Patients readmissions to Intensive Care Unit (ICU) are introduced as a problem associated with increased mortality, morbidity and costs, which complicates the performance of a good clinical management and medical diagnosis. The aim of this work is to use the fuzzy decision tree using the axiomatic fuzzy set (AFS) theory in a type of coherence membership function to apply in the risk of readmission. Three fitness functions are used to obtain the threshold using different assessment measures: accuracy; area under the curve ROC (AUC); and Cohen's kappa coefficient. The results for this problem data demonstrated that the model using fitness function with Cohen's kappa coefficient obtains better performance than the others fitness functions. © 2015 Springer International Publishing.
CITATION STYLE
Silva, C., Vieira, S. M., & Sousa, J. M. C. (2015). Fuzzy decision tree to predict readmissions in intensive care unit. In Lecture Notes in Electrical Engineering (Vol. 321 LNEE, pp. 365–373). Springer Verlag. https://doi.org/10.1007/978-3-319-10380-8_35
Mendeley helps you to discover research relevant for your work.