Open AccessClassification of Newborns with Congenital Syndrome Associated with Zika Virus Infection Using Machine Learning
Author(s) -
Érika G. de Assis,
Luis Enrique Zárate,
Cristiane Neri Nobre
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/kdmile.2021.17461
Subject(s) - microcephaly , zika virus , christian ministry , head circumference , pediatrics , pregnancy , medicine , disease , medical record , virus , virology , birth weight , biology , philosophy , theology , genetics
Due to evidence that Zika virus (ZIKV) infection during pregnancy caused congenital brain anomalies, including microcephaly, in 2016 the WHO declared this disease a worldwide public health problem. The objective of this work is to identify the most important characteristics for the diagnosis of children with congenital syndrome due to ZIKV virus infection. We applied machine learning algorithms to RESP-Microcephaly, a database from the Brazilian Ministry of Health that records suspected cases of congenital abnormalities. At the end of the process, the most relevant characteristics were: weight, age of the pregnant woman, length, head circumference and region where the mother lives. This information is very significant as it is in agreement with the literature that associates these attributes with critical factors for the occurrence of congenital infection.