To develop and validate a machine learning (ML) diagnostic system that integrates Scheimpflug tomography, corneal biomechanics, and clinical risk factors (CRF) to enhance the early detection of keratoconus (KC).Prospective, multicenter, cross-sectional study.Patients diagnosed with KC and individuals evaluated in preoperative refractive surgery clinics.Demographic, lifestyle, and clinical ophthalmic data, including Pentacam and Corvis ST measurements, were collected from patients with KC and refractive surgery candidates across five centers between 2020 and 2024. The dataset was divided into training, validation, internal test, and external test sets. Least absolute shrinkage and selection operator regression was used to identify predictive variables. Six ML models were trained using four feature sets: CRF, device-derived parameters, combined features, and selected features.Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC).The dataset included 1,035 eyes from 1,035 participants across five centers: 590 normal controls, 157 eyes with forme fruste keratoconus (FFKC), 143 with subclinical KC, and 145 with clinical KC. For FFKC detection, the post-feature selection CatBoost model achieved the highest accuracy (AUROC = 0.975), outperforming the combined-feature (AUROC = 0.963), CRF-only (AUROC = 0.856), and device-only models (AUROC = 0.885) in the test set. This model also outperformed the tomographic and biomechanical index in internal (AUROC = 0.976 vs. 0.813; p = 0.048) and external validation (AUROC = 0.952 vs. 0.847; p = 0.012). For subclinical and clinical KC, external validation yielded near-perfect performance (AUROC = 0.991 and 1.000, respectively).A multimodal ML system integrating CRF, tomography, and biomechanics improved early KC detection, particularly for FFKC. This approach may enhance clinical decision-making and screening for refractive surgery candidates.Copyright © 2025. Published by Elsevier Inc.