Methodological Advances in Expert Systems with Artificial Intelligence

Context: With the advancement of artificial intelligence (AI), expert systems (ESs) continue to evolve and are essential to support decisions in complex domains such as healthcare, industry, and automation. Problem: The growth of AI technologies has expanded the possibilities of Expert Systems. With advances in natural language processing, there is a need for an updated mapping of the applications and methodologies of ESs, highlighting the role of new AI techniques. Solution: Literature review is essential to identify trends, methodologies, challenges, and innovations in ESs, providing a comprehensive overview of the most recent trends and their implications. IS Theory: When examining how ESs can integrate and process complex and constantly evolving data, this study is guided by the complex systems theory, which aims to explore how parts of systems exchange information and adapt to new conditions. Method: The study employs a qualitative and interpretative review to investigate the state of the art in inference methodologies, knowledge acquisition, and performance in ESs. Summary of Results: Expert systems have evolved significantly with the use of AI, including deep learning, hybrid models, and natural language processing, improving accuracy, adaptability, and the ability to process large volumes of data. Contributions and Impact on the IS Field: This study highlights the advances that make expert systems more effective, highlighting how the integration of AI improves the ability to deal with uncertainty and complex decisions. The new methodologies show potential to optimize reliability and decision making in critical environments.