TY - JOUR
T1 - Extracción de conocimiento a partir del análisis de los datos en el período 2013-2017 del ministerio de salud pública en Ecuador
AU - Alejo Machado, Oscar J.
AU - Bastidas, Tatiana Tapia
AU - Vázquez, Maikel Yelandi Leyva
N1 - Publisher Copyright:
© 2020 Universidad de La Habana. All rights reserved.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020
Y1 - 2020
N2 - The databases of the Ministry of Public Health of Ecuador in the 2013-2017 period contain valuable information that can be used to determine the strengths, weaknesses, potential problems, among others, that affect the public health of the country. This knowledge can serve to draw better public health policies. This paper aims to propose a methodology that allows us to extract knowledge from these databases and at the same time to obtain association rules based on the combination of algorithms such as FP-growth and k-means. In summary, the methodology consists of the following steps: first, the dataset is stored in 5 files in the SPSS (Statistical Package for the Social Sciences) format, and then the disease-related attributes are grouped and encoded, according to the code ICD-10, for this purpose it is proposed to apply the WEKA software. Finally, the FP-Growth algorithm is used to extract association rules from frequent items with the support of RAPIDMINER, which has the advantage of allowing us the use of WEKA algorithms. The methodology is illustrated with an example that shows how to use it and its usefulness to extract association rules in real-life situations from medical databases. With these representations of the information, morbidity and incidence behavior analysis of the registered groups and diseases can be made.
AB - The databases of the Ministry of Public Health of Ecuador in the 2013-2017 period contain valuable information that can be used to determine the strengths, weaknesses, potential problems, among others, that affect the public health of the country. This knowledge can serve to draw better public health policies. This paper aims to propose a methodology that allows us to extract knowledge from these databases and at the same time to obtain association rules based on the combination of algorithms such as FP-growth and k-means. In summary, the methodology consists of the following steps: first, the dataset is stored in 5 files in the SPSS (Statistical Package for the Social Sciences) format, and then the disease-related attributes are grouped and encoded, according to the code ICD-10, for this purpose it is proposed to apply the WEKA software. Finally, the FP-Growth algorithm is used to extract association rules from frequent items with the support of RAPIDMINER, which has the advantage of allowing us the use of WEKA algorithms. The methodology is illustrated with an example that shows how to use it and its usefulness to extract association rules in real-life situations from medical databases. With these representations of the information, morbidity and incidence behavior analysis of the registered groups and diseases can be made.
KW - Artificial Intelligence in medicine
KW - Associating rule
KW - Clustering
KW - Data mining
KW - Unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85089004729&partnerID=8YFLogxK
M3 - Artículo
AN - SCOPUS:85089004729
SN - 0257-4306
VL - 41
SP - 629
EP - 636
JO - Investigacion Operacional
JF - Investigacion Operacional
IS - 5
ER -