Extracción de conocimiento a partir del análisis de los datos en el período 2013-2017 del ministerio de salud pública en Ecuador

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.