IROF: a low resource evaluation metric for explanation methods
This addresses the need for accessible and unbiased evaluation in healthcare AI, though it is incremental as it builds on existing work in explanation methods.
The paper tackles the problem of evaluating explanation methods for neural networks in healthcare by proposing IROF, a low-resource metric that eliminates manual evaluation, requiring orders of magnitude less computational resources and no human input.
The adoption of machine learning in health care hinges on the transparency of the used algorithms, necessitating the need for explanation methods. However, despite a growing literature on explaining neural networks, no consensus has been reached on how to evaluate those explanation methods. We propose IROF, a new approach to evaluating explanation methods that circumvents the need for manual evaluation. Compared to other recent work, our approach requires several orders of magnitude less computational resources and no human input, making it accessible to lower resource groups and robust to human bias.