Today the state-of-the-art performance in classification is achieved by the so-called “black boxes†, 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.
Explaining Multi-label Black-Box Classifiers for Health Applications
Panigutti C.;Guidotti R.;Monreale A.;Pedreschi D.
2020-01-01
Abstract
Today the state-of-the-art performance in classification is achieved by the so-called “black boxes†, 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.File | Dimensione | Formato | |
---|---|---|---|
w3phiai2019marlena.pdf
accesso aperto
Tipologia:
Documento in Pre-print
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
400.29 kB
Formato
Adobe PDF
|
400.29 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.