Interpretable prediction of neonatal mortality and its key predictors using machine learning and SHAP analysis

Kerebih Getinet Bitew, Yaregal Assabie, Tesfa Tegegne · 2026

Read Interpretable prediction of neonatal mortality and its key predictors using machine learning and SHAP analysis by Kerebih Getinet Bitew, Yaregal Assabie, Tesfa Tegegne (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-13371363.txt.

Description

Kerebih Bitew and co-authors build a machine learning model to flag newborns at risk of death in Ethiopia. Survey data from five national rounds fed several algorithms. Deaths are rare next to survivors, so the team weighted and resampled the data to balance the classes. A weighted gradient boosting model caught the most deaths while staying readable.

An explanation method ranked the drivers. Late first breastfeeding, having no living children, and missing prenatal visits topped the list. Twins, small birth size, boy babies, and short gaps between births also raised risk. The authors offer the tool for targeting care where it saves most lives.

Catalog record

CREATORKerebih Getinet Bitew, Yaregal Assabie, Tesfa Tegegne
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE51 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13371363

Browse the full library · About the Tower of Babel