Statistical Analysis Plan: Predictive Modelling of Stillbirths and Neonatal Deaths in Sub-Saharan Africa Using Classical, Machine Learning, and AI Approaches (Version 1, February 2026)

This component contains the pre-specified Statistical Analysis Plan (SAP) governing the development, internal validation, and external validation of predictive models for stillbirths and neonatal deaths in Sub-Saharan Africa. The SAP covers four prediction scenarios, two primary outcomes, and eight modelling approaches spanning classical statistical methods (logistic regression, GEE), ensemble machine learning (Random Forest, XGBoost, LightGBM, CatBoost), and exploratory deep learning (multilayer perceptrons). This plan was finalised and deposited prior to commencement of model development analyses. Dataset construction and the scoping review are documented separately. Version 1, February 2026. Part of the Wellcome Accelerator Award project at LSHTM.