A Survey of Explainable Artificial Intelligence in Bio-signals Analysis

Abstract

Background: In contrast to the high rate of interest in artificial intelligence (AI) for business, the rate of AI adoption is much lower. It has been found that lack of consumer trust would adversely influence consumer’s evaluations of information given by AI. Hence the need for explanations in model results. MethodS: This is especially the case in clinical practice and juridical enforcement where improvements in prediction and interpretation are crucial. Bio-signals analysis such as EEG diagnosis usually involves complex learning models, which are difficult to explain. Therefore, the explanatory module is imperative if results is to be released to the general public. This research shows a systematic review of explainable artificial intelligence (XAI) advancement in the research community. Recent XAI efforts on bio-signals analysis were reviewed. The explanatory models are found to be in favor compared to the interpretable model approach due to the popularity of deep learning models in many use cases. Result: The verification and validation of explanatory models appear to be one of the crucial gaps in XAI bio-signals research. Currently, human expert evaluation is the easiest validation approach. Although the human directed approach is highly trusted by the bio-signals community, but it suffers from persona and social bias issues. Conclusion: Hence, future research should investigate on more objective evaluation measurements towards achieving the characteristics of inclusiveness, reliability, transparency, and consistency in XAI framework.