A historical perspective of biomedical explainable AI research.

The black-box nature of most artificial intelligence (AI) models encourages the development of explainability methods to engender trust into the AI decision-making process. Such methods can be broadly categorized into two main types: post hoc explanations and inherently interpretable algorithms. We aimed at analyzing the possible associations between COVID-19 and the push of explainable AI (XAI) to the forefront of biomedical research. We automatically extracted from the PubMed database biomedical XAI studies related to concepts of causality or explainability and manually labeled 1,603 papers with respect to XAI categories. To compare the trends pre- and post-COVID-19, we fit a change point detection model and evaluated significant changes in publication rates. We show that the advent of COVID-19 in the beginning of 2020 could be the driving factor behind an increased focus concerning XAI, playing a crucial role in accelerating an already evolving trend. Finally, we present a discussion with future societal use and impact of XAI technologies and potential future directions for those who pursue fostering clinical trust with interpretable machine learning models.
Competing Interests: M.R.-Z. and V.B. are employees of IBM Research, Haifa, Israel. F.M. is an employee of Philips Research, Eindhoven, the Netherlands. I.S. has received funding from multiple funding agencies through a collaborative funding program and declares no support from any organization for the submitted work. P.J.N. receives funding from the Dutch Research Council (DWO) for the grant “Mobile Support Systems for Behavior Change,” of which he is the principal investigator (P.I.). M.L. is funded by the EU-Commission grant no. 101057497-EDIAQI.
(© 2023 The Authors.)