Factors associated with coverage of praziquantel for schistosomiasis control in the community-direct intervention (CDI) approach in Mali (West Africa)

Background: Despite the progress made in the control of Neglected Tropical Diseases (NTD), schistosome and soil-transmitted helminth infections are far from being effectively managed in many parts of the world. Chemotherapy, the key element of all control strategies, is faced with some difficulties in terms of access to treatment. Our study aims to describe the factors involved in the success or failure of the community-directed intervention (CDI) approach through control programmes, which aims to achieve consistent high coverage at affordable and sustainable costs in endemic areas. Methods: The CDI approach was carried out from December 2007 to October 2008 in ten villages of the district of Diema, Mali. At inclusion, each child part of the study's sample was interviewed and submitted for a physical examination. The study focused on: data collection, treatment of the eligible population, evaluation of the treatment coverage, performance of community drug distributors (CDDs), and the involvement and perception of populations. Results: A total of 8,022 eligible people were studied with a mean coverage rate of 76.7%. Using multiple regression, it was determined that receiving praziquantel as treatment was associated with five factors: belonging to the Fulani or Moorish ethnic minority versus the Bambara/Soninke, use of the central versus the house-to-house drug distribution mode, the ratio of the population to the number of CDDs, the lack of supervision and belonging to the age group of 15 years or above (p<0.05). As well as that, it was found that the presence of parallel community-based programmes (HIV, tuberculosis) that provide financial incentives for community members discouraged many CDDs (who in most cases are volunteers) to participate in the CDI approach due to a lack of incentives. Conclusions: The findings indicate that the success of the CDI approach depends on, amongst other things, the personal characteristics of the respondents, as well as on community factors.