A SURVEY ON DIFFERENT MACHINE LEARNING ALGORITHMS IN EMERGENCY DEPARTMENT FOR PATIENT FLOW CONTROL

Computer Science

The efficient management of patient flow control in emergency department (EDs) of a hospital is a critical aspect of delivering quality healthcare services. Overcrowding, long waiting times, and resource allocation challenges are common issues that EDs face on a daily base, leading to compromised patient care and increased healthcare cost. In recent years, machine learning techniques have emerged as a valuable tool for optimizing patient flow control in emergency departments, assessing their effectiveness and potential for addressing the aforementioned challenges. The survey presents a comprehensive analysis of diverse range of machine learning techniques implemented in emergency departments for patient flow management. The algorithm considered include but are not limited to, decision trees, random forest, support vector machines, neural networks, k-mean clustering and reinforcement learning. Both external and internal key factors influencing patient flow control, such as inter arrival time/patterns, triage process, bed allocation and resource optimization are examined in the context of each algorithms contribution and also highlight real–world case scenarios and research efforts that have applied machine learning techniques to address patient flow control challenges in emergency departments. By comparing the outcomes achieved by different techniques, and also providing insight to the strength and weaknesses of each of the approach, enabling healthcare administrators and practitioners to take informed decisions when selecting and implementing machine learning solutions. In conclusion, the study underscores the growing importance of machine learning techniques in revolutionizing patient flow management within the emergency department of the hospital. By shading light on the applicability and performance of various algorithm which will ultimately lead to the improvement of patient care, reduce patient Waiting time, Overcrowding and Resource Allocation.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.