Digital Twins
Using machine learning and simulation modeling to to create digital twins of hospitals
My research focuses on combining machine learning and simulation modeling to improve patient flow in large hospital systems by creating digital twins—virtual models that mirror real-time hospital operations. By integrating machine learning with simulation modeling, these digital twins can forecast patient admissions, track bed utilization, and anticipate bottlenecks in care pathways (Ahmad et al., 2023). This approach allows hospital administrators to make data-driven decisions on resource allocation, staffing, and patient scheduling, optimizing operational efficiency while enhancing patient care. Through these simulations, healthcare systems can test various scenarios, such as surge capacity or changes in care protocols, allowing for proactive adjustments that mitigate delays and improve overall patient flow. The integration of machine learning and digital twins promises continuous enhancements in hospital management, more efficient and resilient healthcare systems.
