Nomogram for predicting cognitive impairment in postpartum depression patients after pharmacotherapy: Development and validation

Objective: To develop and validate a clinical feature-based nomogram for predicting the risk of significant cognitive impairment in postpartum depression (PPD) patients treated with selective serotonin reuptake inhibitors (SSRIs). Methods: A retrospective study was conducted on 350 PPD patients treated with SSRI monotherapy at our institution between January 2020 and December 2024. Cognitive function was assessed at week 8 using the Montreal Cognitive Assessment (MoCA), with MoCA < 26 defined as significant cognitive impairment. Predictors were screened using LASSO regression, and a multivariate logistic regression model was built to construct the nomogram. Internal validation was performed via bootstrapping (1000 repetitions). Model discrimination, calibration, and clinical utility were evaluated using the C-statistic, calibration curve, and decision curve analysis (DCA). Results: Six predictors were identified: age, baseline depression severity (HAMD-17 score), years of education, SSRI type (paroxetine vs. others), baseline sleep quality (PSQI score), and postpartum duration. The model exhibited a C-statistic of 0.82 (95% CI: 0.78–0.86). The calibration curve demonstrated good agreement between predicted and actual risks. DCA indicated significant clinical net benefit across a wide threshold probability range (0.1–0.6). Conclusion: This nomogram effectively predicts individualized risk of significant cognitive impairment in SSRI-treated PPD patients, demonstrating good discrimination, calibration, and clinical utility. It serves as a valuable tool to aid clinical decision-making.