Postpartum Depression Risk Factors from a Chinese Hospital Survey, 2023-2025

Six early risk factors for postpartum depression were identified from a survey of pregnant women in Shandong Province, China, using interpretable machine learning. The dataset likely contains survey responses from participants hospitalized between July 2023 and January 2025, collected by Shusen Lin. The final LightGBM model was validated internally and externally and analyzed using SHAP for global interpretability.

Use Cases

• Building predictive models for postpartum depression screening based on identified risk factors like work pressure and social support.
• Analyzing feature importance and interaction patterns for clinical risk factors using SHAP analysis.
• Comparing the performance of nine different machine learning algorithms on a clinical psychology dataset.
• Studying the application of social ecosystem theory in machine learning for mental health.

Strengths

• The study design includes internal and external validation of machine learning models.
• Feature selection was performed using recursive feature elimination with 10-fold cross-validation.
• The research is based on a specific, defined population from two tertiary grade-A hospitals.

Limitations

• The dataset description lacks column-level documentation, making field semantics unclear.
• Row count is unknown, which may limit suitability assessment for large-scale modeling.
• Data may reflect geographic bias inherent to the convenience sampling method in Shandong Province, China.

Provenance

Source

Shusen Lin via figshare

Collection Method

Convenience sampling survey of pregnant women hospitalized in two hospitals.

Time Range

July 2023 to January 2025

Freshness

Last updated 2026-05-15 04:21:45; freshness should be verified.

Geography

Shandong Province, China