Novel Approach for Phenotyping Based on Diverse Top-K Subgroup Lists

Antonio Lopez-Martinez-Carrasco, Hugo Manuel Proença, Jose M. Juarez, Matthijs van Leeuwen, Manuel Campos

Abstract: The discovery of phenotypes is useful to describe a population. Providing a set of diverse patient phenotypes with the same medical condition may help clinicians to understand it. In this paper, we approach this problem by defining the technical task of mining diverse top-k phenotypes and proposing an algorithm called DSLM to solve it. The phenotypes obtained are evaluated according to their quality and predictive capacity in a bacterial infection problem.