In this work, we present a flexible method for explaining, in human readable terms, the predictions made by decision trees used as decision support in liver transplantation. The decision trees have been obtained through machine learning applied on a dataset collected at the liver transplantation unit at the Coru\~na University Hospital Center and are used to predict long term (five years) survival after transplantation. The method we propose is based on the representation of the decision tree as a set of rules in a logic program (LP) that is further annotated with text messages. This logic program is then processed using the tool xclingo (based on Answer Set Programming) that allows building compound explanations depending on the annotation text and the rules effectively fired when a given input is provided. We explore two alternative LP encodings: one in which rules respect the tree structure (more convenient to reflect the learning process) and one where each rule corresponds to a (previously simplified) tree path (more readable for decision making).

Answer Set Programming (ASP) [13, 12, 4] is a successful paradigm for Knowledge Representation and problem solving. Under this paradigm, the programmer represents a problem as a logic program formed by a set of rules and obtains solutions to that problem in terms of models of the program called answer sets. Thanks to the availability of efficient solvers, ASP is nowadays applied in a wide variety of areas including robotics, bioinformatics, music composition [7, 5, 3], and many more. An ASP program does not contain information about the method to obtain the answer sets, something that is completely delegated to the ASP solver. This, of course, has the advantage of making ASP a fully declarative language, where the programmer must concentrate on specification rather than on design of search algorithms.

One of the current problems in decision support from Artifici al Intelligence systems is the lack of explanations. When a system is making decisions in critical co ntexts and those decisions may have an impact on people's life like in the medical or legal domains, then explanations turn to be crucial, especially if we expect that a domain expert relies on the obtaine d answers. One of these situations from the medical domain where explanations have a crucial role is the process of donor-patient matching in an organ transplantation unit. This process starts when a new o rgan is received and consists in selecting a patient among those included in a waiting list for transplan tation. The transplantation unit is expected to follow an objective policy that takes into account medica l parameters and is experimentally supported by the existing records, but more importantly, this decisio n must be easily reproducible and explicable in a comprehensible way for other agents potentially involved, since it may have life-critical consequences at personal, medical and legal levels. Typically, this deci sion is taken in terms of a set of numerical weights (the impact of weights variation is studied in [7]). Although different classification systems based on Artificial Neural Networks (ANNs) are being propose d (see for instance [2] for the case of liver transplantation) their decisions rely on a black box whose b ehaviour is not explicable in human terms. In this paper, we present a rule interpreter, web-liver, designed for assisting the medical experts in the donor-patient matching of a liver transplantation un it, using the case scenario from the Digestive F. Aguado et al.