Viewpoint: evaluating the impact of malaria control efforts on mortality in sub-Saharan Africa

Abstract

Objective: To describe an approach for evaluating the impact of malaria control efforts on malaria-associated mortality in sub-Saharan Africa, where disease-specific mortality trends usually cannot be measured directly and most malaria deaths occur among young children.

Methods: Methods for evaluating changes in malaria-associated mortality are examined; advantages and disadvantages are presented.

Results: All methods require a plausibility argument-i.e., an assumption that mortality reductions can be attributed to programmatic efforts if improvements are found in steps of the causal pathway between intervention scale-up and mortality trends. As different methods provide complementary information, they can be used together. We recommend following trends in the coverage of malaria control interventions, other factors influencing childhood mortality, malaria-associated morbidity (especially anaemia), and all-cause childhood mortality. This approach reflects decreases in malaria's direct and indirect mortality burden and can be examined in nearly all countries. Adding other information can strengthen the plausibility argument: trends in indicators of malaria transmission, information from demographic surveillance systems and sentinel sites where malaria diagnostics are systematically used, and verbal autopsies linked to representative household surveys. Health facility data on malaria deaths have well-recognized limitations; however, in specific circumstances, they could produce reliable trends. Model-based predictions can help describe changes in malaria-specific burden and assist with program management and advocacy.

Conclusions: Despite challenges, efforts to reduce malaria-associated mortality in Africa can be evaluated with trends in malaria intervention coverage and all-cause childhood mortality. Where there are resources and interest, complementary data on malaria morbidity and malaria-specific mortality could be added.