Schistosomiasis risk mapping in the state of Minas Gerais, Brazil, using a decision tree approach, remote sensing data and sociological indicators

• Published in: Memórias do Instituto Oswaldo Cruz Vol. 105; no. 4; pp. 541 - 548
• Main Authors: Martins-Bedê, Flávia T, Dutra, Luciano V, Freitas, Corina C, Guimarães, Ricardo J.P.S, Amaral, Ronaldo S, Drummond, Sandra C, Carvalho, Omar S
• Format: Journal Article
• Language: English
• Published: Brazil Fundação Oswaldo Cruz, Fiocruz 01-07-2010; Instituto Oswaldo Cruz, Ministério da Saúde; Fundação Oswaldo Cruz (FIOCRUZ)
• Subjects: Animals; Biomphalaria; Brazil - epidemiology; decision tree; Decision Trees; Disease Vectors; Geographic Information Systems; Humans; PARASITOLOGY; Prevalence; public health; Risk; risk mapping; Sanitation - statistics & numerical data; schistosomiasis; schistosomiasis - risk mapping - public health - decision tree; Schistosomiasis mansoni - epidemiology; Schistosomiasis mansoni - transmission; Seasons; Socioeconomic Factors; Topography, Medical; TROPICAL MEDICINE; Water - parasitology; Brazil; decision tree; schistosomiasis; public health; risk mapping
• ISSN: 1678-8060; 0074-0276; 1678-8060; 0074-0276
• DOI: 10.1590/S0074-02762010000400033

Schistosoma mansoni is not just a physical disease, but is related to
social and behavioural factors as well. Snails of the Biomphalaria
genus are an intermediate host for Schistosoma mansoni and infect
humans through water. The objective of this study is to classify the
risk of schistosomiasis in the state of Minas Gerais (MG). We focus on
socioeconomic and demographic features, basic sanitation features, the
presence of accumulated water bodies, dense vegetation in the summer
and winter seasons and related terrain characteristics. We draw on the
decision tree approach to infection risk modelling and mapping. The
model robustness was properly verified. The main variables that were
selected by the procedure included the terrain's water
accumulation capacity, temperature extremes and the Human Development
Index. In addition, the model was used to generate two maps, one that
included risk classification for the entire of MG and another that
included classification errors. The resulting map was 62.9% accurate.