OptiDON-Guard: An Ensemble Model for Identification of Dysthyroid Optic Neuropathy Using Optical Coherence Tomography Angiography

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: AUC 0.872 (internal validation), 0.854 (external test)

• Primary Outcome: Diagnostic accuracy for identifying dysthyroid optic neuropathy

• Nnt Or Sensitivity: Sensitivity 66.7% (internal), 76.7% (external); Specificity 97.9% (internal), 84.2% (external)

• Confidence Interval: Not reported

Clinical Application

Requires OCTA imaging capability and machine learning infrastructure, which may limit accessibility in some settings OCTA is available in major Australian ophthalmology centers. Would need TGA approval for clinical use. Could complement existing RACGP thyroid eye disease management guidelines Patients with thyroid eye disease requiring assessment for dysthyroid optic neuropathy

Abstract

PURPOSE: To explore the value of machine learning models based on optical coherence tomography angiography (OCTA) in identifying dysthyroid optic neuropathy (DON). METHODS: A retrospective, dual-center, cross-sectional study was conducted involving 346 thyroid eye disease patients (with/without DON) from two institutions. Participants underwent ophthalmic examinations, including OCTA scans centered on the macula and optic nerve head. The OCTA data from Center 1 were split into a training set and an internal validation set, while the data from Center 2 served as an external test set. Features were extracted from OCTA images, and a wrapper-based feature selection strategy identified the optimal subset. A two-tiered stacking modeling framework was used, incorporating baseline model construction, data augmentation using pseudo-labeling, and ensemble integration. Model performance (area under the curve [AUC], accuracy, sensitivity, specificity, precision) was evaluated alongside receiver operating characteristic, calibration, and decision curve analyses. Additionally, the SHapley Additive exPlanation method was used to interpret feature contributions. RESULTS: The ensemble model, OptiDON-Guard, demonstrated superior performance to individual models on both internal validation and external test sets. In the internal validation set, it achieved an AUC of 0.872, accuracy of 0.943, sensitivity of 0.667, specificity of 0.979, and precision of 0.943. In the external test set, it maintained strong performance with an AUC of 0.854, accuracy of 0.816, sensitivity of 0.767, specificity of 0.842, and precision of 0.854. CONCLUSIONS: The OptiDON-Guard is a reliable, interpretable, and clinically applicable tool for identifying DON. TRANSLATIONAL RELEVANCE: The OptiDON-Guard offers a valuable clinical tool to enhance the diagnostic precision of DON.

References

1. 1.Zhang, Y., Mao, Y., Zheng, J., Wang, L., Wu, M., Zhao, J., Li, Z., Liu, W., Zhou, S., Wan, S., Tu, Y., Wu, W., & Yan, W. (2026). OptiDON-Guard: An ensemble model for identification of dysthyroid optic neuropathy using optical coherence tomography angiography. Translational Vision Science & Technology, 15(4), 4. https://doi.org/10.1167/tvst.15.4.4