Document resource
Purpose To develop and validate deep learning models predicting keratoconus progression risk using multimodal imaging, enabling risk-stratified monitoring.Design Retrospective cohort study with internal and external validation.Participants 7,396 eyes (3,893 patients) from MS-39 multimodal imaging, 963 eyes (519 patients) for external MS-39 validation, and 4,498 eyes (2,983 patients) with Pentacam tomography data.Methods Progression was defined using global consensus criteria requiring changes in multiple parameters above device-specific precision limits. We compared conventional machine learning (XGBoost), unimodal deep learning, and multimodal fusion architectures for predicting two-year progression from baseline data. Recurrent neural networks (LSTM) incorporated sequential visit data. Clinical utility was assessed through simulated risk-stratified triage using predictive values.Main Outcome Measures AUROC, sensitivity, specificity, PPV, and NPV for progression prediction.Results The MS-39 multimodal model (AS-OCT, Placido, tabular data) achieved AUROC 0.84 (95% CI: 0.83–0.85) at baseline, improving to 0.93 (95% CI: 0.91–0.96) with sequential LSTM models. Pentacam tabular data achieved AUROC 0.81 (95% CI: 0.78–0.84), improving to 0.87 (95% CI: 0.85–0.89) with two-visit LSTM. In simulated triage, 83% of patients were classified as low risk (NPV >90%) and 10% as high risk (PPV >90%) for consideration of early cross-linking.Conclusions AI-driven risk stratification enables efficient monitoring across imaging platforms, with high NPV (>90%) safely reducing follow-up for low-risk patients and high PPV (>90%) ensuring timely intervention for high-risk cases.