The influence of maternal agency on severe child undernutrition in conflict-ridden Nigeria: Modeling heterogeneous treatment effects with machine learning.

Nigeria is one of the fastest growing African economies, yet struggles with armed conflict, poverty, and morbidity. An area of high concern is how this situation affects vulnerable families and their children. A key pathway in improving the situation for children in times of conflict is to reinforce maternal agency, for instance, through education. However, the state of the art of research lacks a clear understanding of how many years of education is needed before children benefit. Due to mother's differing social context and ability, the effect of maternal education varies. We study the heterogeneous treatment effects of maternal agency, here operationalized as length of education, on severe child undernutrition in the context of armed conflict. We deploy a repeated cross-sectional study design, using the Nigeria 2008 and 2013 Demographic and Health Survey (DHS). The sample covers 25,917 children and their respective mothers. A key methodological challenge is to estimate this heterogeneity inductively. The causal inference literature proposes a machine learning approach, Bayesian Additive Regression Trees (BART), as a promising avenue to overcome this challenge. Based on BART-estimation of the Conditional Average Treatment Effect (CATE) this study confirms earlier findings in that maternal education decreases severe child undernutrition, but only when mothers acquire an education that lasts more than the country's compulsory 9 years; that is 10 years of education and higher. This protective effect remains even during the exposure of armed conflict.

"I am not telling. The mobile is telling": Factors influencing the outcomes of a community health worker mHealth intervention in India.

INTRODUCTION: Improving maternal health outcomes remains a priority in Low and Middle Income Countries. With the rapid proliferation of mobile health technologies, there is an increased interest in understanding how these technologies can effectively improve maternal health outcomes particularly maternal health seeking knowledge and behaviors. However, few studies present clear explanations of the program developers' rationale (theory of change) and contextual factors that could influence program outcomes. This mixed-methods study assesses Mobile for Mothers, a community health workers (CHW) utilized maternal mHealth intervention. We present the program developers' rationale and utilize it as a framework to guide our study that aimed to identify intervention-related and contextual factors, which influence the observed outcomes of a CHW, utilized mHealth intervention. MATERIALS AND METHODS: Quantitative methods (a questionnaire with 740 women who received the intervention and survey of 57 CHWs who utilized the intervention) and qualitative methods (12 interviews and 4 group discussions with CHWs and 20 interviews and 5 group discussions with pregnant and lactating women and 15 interviews and 2 group discussions with men) were conducted. These were used to understand how the mHealth intervention was implemented and to gain insight into contextual factors that potentially influenced the observed intervention outcomes. RESULTS: Results were grouped following three categories: (1) perceptions and experiences of CHWs utilizing the mHealth technology; (2) CHW-related outcomes; and (3) contextual factors that influence maternal health-seeking behavior. The overall response of CHWs and community members to the intervention was positive. However, contextual factors like the relationship between the CHWs and their respective communities, the pregnant women's decision-making power and lack of access due to financial influenced the observed outcomes. CONCLUSION: Mobile health applications are promising interventions for improving the performance of CHWs and health-seeking behavior of pregnant women. However, the contextual factors play a crucial role in intervention outcomes and need to be explicated by program developers during intervention design and implementation.