Título: SOM Neural Networks as a Tool in Pleural Tuberculosis Diagnostic
Autores: Orjuela-Cañón, Alvaro D.; Seixas, José Manoel de; Trajman, Anete
Resumo: Diagnostic tasks in a contagious disease as pleural tuberculosis is essential to send the patients to a correct treatment to cure the ailment. Tools for supporting this task are still a challenge because different variables are necessary, including invasive standard tests. In the present work Self Organizing Maps were used for clustering of patients of pleural tuberculosis in three risk groups. The first approach employs just anamnesis variables and a second methodology uses additional information about some classical result tests. The last approach exhibits best results compared to the approach using anamneses variables.
Palavras-chave: Neural Networks; Diagnosis; Pleural Tuberculosis; Clustering
Código DOI: 10.21528/CBIC2013-288
Artigo em pdf: bricsccicbic2013_submission_288.pdf
Arquivo BibTex: bricsccicbic2013_submission_288.bib