Optical Coherence Tomography Radiomics and Machine Learning Enable Accurate Detection of Forme Fruste Keratoconus

Clinical Snapshot

Key Findings

• P Value: P > 0.05 for model comparisons

• Effect Size: AUC = 0.93 for XGBoost model

• Primary Outcome: Diagnostic accuracy for forme fruste keratoconus detection

• Nnt Or Sensitivity: Sensitivity 0.857, Specificity 0.978

• Confidence Interval: 95% CI: 0.829-1.0

Clinical Application

Requires OCT imaging capability and specialized radiomics analysis software - may be limited to tertiary centers initially Could complement existing keratoconus screening protocols in Australian ophthalmology practices, though TGA approval would be required for clinical implementation of the diagnostic algorithm Patients at risk for keratoconus requiring early detection, particularly those with family history or refractive surgery candidates

Abstract

PURPOSE: To evaluate the diagnostic performance of a radiomics-based machine learning approach applied to corneal optical coherence tomography (OCT) images for detecting forme fruste keratoconus (FFKC). DESIGN: Evaluation of machine learning diagnostic algorithms. METHODS: OCT images from 307 eyes (234 normal, 73 FFKC) were acquired along eight meridians (M1-M8). All images underwent preprocessing before texture-based radiomics feature extraction. Three machine learning classifiers-Random Forest, C5.0, and XGBoost-were trained using a feature subset selected by recursive feature elimination (RFE). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. RESULTS: A total of 3752 features were extracted per eye, of which 41 were selected for model training. All three models demonstrated strong diagnostic performance in the test set (AUCs > 0.92), with no significant differences between models (P > .05). The XGBoost model achieved the highest performance (AUC = 0.93, 95% CI: 0.829-1.0, sensitivity 0.857, specificity = 0.978, accuracy = 0.950). Among the top 10 XGBoost features ranked by importance, a preferred meridional distribution was observed, with most features concentrated along M1 to M3, corresponding to the inferotemporal corneal region. CONCLUSION: Radiomics analysis of corneal OCT images combined with machine learning enables accurate FFKC detection using a single imaging device, providing diagnostic information beyond conventional morphological assessment and suggesting a potential imaging biomarker for early keratoconus screening.

References

1. 1.Luo, S., Li, X., Lin, K., Bao, F., Chen, S., Lu, F., & Wang, J. (2026). Optical coherence tomography radiomics and machine learning enable accurate detection of forme fruste keratoconus. American Journal of Ophthalmology. https://doi.org/10.1016/j.ajo.2026.02.018