Prediction of neonatal mortality in Sub-Saharan African countries using data-level linkage of multiple surveys
This work is significant for public health researchers and policymakers in Sub-Saharan Africa, as it aims to improve the prediction of neonatal mortality despite limited data.
This paper addresses the scarcity of data for predicting crucial problems like child mortality in developing countries by linking disjoint surveys across Sub-Saharan African countries. This data-level linkage improved the prediction performance of neonatal death and offered cross-domain explainability.
Existing datasets available to address crucial problems, such as child mortality and family planning discontinuation in developing countries, are not ample for data-driven approaches. This is partly due to disjoint data collection efforts employed across locations, times, and variations of modalities. On the other hand, state-of-the-art methods for small data problem are confined to image modalities. In this work, we proposed a data-level linkage of disjoint surveys across Sub-Saharan African countries to improve prediction performance of neonatal death and provide cross-domain explainability.