Hybrid Algorithm Applied to the Identification of Risk Factors on the Health of Newly Born in Mexico

Hybrid Algorithm Applied to the Identification of Risk Factors on the Health of Newly Born in Mexico

María Dolores Torres (Autonomous University of Aguascalientes, Mexico), Aurora Torres Soto (Autonomous University of Aguascalientes, Mexico), Carlos Alberto Ochoa Ortiz Zezzatti (Juarez City University, México), Eunice E. Ponce de León Sentí (Autonomous University of Aguascalientes, Mexico), Elva Díaz Díaz (Autonomous University of Aguascalientes, Mexico), Cristina Juárez Landín (Autonomous University of Mexico’s State, Mexico) and César Eduardo Velázquez Amador (Autonomous University of Aguascalientes, Mexico)
DOI: 10.4018/978-1-4666-0297-7.ch004


This chapter presents the implementation of a Genetic Algorithm into a framework for machine learning that deals with the problem of identifying the factors that impact the health state of newborns in Mexico. Experimental results show a percentage of correct clustering for unsupervised learning of 89%, a real life training matrix of 46 variables, was reduced to only 25 that represent 54% of its original size. Moreover execution time is about one and a half minutes. Each risk factor (of neonatal health) found by the algorithm was validated by medical experts. The contribution to the medical field is invaluable, since the cost of monitoring these features is minimal and it can reduce neonatal mortality in our country.
Chapter Preview

Identification Of Risk Factors During Pregnancy

Nowadays in medicine like in any other science, the use of computational tools to make a better use of data gathered about a specific phenomenon results essential. Pediatrician from all over the world have always had the need to be well informed about maternal antecedents and previous and actual obstetric record, when acquire the responsibility of a new patient (Hobel, Hyvarinen, Okada, & Oh, 1973); therefore, many researchers have focused on the identification of risk factors of neonatal mortality, stillbirth and morbidity, in order to improve prognosis and to prevent complications.

This work has the goal of identify the features that impact the most on the health state of the newly born, identify the features that are less important and the ones that can be ignore; giving to medical staff a decision support tool to intervene opportunely during pregnancy.

Manipulated data is the result of a transverse study with a sample of 701 pregnancy cases assisted on the zone no.1 with familiar medicine of the Mexican Institute of Social Security and hospitals 1, 2, 5, 7, 45 and 49 in the city of San Luis Potosí, México on 1999 (Torres, 1999).

Initially data base was discretized according to medical literature. Table 1 shows the general conditions of the sample mentioned before.

Complete Chapter List

Search this Book: