Enhancing Hospital Efficiency Through Web-Deployed Object Detection: A YOLOv8-Based Approach for Automating Healthcare Operations

Hospital operation efficiency plays a crucial role in health- care delivery and patient outcomes. Traditional hospital sys- tems, often managed manually, are subject to human error and inefficiencies. There is a pressing need to automate certain tasks to improve speed, accuracy, and resource utilization. This research paper presents an innovative approach towards hospital automation using a You Only Look Once version 8 (YOLOv8) deep learning model. We propose training the YOLOv8 model to detect and recognize several classes per- tinent to hospital operations including Ambulances, Beds, Wheelchairs, Stetho-scopes, Medical equipment, Stretchers, Band-aids, and Towels. This model is planned to be deployed in web applications using React.js and TensorFlow.js, enabling its use on various platforms including computers, smartphones, and tablets. By integrating this technology with hospital management systems, we aim to assist hospital personnel in their tasks and improve operational efficiency. This could potentially increase the precision and speed of routine tasks, improve resource tracking, and enable healthcare workers to concentrate more on patient care