Michael Green, Lars Edenbrandt, Ulf Ekelund, Jonas Björk, Jakob L. Forberg and Mattias Ohlsson
Exploring new possibilities for case-based explanation of artificial neural network ensembles
Neural Networks 22, 75-81 (2009)
Abstract:
Artificial neural network (ANN) ensembles has long
suffered from lack of interpretability. This has
severely limited the practical usability of ANNs in
settings where an erroneous decision can be
disastrous. Several attempts have been made to
alleviate this problem. Many of them are based on
decomposing the decision boundary of the ANN into a
set of rules.
We explore and compare a set of new methods for this explanation process on two artificial data sets (Monks 1 and 3), and one acute coronary syndrome data set consisting of 861 electrocardiograms (ECG) collected retrospectively at the emergency department at Lund University Hospital.
The algorithms managed to extract good explanations in more than 84% of the cases. More to the point, the best method provided 99 and 91% good explanations in Monks data 1 and 3 respectively. Also there was a significant overlap between the algorithms. Furthermore, when explaining a given ECG, the overlap between this method and one of the physicians was the same as the one between the two physicians in this study. Still the physicians were significantly, p-value < 0.001, more similar to each other than to any of the methods.
The algorithms has the potential to be used as an explanatory aid when using ANN ensembles in clinical decision support systems.
We explore and compare a set of new methods for this explanation process on two artificial data sets (Monks 1 and 3), and one acute coronary syndrome data set consisting of 861 electrocardiograms (ECG) collected retrospectively at the emergency department at Lund University Hospital.
The algorithms managed to extract good explanations in more than 84% of the cases. More to the point, the best method provided 99 and 91% good explanations in Monks data 1 and 3 respectively. Also there was a significant overlap between the algorithms. Furthermore, when explaining a given ECG, the overlap between this method and one of the physicians was the same as the one between the two physicians in this study. Still the physicians were significantly, p-value < 0.001, more similar to each other than to any of the methods.
The algorithms has the potential to be used as an explanatory aid when using ANN ensembles in clinical decision support systems.
LU TP 07-43