Development and external validation of an explainable XGBoost model with a web-based calculator for risk prediction of postpartum depressive symptoms
Qian Zhang, Fang Wu, Mei Zhu, Liwei Sun · 2026
Read Development and external validation of an explainable XGBoost model with a web-based calculator for risk prediction of postpartum depressive symptoms by Qian Zhang, Fang Wu, Mei Zhu, Liwei Sun (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13619944.txt.
Description
Qian Zhang and three colleagues build a web tool that flags new mothers at risk of low mood after birth. Postpartum depression is common and often missed. Older risk scores are weak, and many smart models are hard to read or fail when moved to a new hospital.
The team trained five models on 403 women from one hospital and tested the best one on 150 women from a second. A gradient-boosted tree model sorted high-risk from low-risk women well in both places. It leaned most on age, how good the marriage felt, low mood before birth, income, and poor sleep. The tool tends to overstate risk in the new setting, so the authors urge more checks before wide use.
Catalog record
| CREATOR | Qian Zhang, Fang Wu, Mei Zhu, Liwei Sun |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |