Smart Systems for Industrial Applications

This system involves the diagnosis of the patient from the point of the service area to initialize the method; the required devices are included into the eHealthcare system that will provide the service that has the real-time conferencing with the data between a doctor and a patient; it consists of the session that enables the prototype to client service media application. The data generated through the conferencing are recorded and sent through the service layer to attain a level of security and authenticity of the service and then to store the data in the data warehouse; it contains a collection of data that are used by the medical professionals [3]; the storing data vary for the same user for different readings; for those purposes, the structured query language is used because of the complexity of data in database relational database is more sophisticated. However, it might have an issue of managing larger database complexity. It has more advanced security features of data handling before inserting the data into the data server; it cleans the data, loads it and analyzes it for any vulnerabilities. Finally, it visualizes the loaded data for the analytical purpose [1–3]; the SQL structure handles data handling works.

The acquired data sources are accessed by the authorized healthcare member where the entire medical healthcare statistics of the patient are all displayed to the specialized person. It has also maintained a healthcare decision system that is more emerging features that will provide the solutions for the already existing diagnosis. This eliminates the repetitive task of producing the same results. It is also connected with the health records system and the research centers, so the data will serve as a tool for the modern medical development process. The regular steps carried in the day-to-day medical procedures are all automated in the eHealthcare system and the accuracy is one of the prominent features in this method. The laboratory information system provides the ease of access to the records and manages and stores the data for clinical laboratories [4], tracking of the test orders and sending those data in the digitalized form through a searchable database.

Mobile health is another critical paradigm, which overcomes the geographical, organizational, and temporal barriers in healthcare services. The idea has evolved in accordance with the technological changes in communication protocols that have changed from GSM, GPRS, wireless LAN to 4G and, more recently, 5G communication technologies [5]. The wireless ECG transmissions, wireless ambulance services, video images and teleradiology, and other integrated mobile telemedical monitoring systems are some examples of applications of 2G and 3G technologies. The evolution of mHealth for personalized medical systems with flexible functionalities is possible because of the development of 4G networks. Moreover, the reduced latency and good media services in healthcare are achieved with the advent of 5G communication technologies in mobile healthcare.

Personalized health is user-specific, and it is targeted toward taking patient-specific decisions. It is also called otherwise as adaptive health. In personalized health, the sources of data include wearable devices and sensors with implementable micro- or nanotechnologies. The data collected from these devices are combined at the decision center for making up any decision [6]. The idea can be enhanced to P4 medicine, in which the data sources could be the genetic information from each individual.

Table 1.1 Role of communication technologies in healthcare.

The collective insight on one’s biology can address the source of disease and the condition of health, which can impact screening and diagnosis. Smart health is supported by smart devices like mobile phones and likely devices for the practicing of public and individual healthcare. Other than mobile phones, the devices used for smart health include sensors, robots, smart cards, and the internet with a pay-according to user basis [7].

Mobile broadband connectivity alleviates the issues caused by limited coverage of healthcare services in remote areas. Along with the existing 4G, the advent of 5G networks revolutionized healthcare communication technologies in terms of increased data rate, reduced latency, and improved capacity to support many challenging applications [8]. Machine-tomachine communication in the current era enables day-to-day objects and the surrounding atmosphere managed and connected through extensive devices, communication protocols, and clouds or servers. IEEE standards, namely, IEEE 802.15, the wireless personal area network, and wireless body area network (WBAN), are adopted in many healthcare systems. The summary on applications of communication technologies in healthcare is given in Table 1.1.

The development of communication technologies plays a significant role in the growth of healthcare as an industry. To quote a few advancements in healthcare are rapid growth in the number of patient records that are converted into electronic health record. The health record is a document that covers historical information about the patients. Technology in healthcare is not only introducing digital transformation; it becomes a trend in controlling in every aspect of healthcare. In recent trends, Artificial Intelligence (AI) also gains attention in the enhancement of various system modeling, processes, and ease of prediction [9]. Most of the human illness are identified and diagnosed through image processing and pattern recognition algorithms. In recent times, AI is used to enhance the accuracy of imaging tools. In this chapter, we provide a detailed discussion of the impact of AI and various communication technologies in healthcare.

In this section, we provide an overview of recent AI technologies that are responsible for recent shifts in healthcare, as shown in Figure 1.2.

Figure 1.2 Impact of AI in different domains of healthcare.

In this section, we present the effect of AI in healthcare for diagnosis application with examples. A simple process of AI transformation is shown in Figure 1.3. Online-based application has been developed to ease the process and increases real-time availability and accessibility of health-related information. Online healthcare has set a new channel for data transfer between the patient and the health unit. Extracting and analyzing the health record is a challenging task, which is achieved by reliable AI algorithms. These algorithms can predict the disease by understanding the nature of the patient’s record. Deep learning–based risk scoring and stratification tools are successfully developed to identify probable correlation from an unknown dataset within the patient’s record.