Urine output is closely associated with renal function and has been used as a diagnostic criterion for acute kidney injury (AKI). However, urine output during cardiopulmonary bypass (CPB) has never been identified as a predictor of postoperative AKI. Considering altered renal homeostasis during CPB, we made a comprehensible approach to CPB urine output and evaluated its predictability for AKI.P...

Ensemble methods improve accuracy by combining the predictions of a set of different hypotheses. However, there are two important shortcomings associated with ensemble methods. Huge amounts of memory are required to store a set of multiple hypotheses and, more importantly, comprehensibility of a single hypothesis is lost. In this work, we devise a new method to extract one single solution from ...

Clustering is an important data mining task which helps in nding useful patterns to summarize the data. In the KDD context, data mining is often used for description purposes rather than for prediction. However, it turns out diicult to nd clustering systems that help to ease the interpretation task to the user in both, statistics and Machine Learning elds. In this paper we present Isaac, a hier...