Analysis of Influencing Factors and Development of a Clinical Prediction Model for Postoperative Visual Improvement Prognosis in Patients with Age-Related Cataract

Purpose: To identify independent factors associated with postoperative visual improvement after phacoemulsification combined with intraocular lens (IOL) implantation in patients with age-related cataract (ARC) and to develop an interpretable individualized clinical prediction nomogram for preoperative risk stratification. Methods: This single-center retrospective study included 1,847 eyes with ARC who underwent phacoemulsification combined with IOL implantation. Univariate and multivariate logistic regression analyses were performed to identify independent predictors associated with postoperative visual improvement. Internal validation was conducted using bootstrap resampling with 1,000 iterations. Model performance was evaluated using the receiver operating characteristic (ROC) curve, calibration curve, decision curve analysis (DCA), and Shapley Additive Explanations (SHAP) value analysis. Results: Age, severity of preoperative visual impairment, fundus lesions, axial length, and keratometric value (K-value) were identified as independent predictors of postoperative visual improvement. The prediction model demonstrated good discriminative ability, with an area under the curve (AUC) of 0.83 (95% confidence interval [CI], 0.78–0.89) in the training cohort and 0.78 (95% CI, 0.70–0.86) in the validation cohort. Calibration analysis showed good agreement between predicted and observed outcomes, and decision curve analysis indicated favorable clinical utility. SHAP analysis revealed that age contributed most significantly to the model prediction. A visual nomogram was subsequently developed to provide individualized risk estimation. Conclusion: The nomogram incorporating five independent predictors demonstrated good discrimination, calibration, and clinical applicability for predicting postoperative visual improvement in patients with ARC. This model may serve as a practical tool for preoperative risk assessment, individualized patient counseling, and doctor–patient communication.