A Novel Analysis of Intelligent Systems for Dynamic Bed Allocation using ML Algorithms

The project presents an innovative hybrid framework for effective management of patient influx in the Outpatient Department (OPD) by integrating queuing models with dynamic bed allocation strategies to optimize healthcare resources during high-demand periods. It addresses the unpredictability of patient arrivals and limited hospital capacity by combining Reinforcement Learning (RL), Genetic Algorithms (GAs), and real-time data processing to analyze and predict complex patient flow patterns. The model incorporates an attention mechanism to merge patient information with real-time hospital capacity data, enabling accurate and timely bed allocation decisions. By optimizing resource distribution, reducing waiting times, and ensuring fair utilization of available facilities, the system enhances overall patient flow and adapts dynamically to fluctuating demand. This integrated approach demonstrates how combining RL, machine learning, queuing theory, and predictive analytics can significantly improve hospital efficiency, resource utilization, patient experience, and healthcare outcomes.