Analysis of Influencing Factors of Fundus Functional Lesions in Patients with Pregnancy-Induced Hypertension and Construction of Prediction Model

Objective: Fundus functional lesions are an important complication of pregnancy-induced hypertension (PIH) that may threaten visual function. This study aimed to identify factors associated with retinal functional lesions in PIH patients and to develop a nomogram model for individualized risk prediction. Methods: A retrospective analysis was conducted on 307 PIH patients admitted to our hospital between May 2020 and July 2024. Patients were randomly divided into a training set (n=215) and a validation set (n=92). According to the presence of fundus functional lesions, patients in the training set were classified into lesion and non-lesion groups. Multivariate logistic regression analysis was used to identify independent influencing factors. A nomogram model was constructed using R software and evaluated through internal validation and split-sample validation. Model performance was assessed using the receiver operating characteristic (ROC) curve, calibration curve, Hosmer-Lemeshow test, and decision curve analysis (DCA). Results: No significant differences in baseline clinical characteristics were observed between the training and validation sets. Patients with fundus functional lesions showed lower pre-pregnancy body mass index (BMI) and platelet count (PLT), while higher systolic blood pressure (SBP), higher hematocrit, and a greater prevalence of obstructive sleep apnea (OSA) were observed. Multivariate analysis identified pre-pregnancy BMI, highest SBP, presence of OSA, hematocrit ≥35%, and PLT as independent influencing factors for fundus functional lesions. The nomogram model demonstrated good discrimination and calibration in both training and validation sets. Decision curve analysis indicated favorable clinical utility across a wide range of threshold probabilities. Conclusion: Pre-pregnancy BMI, maximum systolic blood pressure, OSA, hematocrit, and platelet count were independent predictors of retinal functional lesions in PIH patients. The developed nomogram model demonstrated good predictive performance and may serve as a helpful clinical tool, pending further external validation.