Artificial intelligence (AI) is the imitation of human cognitive abilities. It's changing the way people think about medical services, thanks to increased access to medical information and rapid advancements in examination techniques. The authors look at the current state of AI in medical services and speculate on its future. Artificial intelligence can be used to analyse various types of medical data (structured and unstructured). AI approaches for structured data machine learning methods, such as the old-style support vector machine and neural network, as well as modern deep learning, and regular language processing for unstructured data are among the most well-known AI tactics. Finding and treatment suggestions, patient commitment and adherence, and managerial exercises are all important classifications of utilizations. Malignant growth, nervous system science, and cardiology, for example, are some of the major disease areas that use AI devices.
TopIntroduction
The purpose of this chapter is to debate current state-of-the-art intelligent healthcare systems, with a focus on major areas such as portable and smart phone gadgets for patient monitoring, machine learning for diagnosis of diseases, and assistive structures, such as social robots established for the adaptable living situation. Remote surveillance systems can provide individual and worldwide sensing on a variety of scales. Sensing is divided into three categories: personal, group, and social sensing. Real time tracking systems are built for a single personal and are generally concentrated on gathering and examining personal information. Monitoring users' exercise habits, assessing activity levels, and identifying symptoms associated with psychiatric problems are all common instances. Although the data generated is intended solely for the user's use, it is normal to share it with medical professionals. FitBit, Google Glass and the Nike+ FuelBand are all intelligent personal monitoring devices. Individuals who participate in health monitoring and share a similar hobby, problem, or aim create a group. In social networks or related groups, where information can be openly distributed or else with information secrecy, collective monitoring systems might be popular.
Patient monitoring applications, such as contests based on specific goals such as running distance, weight loss, calorie consumption, and so on, are common examples. Community or population monitoring refers to when a lot of people participate in health and activity monitoring. Crowd modelling and monitoring entails community-wide data analytics for the greater good. However, it entails collaboration between people who do not trust one another, emphasising the necessity for confidentiality protection and possibly minimal user engagement. Measuring the transmission of diseases over an area, looking for certain medical disorders, and so on are examples of population monitoring. Although the influence of scale on monitoring applications is being investigated, numerous research questions including intelligence sharing, data rights, data synthesis, protection and confidentiality, methods of data mining, delivering valuable opinion, and so on stay unanswered. This chapter discusses the major constraints and opportunities in the gathering, modelling, and processing of medical data in the framework of mortal health and behaviour monitoring. Section I contains an introduction to AI, Section II contains a review of medical information modelling using AI, Section III contains information on the impact of AI medical models on society, and Section IV contains information on the benefits and applications of AI in healthcare systems. Conclusion and references were the subject of Sections V and VI.
Figure 1. Architecture of smart health care monitoring system
Figure 1. depicts the different stages of the overall architecture of the health care monitoring system. Four different stages are there in this monitoring system, which includes 1. sensor data collection and feature extraction. 2. Remote Health server 3. Remote Health Gateway 4. Remote Health Analysis and Visualization. In the first phase, data collection can be done by using various resources like physical, virtual, and social sensors, smart phones, smart watches, and bracelets, etc, and user generated content on social media. Once the data collection process is done, then local processing and analytics must happen. This phase ends with some health mobile applications. The same sensed or collected data, events, and data from IoT sensors and devices are to be loaded into the server for further discovery. Personal request and response information can be shared between mobile applications and health servers via remote health gateway. In the second phase of this monitoring system, processing, analysis, and mining of streaming or stored sensing data takes place on a remote health server that is associated with the cloud environment. Storing, filtering, and aggregation operations can be done in a cluster or cloud. The third stage of this system is remote health analytics and visualization. Personal health services and notifications can be shared at this stage on the mobile applications. The Health Analytics or Visualization phase can send a query to a remote server, and the server can respond with analytics knowledge.