K., Kashiwagi, K., Maeda, N., Shimazaki, J., Noma, H., Mori, K., & Oshika, T. (2024). Deep learning model for extensive smartphone-based diagnosis and triage of cataracts and multiple corneal diseases. British Journal of Ophthalmology, 108(10), 1406–1413. https://doi.org/10.1136/bjo-2023-324488
Xu, Z., Xu, J., Shi, C., Xu, W., Jin, X., Han, W., Jin, K., Grzybowski, A., & Yao, K. (2023). Artificial Intelligence for Anterior Segment Diseases: A Review of Potential Developments and Clinical Applications. Ophthalmology and Therapy, 12(3), 1439–1455. https://doi.org/10.1007/s40123-023-00690-4
Zhang, W., Belcheva, V., & Ermakova, T. (2025). Interpretable Deep Learning for Diabetic Retinopathy: A Comparative Study of CNN, ViT, and Hybrid Architectures. Computers, 14(5), 187–187. https://doi.org/10.3390/computers14050187
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2026 Marcelino Torres Villanueva, Juan Pedro Santos Fernández
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
