In models, the algorithms are proposed and processed locally without dependence on the cloud, internet, etc. They use the data that they have generated themselves for training purposes, storing it locally and taking quick decisions when needed. Such techniques are model trains on various client devices. The model updates and the curated data are then sent to the remote server periodically. The implementation of such models saves backhauling costs and bandwidth requirements. In a field such as healthcare where even a second's delay can result in death, reduced latency is a major point to be considered. The analytics methods utilised by the edge-AI (edge-artificial intelligence) techniques to locally curate, analyse, and produce results, include advanced analytics methods like artificial intelligence and machine learning, edge computing techniques like machine vision, video analytics, and sensor fusion, and methods incorporating location intelligence. The hardware support consists of electronics and devices that enable edge computing. The power efficiency and scalability reduce costs, increase real-time performance, and achieve accurate analytics which, along with the greater reach, make this technique more lucrative. Such techniques can enable medical workers to obtain information about critical patients even in regions where the connectivity is inadequate. Detection, identification, and diagnosis of musculoskeletal injuries, fractures, cardiovascular abnormalities, and even some neurological diseases will be possible, even in remote locations, with the help of edge-AI. The impact of AI and its applications in various industries all over the world has significantly improved. Nowadays, cloud computing is being used in almost every field in the face of the growing data needs of the corporate world, thereby becoming an integral part of AI. Edge-AI, regarded as the future of AI, is a combination of AI and edge computing that uses machine learning to deploy intelligent solutions on hardware devices. These hardware devices are known as edge devices and use machine-learning algorithms to sort, filter, and analyse data which are generated by this device, and make decisions in real time. Edge AI processes data locally, directly on a server or device, which reduces time latency as the data doesn’t have to be transferred to the cloud. This shift from the cloud to the edge is quite beneficial. Another advantage of edge AI is that it doesn’t need internet connectivity to analyse data in real time. The role of AI in improving the systems and enhancing technology in different industrial sectors in recent years is commendable. Healthcare is one of the leading industries driven by AI technology and edge computing (Fasciano & Vitulano 2020). AI has the potential to automate processes and has become extremely useful in enabling autonomous monitoring of hospital rooms and patients, enhanced by edge-AI. This is achieved by various AI algorithms which use a host of sensors to gather and process data in order to respond appropriately. There have been a lot of different innovations and developments in transforming the present-day healthcare landscape by automation of cardiovascular tests like X-rays, and much more. The increasing global population brings many problems and challenges surrounding the quality of life for people of all ages. This is mainly affecting the healthcare sector. With the help of AI-based techniques directly on the edge, a faster, more private, and more precise result is enabled which directly works on edge computing.