Machine Learning for Predicting Recurrent Course in Uveitis Using Baseline Clinical Characteristics
Investigative Ophthalmology & Visual Science · 2025-08-27 · 66 (11) · 67
DOI: 10.1167/iovs.66.11.67 ↗At a glance
Journal article in Investigative Ophthalmology & Visual Science, published on 2025-08-27. Written by William Rojas-Carabali and 14 co-authors. Institution: Programme for Ocular Inflammation & Infection Translational Research, Department of Ophthalmology, National Healthcare Group Eye Institute, Tan Tock …. Major MEDLINE topics: Uveitis, Machine Learning. Cited 11 times so far (Crossref); 29 references. The full text is freely available (open access, CC BY-NC-ND 4.0).
Abstract (original language)
Purpose
We developed and evaluated machine learning models for predicting the risk of recurrent uveitis using baseline clinical characteristics, to inform clinical decision-making and risk stratification.
Methods
A retrospective analysis was conducted using the Ocular Autoimmune Systemic Inflammatory Infectious Study registry, including 966 patients (1432 eyes) with uveitis. Three machine learning classifiers-random Forest, eXtreme Gradient Boosting, and radial basis function support vector classifier-were trained on preprocessed baseline demographic and clinical data. Predictors were selected through bivariate analysis with false discovery rate correction. Models were optimized using grid search with five-fold stratified cross-validation. Performance was evaluated on a hold-out test set using accuracy, sensitivity, specificity, area under the receiver operating characteristic curve, and Shapley additive explanations values for feature importance.
Results
The random Forest model achieved the highest test accuracy (0.77), with high specificity (0.93) but modest sensitivity (0.44) for identifying recurrences. eXtreme Gradient Boosting and radial basis function support vector classifier showed comparable accuracies (0.73 and 0.74, respectively) but slightly lower sensitivities. Shapley additive explanation analysis identified vitreous haze, retrolental cells, and noninfectious etiology as key predictors. Learning curves indicated that model performance stabilized with the available sample size, suggesting adequate training data.
Conclusions
Machine learning models, particularly random Forest, effectively identified patients at low risk of uveitis recurrence, offering high specificity. However, sensitivity remained limited, highlighting challenges in predicting infrequent events in a heterogeneous disease population.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- Programme for Ocular Inflammation & Infection Translational Research, Department of Ophthalmology, National Healthcare Group Eye Institute, Tan Tock Seng Hospital, Singapore, Singapore.
- Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore.
- National Healthcare Group Eye Institute, Tan Tock Seng Hospital, Singapore, Singapore.
- Jakarta Eye Centre, Jakarta, Indonesia.
- Dr Shroff's Charity Eye Hospital, New Delhi, India.
- Department of Ophthalmology and Schepens Eye Research Institute, Massachusetts Eye and Ear/ Harvard Medical School, Boston, Massachusetts, United States.
Cite
APA
Rojas-Carabali, W., Cifuentes-González, C., Utami, A., Agarwal, M., Kempen, J. H., Tsui, E., Finger, R. P., Sen, A., Chan, A., Schlaen, A., Gupta, V., de-la-Torre, A., Lee, B., Agrawal, R., & PROTON Study Group (2025). Machine Learning for Predicting Recurrent Course in Uveitis Using Baseline Clinical Characteristics. Investigative Ophthalmology & Visual Science, 66(11), 67. https://doi.org/10.1167/iovs.66.11.67
Vancouver
Rojas-Carabali W, Cifuentes-González C, Utami A, Agarwal M, Kempen JH, Tsui E, et al. Machine Learning for Predicting Recurrent Course in Uveitis Using Baseline Clinical Characteristics. Investigative Ophthalmology & Visual Science. 2025;66(11):67. doi:10.1167/iovs.66.11.67
BibTeX
@article{RojasCarabali2025,
author = {Rojas-Carabali, William and Cifuentes-González, Carlos and Utami, Anna and Agarwal, Manisha and Kempen, John H and Tsui, Edmund and Finger, Robert P and Sen, Alok and Chan, Anita and Schlaen, Ariel and Gupta, Vishali and de-la-Torre, Alejandra and Lee, Bernett and Agrawal, Rupesh and PROTON Study Group, PROTON Study Group},
title = {Machine Learning for Predicting Recurrent Course in Uveitis Using Baseline Clinical Characteristics},
journal = {Investigative Ophthalmology & Visual Science},
year = {2025},
volume = {66},
number = {11},
pages = {67},
doi = {10.1167/iovs.66.11.67}
}
EUVIMED