Machine Learning Identifies Predictors of Amniotic Membrane Graft Failure in Neurotrophic Keratitis

Neurotrophic keratitis (NK) is a rare, vision-threatening corneal disease characterized by impaired epithelial healing and frequent recurrence of defects. Amniotic membrane transplantation (AMT) is an established therapeutic option, but outcomes remain variable and predictors of failure are poorly defined. We aimed to identify clinical and systemic factors associated with recurrence following AMT using both classical statistics and machine learning approaches.

We conducted a retrospective cohort study of 66 patients with NK who underwent AMT at a tertiary referral center between 2019 and 2025. The primary endpoint was post-AMT epithelial defect recurrence. The prespecified primary analysis was a multivariable logistic regression, complemented by exploratory machine learning approaches. Clinical, demographic, and ophthalmic variables were abstracted from medical records. All patients had complete outcome data; covariate-level missingness was minimal and handled with complete-case analyses. Associations with recurrence were examined using bivariate tests and multivariable regression; data structure was explored with principal component analysis (PCA) and hierarchical clustering; and predictive performance was additionally evaluated using random forest classifiers.

Epithelial defect recurrence occurred in 46 patients (70%). Multivariable analysis identified systemic immunosuppressive therapy (odds ratio [OR] 19.9; p = 0.023) and number of AMTs (OR 2.73 per graft; p = 0.040) as independent predictors, with prior ocular surgery showing a borderline association (p = 0.060). PCA and clustering revealed three phenotypic subgroups, including a high-risk cluster (72% recurrence) characterized by immunosuppression, multiple AMTs, prior surgery, and inflammatory complications. Random forest classification confirmed the predictive role of these variables, achieving an AUC of 0.82 with balanced sensitivity (74%) and specificity (81%).

Systemic immunosuppression, repeated AMTs, and prior ocular surgery are key predictors of AMT failure in NK. Combining regression models, clustering, and machine learning provides a robust framework for risk stratification. These findings support the development of personalized monitoring and treatment strategies to improve surgical outcomes in NK.