Today the state-of-the-art performance in classification is achieved by the so-called “black boxesâ€, i.e. decision-making systems whose internal logic is obscure. Such models could revolutionize the health-care system, however their deployment in real-world diagnosis decision support systems is subject to several risks and limitations due to the lack of transparency. The typical classification problem in health-care requires a multi-label approach since the possible labels are not mutually exclusive, e.g. diagnoses. We propose MARLENA, a model-agnostic method which explains multi-label black box decisions. MARLENA explains an individual decision in three steps. First, it generates a synthetic neighborhood around the instance to be explained using a strategy suitable for multi-label decisions. It then learns a decision tree on such neighborhood and finally derives from it a decision rule that explains the black box decision. Our experiments show that MARLENA performs well in terms of mimicking the black box behavior while gaining at the same time a notable amount of interpretability through compact decision rules, i.e. rules with limited length.
CITATION STYLE
Panigutti, C., Guidotti, R., Monreale, A., & Pedreschi, D. (2020). Explaining Multi-label Black-Box Classifiers for Health Applications. In Studies in Computational Intelligence (Vol. 843, pp. 97–110). Springer Verlag. https://doi.org/10.1007/978-3-030-24409-5_9
Mendeley helps you to discover research relevant for your work.