Evaluation of an accelerometer-based monitor for detecting bed net use and human entry/exit using a machine learning algorithm.

BACKGROUND: Distribution of long-lasting insecticidal bed nets (LLINs) is one of the main control strategies for malaria. Improving malaria prevention programmes requires understanding usage patterns in households receiving LLINs, but there are limits to what standard cross-sectional surveys of self-reported LLIN use can provide. This study was designed to assess the performance of an accelerometer-based approach for measuring a range of LLIN use behaviours as a proof of concept for more granular LLIN-use monitoring over longer time periods. METHODS: This study was carried out under controlled conditions from May to July 2018 in Liverpool, UK. A single accelerometer was affixed to the side panel of an LLIN and participants carried out five LLIN use behaviours: (1) unfurling a net; (2) entering an unfurled net; (3) lying still as if sleeping; (4) exiting from under a net; and, (5) folding up a net. The randomForest package in R, a supervised non-linear classification algorithm, was used to train models on 20-s epochs of tagged accelerometer data. Models were compared in a validation dataset using overall accuracy, sensitivity and specificity, receiver operating curves and the area under the curve (AUC). RESULTS: The five-category model had overall accuracy of 82.9% in the validation dataset, a sensitivity of 0.681 for entering a net, 0.632 for exiting, 0.733 for net down, and 0.800 for net up. A simplified four-category model, combining entering/exiting a net into one category had accuracy of 94.8%, and increased sensitivity for net down (0.756) and net up (0.829). A further simplified three-category model, identifying sleeping, net up, and a combined net down/enter/exit category had accuracy of 96.2% (483/502), with an AUC of 0.997 for net down and 0.987 for net up. Models for detecting entering/exiting by adults were significantly more accurate than for children (87.8% vs 70.0%; p < 0.001) and had a higher AUC (p = 0.03). CONCLUSIONS: Understanding how LLINs are used is crucial for planning malaria prevention programmes. Accelerometer-based systems provide a promising new methodology for studying LLIN use. Further work exploring accelerometer placement, frequency of measurements and other machine learning approaches could make these methods even more accurate in the future.

Health and economic burden estimates of snakebite management upon health facilities in three regions of southern Burkina Faso.

BACKGROUND: Snakebite has become better recognized as a significant cause of death and disability in Sub-Saharan Africa, but the health economic consequences to victims and health infrastructures serving them remain poorly understood. This information gap is important as it provides an evidence-base guiding national and international health policy decision making on the most cost-effective interventions to better manage snakebite. Here, we assessed hospital-based data to estimate the health economic burden of snakebite in three regions of Burkina Faso (Centre-Ouest, Hauts Bassins and Sud-Ouest). METHODOLOGY: Primary data of snakebite victims admitted to regional and district health facilities (eg, number of admissions, mortality, hospital bed days occupied) was collected in three regions over 17 months in 2013/14. The health burden of snakebite was assessed using Disability-Adjusted Life Years (DALYs) calculations based upon hospitalisation, mortality and disability data from admitted patients amongst other inputs from secondary sources (eg, populations, life-expectancy and age-weighting constants). An activity-based costing approach to determine the direct cost of snake envenoming included unit costs of clinical staff wages, antivenom, supportive care and equipment extracted from context-relevant literature. FINDINGS: The 10,165 snakebite victims admitted to hospital occupied 28,164 hospital bed days over 17 months. The annual rate of hospitalisation and mortality of admitted snakebite victims was 173 and 1.39/100,000 population, respectively. The estimated annual (i) DALYs lost was 2,153 (0.52/1,000) and (ii) cost to hospitals was USD 506,413 (USD 49/hospitalisation) in these three regions of Burkina Faso. These costs appeared to be influenced by the number of patients receiving antivenom (10.90% in total) in each area (highest in Sud-Ouest) and the type of health facility. CONCLUSION: The economic burden of snake envenoming is primarily shouldered by the rural health centres closest to snakebite victims-facilities that are typically least well equipped or resourced to manage this burden. Our study highlights the need for more research in other regions/countries to demonstrate the burden of snakebite and the socioeconomic benefits of its management. This evidence can guide the most cost-effective intervention from government and development partners to meet the snakebite-management needs of rural communities and their health centres.