Key points are not available for this paper at this time.
This work employs a multidisciplinary approach to identify research gaps in the existing literature by presenting a systematic review of systematic reviews on Explainable Artificial Intelligence (XAI). To the best of our knowledge, this is the first thorough meta-review that combines the findings of several excellent reviews to offer a more elevated viewpoint on the goals and difficulties facing the area. The review covers empirical studies published between 2021 and 2023, focusing on high-quality sources. An initial pool of 997 entries was screened across multiple databases, yielding 928 unique articles after duplicate removal. Ultimately, 14 studies met the inclusion criteria and were analyzed in depth. The quality assessment confirmed that all selected reviews adhered to established methodological standards. The key findings show XAI's broad uses, which range from increasing trust and transparency to assisting with financial and management decision-making. The prevalence of healthcare-focused studies emphasizes XAI's importance in enhancing interpretability, fairness, regulatory compliance, and personalized treatment options. Commonly used techniques include visual explanation tools, interpretable machine learning models, and model-agnostic approaches. While the review offers valuable insights, it acknowledges limitations such as its reliance on Q1 journals and the exclusion of broader sources, which may affect comprehensiveness. To advance the field, the study recommends expanding future research to underrepresented domains like autonomous vehicles, defense, and smart cities. It also calls for methodological innovation to enhance accessibility, fairness, privacy, and the development of intuitive explanation strategies. Addressing these gaps can significantly improve the trustworthiness and effectiveness of AI systems across sectors.
Monem et al. (Tue,) studied this question.