Global crises, such as pandemics and climate-related disasters, place unprecedented strain on healthcare Systems, exposing weaknesses in resource management and patient care. This study aims to address these challenges by developing an integrated computational framework for crisis-resilient healthcare robotics. We propose a unified approach that combines Multiple Linear Regression (MLR), Markov Decision Processes (MDPs), and Petri Nets. MLR is applied to predict the Average Length of Stay (ALOS) using patient and hospital data. These forecasts inform MDPs, which guide admission and triage decisions under uncertainty. Petri Nets are employed to model and validate patient flow and hospital workflows, ensuring feasibility and efficiency. Case studies, including ICU bed prioritization and disaster logistics, demonstrate that the proposed framework improves adaptability and resource utilization while supporting structured decision guidance. Simulation results highlight enhanced system efficiency, better patient prioritization, and reduced congestion during surge conditions. The integration of predictive analytics, probabilistic optimization, and workflow modeling provides a robust decision-support system for health-care robotics in crisis scenarios. This interdisciplinary framework offers practical solutions for improving resilience, scalability, and patient outcomes, providing a structured foundation for enhancing resilience and coordination in healthcare systems facing future emergencies.
Dahamou et al. (Thu,) studied this question.