@inbook{31835,
  keywords = {clustering, Data mining, Epidemiology, Kohonen networks, leprosy},
  author = {Tan Y and Shi Y and Tang Q and Dutra da Silva YE and Salgado CG and Gomes Conde VM and Conde G},
  title = {Data mining using clustering techniques as leprosy epidemiology analyzing model.},
  abstract = {<p>Leprosy remains a public health problem in the world and also in Brazil. The people’s living conditions, especially of the most socially vulnerable, dramatically influence the risk of contagion of the disease. In this context, this study aimed to analyze the epidemiology of leprosy through the list of patients and the environment of these using data mining techniques with clustering methods. In the process of creating of clusters, best results were obtained with Self-Organizing Maps of Kohonen with information organized into 6 clusters. A set of data with SINAN patients and new cases of leprosy found in an active search carried out in the municipality of Santarém in the year 2014. The results were analyzed, draws attention the values found for the Anti PGL-1 in cluster 4 first set of data analysis which indicates very high values of positive, indicating a high load of the leprosy bacillus, and therefore a high risk for communicating. The study demonstrated that the identification of leprosy patient’s relationship profile with your family and your household appear as promising tools like leprosy control strategy.</p>
},
  year = {2018},
  journal = {Data Mining and Big Data},
  pages = {284-293},
  publisher = {Springer International Publishing},
  address = {Cham},
  issn = {0302-9743},
  isbn = {978-3-319-93802-8},
  doi = {10.1007/978-3-319-93803-5_27},
  language = {eng},
}