No abstract

This research identifies the factors influencing the reduction of autopsies in a hospital of Veracruz. The study is based on the application of data mining techniques such as association rules and Bayesian networks in data sets obtained from opinions of physicians. We analyzed, for the exploration and extraction of the knowledge, algorithms like Apriori, FPGrowth, PredictiveApriori, Tertius, J48, NaiveBayes, MultilayerPerceptron, and BayesNet, all of them provided by the API of WEKA. To generate mining models and present the new knowledge in natural language, we also developed a web application. The results presented in this study are those obtained from the best-evaluated algorithms, which have been validated by specialists in the field of pathology.

In the last years, a significant reduction in the number of autopsies realized in the hospitals of the world has been observed. Since medics are the closest people to this problematic, they can offer information that helps clarify why the decreasing of this practice has occurred. In this paper, data mining techniques are applied to perform an analysis of medical opinions regarding the realization of autopsies in a hospital of Veracruz, in Mexico. The opinions were collected through surveys applied to 85 medics of the hospital. The result is a model represented by a set of rules that suggests some of the factors that are related to the decrease in the number of autopsies in the hospital, according to the survey respondents.