Artificial Intelligence for Human-Centric Intelligent Decision Support Systems

Abstract

Intelligent Decision Support Systems (IDSS) have emerged as a critical advancement over traditional decision support technologies by integrating artificial intelligence, data analytics, and human-centred design principles. In complex and uncertain environments, decision-makers require systems that not only deliver accurate recommendations but also ensure transparency, interpretability, and ethical accountability. This paper proposes a human-centric IDSS framework that combines machine learning models, explainable artificial intelligence techniques, uncertainty-aware reasoning, and interactive user interfaces to support informed and responsible decision-making. The proposed architecture adopts a modular design that enables seamless integration of predictive models, explanation mechanisms, and human-inthe-loop interaction. Explainability methods are incorporated to enhance user understanding and trust, while uncertainty quantification supports risk-aware decisions in dynamic contexts. The framework emphasises ethical and sustainable AI practices by addressing issues related to fairness, accountability, and transparency. Application scenarios in healthcare and business decision-making are discussed to demonstrate the practical relevance of the proposed system. An evaluation framework is outlined to assess predictive performance, explanation quality, usability, and decision effectiveness. The study highlights how human-centric intelligent decision support systems can augment human judgement, improve decision quality, and promote sustainable and socially responsible outcomes in real-world applications.