Development and validation of a lasso-logistic regression-based risk prediction model for retinopathy in patients with hypertensive disorders of pregnancy

Objective: To identify risk factors for retinopathy in patients with hypertensive disorders of pregnancy (HDP) and develop a predictive nomogram model. Methods: = 288). Additionally, 200 PIH patients from Xunwu County People's Hospital (January 2021 to December 2024) were included as an external validation cohort. LASSO regression was used to screen potential predictors, followed by multivariate logistic regression to identify independent risk factors. A nomogram prediction model was constructed. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis (DCA). Results: < 0.05). The nomogram demonstrated good calibration in the training, internal validation, and external validation cohorts. The AUC values were 0.948 (95% CI: 0.925-0.970), 0.921 (95% CI: 0.881-0.962), and 0.907 (95% CI: 0.842-0.972), respectively. DCA showed favorable net clinical benefit across a wide range of threshold probabilities. Conclusion: The nomogram based on clinical and laboratory indicators demonstrated good discrimination and calibration in internal and external validation of retinopathy risk in PIH patients, with good clinical applicability.