Construction and Validation of a Nomogram for Predicting Intrahepatic Cholestasis of Pregnancy (ICP) Risk: A Prospective Cohort Study

Background Intrahepatic cholestasis of pregnancy (ICP) is a liver disorder unique to pregnancy. Although serum total bile acids (TBA) serve as the primary diagnostic marker for ICP, their metabolism is influenced by environmental, dietary, and genetic factors, leading to significant individual variability and diagnostic limitations. Thus, establishing a novel ICP risk prediction model holds substantial clinical significance. Methods From June 2022 to June 2024, pregnant women attending prenatal care at Shanghai Public Health Clinical Center were enrolled. The study included 391 participants (184 ICP cases and 207 healthy controls). Clinical characteristics and serum biomarker levels were recorded. Univariate analysis, LASSO (Least Absolute Shrinkage and Selection Operator) regression, and multivariate logistic regression identified seven independent predictors for ICP risk, which were incorporated into a nomogram. Internal validation was performed via bootstrap resampling (1,000 replicates). Model performance was assessed using discrimination (AUC), calibration (calibration curve with Hosmer-Lemeshow test), and clinical utility (decision curve analysis and clinical impact curve). Results Multivariate analysis revealed seven independent predictors (all P < 0.05): maternal age ≥ 35 years, alanine aminotransferase (ALT), triglycerides (TG), apolipoprotein A (ApoA), fibrinogen (FIB), phospholipid transfer protein (PLTP), and soluble intercellular adhesion molecule-1 (sICAM-1). The nomogram achieved an AUC of 0.991. Calibration curves showed excellent agreement (*Hosmer-Lemeshow* χ² = 0.991, P = 0.998). Decision curve analysis confirmed clinical utility, supporting robust predictive performance. Conclusion This nomogram enables early ICP risk prediction, facilitating timely interventions to improve maternal and neonatal outcomes.