Digital Twin Modeling for Acanthamoeba Keratitis: From Empirical Therapy to Predictive Ophthalmology

Acanthamoeba keratitis is a rare, vision-threatening corneal infection that remains difficult to diagnose and treat, with therapy often extending for many months. Despite recent advances, the management of Acanthamoeba keratitis still depends largely on empirical regimens combining biguanides, diamidines, and azoles. Outcomes vary widely, reflecting differences in pathogen virulence, drug penetration, host response, and timing of diagnosis. It is proposed that digital-twin technology offers a powerful new framework for studying and managing this disease. Digital twin is a data-driven computational approach that creates continuously updating virtual replicas of biological systems. By integrating multimodal clinical, imaging, and molecular data, digital twins could simulate corneal infection dynamics, drug diffusion, and cyst reactivation, providing clinicians with predictive insight rather than retrospective interpretation. Here, it is discussed how digital-twin models could be constructed for Acanthamoeba keratitis, challenges to implementation, and implications for precision ophthalmology.