Paediatric malaria case-management with artemether-lumefantrine in Zambia: a repeat cross-sectional study

BACKGROUND:Zambia was the first African country to change national antimalarial treatment policy to artemisinin-based combination therapy - artemether-lumefantrine. An evaluation during the early implementation phase revealed low readiness of health facilities and health workers to deliver artemether-lumefantrine, and worryingly suboptimal treatment practices. Improvements in the case-management of uncomplicated malaria two years after the initial evaluation and three years after the change of policy in Zambia are reported.METHODS:Data collected during the health facility surveys undertaken in 2004 and 2006 at all outpatient departments of government and mission facilities in four Zambian districts were analysed. The surveys were cross-sectional, using a range of quality of care assessment methods. The main outcome measures were changes in health facility and health worker readiness to deliver artemether-lumefantrine, and changes in case-management practices for children below five years of age presenting with uncomplicated malaria as defined by national guidelines.RESULTS:In 2004, 94 health facilities, 103 health workers and 944 consultations for children with uncomplicated malaria were evaluated. In 2006, 104 facilities, 135 health workers and 1125 consultations were evaluated using the same criteria of selection. Health facility and health worker readiness improved from 2004 to 2006: availability of artemether-lumefantrine from 51% (48/94) to 60% (62/104), presence of artemether-lumefantrine dosage wall charts from 20% (19/94) to 75% (78/104), possession of guidelines from 58% (60/103) to 92% (124/135), and provision of in-service training from 25% (26/103) to 41% (55/135). The proportions of children with uncomplicated malaria treated with artemether-lumefantrine also increased from 2004 to 2006: from 1% (6/527) to 27% (149/552) in children weighing 5 to 9 kg, and from 11% (42/394) to 42% (231/547) in children weighing 10 kg or more. In both weight groups and both years, 22% (441/2020) of children with uncomplicated malaria were not prescribed any antimalarial drug.CONCLUSION:Although significant improvements in malaria case-management have occurred over two years in Zambia, the quality of treatment provided at the point of care is not yet optimal. Strengthening weak health systems and improving the delivery of effective interventions should remain high priority in all countries implementing new treatment policies for malaria.

ARTMAP: Supervised Real-Time Learning and Classification of Nonstationary Data by a Self-Organizing Neural Network

This article introduces a new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. This supervised learning system is built up from a pair of Adaptive Resonance Theory modules (ARTa and ARTb) that are capable of self-organizing stable recognition categories in response to arbitrary sequences of input patterns. During training trials, the ARTa module receives a stream {a^(p)} of input patterns, and ARTb receives a stream {b^(p)} of input patterns, where b^(p) is the correct prediction given a^(p). These ART modules are linked by an associative learning network and an internal controller that ensures autonomous system operation in real time. During test trials, the remaining patterns a^(p) are presented without b^(p), and their predictions at ARTb are compared with b^(p). Tested on a benchmark machine learning database in both on-line and off-line simulations, the ARTMAP system learns orders of magnitude more quickly, efficiently, and accurately than alternative algorithms, and achieves 100% accuracy after training on less than half the input patterns in the database. It achieves these properties by using an internal controller that conjointly maximizes predictive generalization and minimizes predictive error by linking predictive success to category size on a trial-by-trial basis, using only local operations. This computation increases the vigilance parameter ρa of ARTa by the minimal amount needed to correct a predictive error at ARTb· Parameter ρa calibrates the minimum confidence that ARTa must have in a category, or hypothesis, activated by an input a^(p) in order for ARTa to accept that category, rather than search for a better one through an automatically controlled process of hypothesis testing. Parameter ρa is compared with the degree of match between a^(p) and the top-down learned expectation, or prototype, that is read-out subsequent to activation of an ARTa category. Search occurs if the degree of match is less than ρa. ARTMAP is hereby a type of self-organizing expert system that calibrates the selectivity of its hypotheses based upon predictive success. As a result, rare but important events can be quickly and sharply distinguished even if they are similar to frequent events with different consequences. Between input trials ρa relaxes to a baseline vigilance pa When ρa is large, the system runs in a conservative mode, wherein predictions are made only if the system is confident of the outcome. Very few false-alarm errors then occur at any stage of learning, yet the system reaches asymptote with no loss of speed. Because ARTMAP learning is self stabilizing, it can continue learning one or more databases, without degrading its corpus of memories, until its full memory capacity is utilized.