National and sub-national variation in patterns of febrile case management in sub-Saharan Africa

Abstract

Given national healthcare coverage gaps, understanding treatment-seeking behaviour for fever is crucial for the management of childhood illness and to reduce deaths. Here, we conduct a modelling study triangulating household survey data for fever in children under the age of five years with georeferenced public health facility databases (n = 86,442 facilities) in 29 countries across sub-Saharan Africa, to estimate the probability of seeking treatment for fever at public facilities. A Bayesian item response theory framework is used to estimate this probability based on reported fever episodes, treatment choice, residence, and estimated travel-time to the nearest public-sector health facility. Findings show inter- and intra-country variation, with the likelihood of seeking treatment for fever less than 50% in 16 countries. Results highlight the need to invest in public healthcare and related databases. The variation in public sector use illustrates the need to include such modelling in future infectious disease burden estimation.

Fig. 1

Health facilities and cases of fever. a The distribution of public health facilities in sub-Saharan Africa by type. b Aggregate estimates of cases of fever treated at Administrative level 1 per 1000 children under five (weighted by the population at risk). Overall, 56,719 out of 99,631 sampled children sought fever treatment in the public sector. Data assemblies were between 2010–2016, except for South Sudan and Djibouti. Northern Africa countries and South Africa were not included in the analysis. Data were obtained from national reports in countries where georeferenced data were not available, for example, Somalia

Fig. 2

Travel time maps. Travel time to the nearest health facilities at 1 km spatial resolution in sub-Saharan Africa based on combined motorised transport and walking, adjusting for topography for a major general hospitals, b health centres and c dispensaries, clinics and health posts (lower-tier health facilities). The white patches are regions where health centre or dispensary maps were unavailable (the Congo, Equatorial Guinea, Guinea Bissau and two regions in the Democratic Republic of Congo (DRC))

Fig. 3

Probability of seeking fever treatment. a National variation in the probability of seeking fever treatment (posterior median) for any type of public health facility. The red shaded region and vertical lines represent the probability of seeking treatment for fever in the public sector by travel time at 10 min, 30 min, 1 h and 2 h. b Funnel plot representing national posterior median probability of seeking fever treatment in the public sector (length of bar indicates the probability) at 2 h’ travel time to the nearest primary healthcare facility (dispensary, clinic or health post). The probability of treatment was modelled based on the item response theory (IRT) model