Finding hidden patterns of hospital infections on newborn: A data mining approach
The increasing number of hospital infections with considerable morbidity, mortality and economic burden attracts the attention of not only the health-care environment, but also the whole society. This study presents an application of data mining methods for hospital infection detection in a newborn intensive care unit. The data set is provided by Department of Clinical Microbiology and Infectious Diseases, Eskişehir Osmangazi University, Faculty of Medicine. Decision tree and neural network classification models are built using accuracy estimation methods; holdout sampling and cross validation. In model comparison, accuracy and sensitivity measures are taken into consideration primarily. The study highlights that antibiotics and urinary catheter usage, peripheral catheter duration, enteral and total parenteral nutrition durations, and birth weight for gestational age are considerable risk factors. Among the models, neural network and CHAID decision tree perform better on hospital infections detection.
Data mining, hospital infections, decision trees, neural networks