AI-Enabled Decision Support for Sustainable Strategic Leadership in Complex Engineering Systems: A Healthcare Case Study

Abstract

Hospital inpatient departments are complex, uncertain environments where non-technical managers struggle to act on AI-generated forecasts — a gap this thesis calls the "Translation Gap." To bridge it, a five-layer AI-enabled decision support framework is proposed, spanning data capture, predictive modeling, sustainability assessment via the Triple Bottom Line, strategy scoring, and plain-language explainability. The framework was validated through simulation across three scenarios — Normal Operations, Increasing Demand, and a Surge Crisis — successfully distinguishing subtle demand trends, exposing strategic trade-offs, and honestly flagging when no tested solution resolves a crisis. Results demonstrate that the framework supports more informed, transparent, and sustainability-conscious managerial decision-making. While validated on synthetic hospital data, the framework is broadly applicable to other complex systems such as power grids, logistics, and transportation networks.