Document - Explaining multi-label black-box classifiers for health applications

2020

Contribution to book Open Access

Explaining multi-label black-box classifiers for health applications

Panigutti C, Guidotti R, Monreale A, Pedreschi D

Multilabel Classification Explainable AI Mult Health

Today the state-of-the-art performance in classification is achieved by the so-called âEURoeblack boxesâEUR, 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.

Source: STUDIES IN COMPUTATIONAL INTELLIGENCE (PRINT), pp. 97-110

Metrics

Back to previous page

Cite as

BibTeX entry

@inbook{oai:it.cnr:prodotti:417419,
	title = {Explaining multi-label black-box classifiers for health applications},
	author = {Panigutti C and Guidotti R and Monreale A and Pedreschi D},
	doi = {10.1007/978-3-030-24409-5_9},
	booktitle = {STUDIES IN COMPUTATIONAL INTELLIGENCE (PRINT), pp. 97-110},
	year = {2020}
}