The Fusion of Internet of Things, Artificial Intelligence, and Cloud Computing in Health Care

In the health context, when it relates to medical devices, IoT consists of the evolution of IoMT, having its applications evaluating the central objective in offering customized treatment. IoMT uses either through mobile devices with smart applications, guided by data generated through connected devices, service applications, emergency care kits, medical equipment for home use, among many varied forms of performance of this technology applied to health areas. Through IoMT, medicine has properties seeing can be employed through electronic medical records, sensors, wearable devices, smart apps, collecting data during daily activities of patients, related to symptoms, and conditions. From this information, greater agility can be achieved through AI algorithms through machine learning capable of guiding diagnostics and therapies at a distance and also can monitor the evolution of the disease, reducing the requirement for a complete specialist medical team in loco. Thus, IoMT has been revolutionizing employing disruptive technologies, through the revolutionary aspect of diagnoses in real time and efficient treatment health, generated a great differentiator for communities to approach an overburdened health system that will only be under more stress as the population continues to act. Therefore, this chapter has the mission and objective of providing an updated overview of IoT and IoMT and their ramifications across the field of health, addressing its branch of application concerning modern medicine and in conjunction with other disruptive technologies. Also, it is worth mentioning that the novelty of this manuscript is in dealing with the approach to the theme focusing on the role of this technology in modern perspectives, categorizing, and synthesizing the potential of technologies.

Modern healthcare systems are more and more complex today as they involve EHR applications, mobile applications, and IoT system integration. They typically generate a large volume of data on a daily basis, whereby the storage of the healthcare big data becomes challenging especially data from IoT connected devices. Traditional on-premise storage is not scalable enough. Cloud computing is a good option for storing healthcare big data as it is scalable, secure, reliable, provides ubiquitous access, and is highly available. In this chapter, the different storage media used to store data are described and the different storage mechanisms such as file storage, block storage, and object storage are discussed. Object storage is being increasingly adopted for storing healthcare Big data as it is more scalable, cost-effective, secure and reliable, and more suitable for data analytics. Blockchain technology is also being investigated for the healthcare industry. The use of blockchain for storing data on the cloud is also discussed, and the security of the data stored on cloud storage is described.

Image retrieval and classification are the most prominent area of research in computer vision. Nowadays, bounteous medical images are generated through different types of medical imaging modalities in healthcare systems. It is often very difficult for researchers and doctors to access manage and retrieve images easily. The efficient and effective analysis and usage of heterogeneous biomedical images growing rapidly are a tedious task. Content-based image retrieval (CBIR) is one of the most widely used methods for automatic retrieval of images and widely used in medical images. Abundant research articles are published in different domain of applications related to CBIR and classification. The aim of this study is to provide a road map for researchers by exploring the various approaches, techniques, and algorithms used for medical image retrieval and classification. Feature extraction is the main subject for improving the performance of image classification and retrieval. Bag of visual words techniques and deep convolutional neural networks are widely used in content-based medical image retrieval (CBMIR). The state-of-the-art methods presented in this review are well suited to classify and retrieve multimodal medical images for different body organs. The methods include preprocessing of images, feature extraction, classification, and retrieval steps to develop an efficient biomedical image retrieval system. This chapter briefly reviews the various techniques used for biomedical images, and different methods adopted in classification and retrieval are focused.

The aim of the paper is to describe a project of novel highly accurate AI system for screening of breast cancer based on investigation of fractal properties of chromatin in Feulgen-stained nuclei of buccal epithelium. The work of the system consists in data collection in cloud storage, morphological pre-processing and classification on the cloud platform and traditional computers, and communication with patients using IoT technology. We studied data on 130 patients: 68 patients with breast cancer, 33 patients with fibroadenomatosis, and 29 healthy individuals containing in average data on 52 nuclei of buccal epithelium. The data set consists of 20,256 images of interphase nuclei of buccal epithelium (6752 nuclei scanned without filter, through a yellow filter, and through a violet filter). Each image consists of three channels: red, green, blue, as well as gray halftones. The combination of cloud storage of data, classification on cloud platform and using the IoT technologies for communication with patients provides high accuracy of diagnosis and comfort for patients.

The use of AI in healthcare sector is a huge transformation from traditional technologies to new AI technology with the use of complicated programming and software. It replaces human doctors in analyzing, interpreting complicated medical data. Different research works of recent past reveal that patient satisfaction is an important issue for any hospitals or clinic, particularly in healthcare sector where new technology like AI is also needed. This study aims at understanding patients’ satisfaction with the use of AI technology in hospitals in different parts of the world. From literature review, 28 components related to the use of AI in healthcare service have been determined. Data collection was done with the help of structured questionnaire across USA, Canada, Australia, UAE, and China. There were 249 respondents for this survey. Exploratory Factor Analysis (EFA) was initially performed to understand which factors contributed to patient satisfaction. This study found that patient satisfaction mainly depends on six broad dimensions, first factor is “Personal Touch,” second factor is “Comprehensive Gap,” third factor is “Answerability,” fourth factor is “Nerve Racking,” fifth factor is “Wrong Reporting,” and sixth factor is “Enlightened.” This study further helps in understanding patient’s satisfaction of using AI for medical purpose and treatment with the above-mentioned factors. It has emerged that the factors “Personal Touch” and “Enlightened” play a significant impact in determining patient satisfaction.

The Internet of Things (IoT) Healthcare system has become one of the most indispensable parts of human lives, and this has dramatically increased the medical information system that brings about big data. Healthcare practitioners are already adopting wearable devices based on the IoT to streamline the diagnosis, monitoring, prediction, and treatment process. The affordability and user-friendliness of the usage of IoT start revolutionizing healthcare services. Billions of sensors, devices, and vehicles in recent times have been connected through the Internet using IoT technologies. For continuous health tracking, wireless sensor networks can be implemented to enhance the well-being of patients, make the healthcare system more effective, and help respond quickly to emergencies. The IoT-based healthcare can be employed to enhance the well-being of patients, make the healthcare system more effective, and help respond quickly to emergencies. However, these systems also pose significant risks in terms of privacy and security issues surrounding data transfer, processing, monitoring, and documentation. Such healthcare data protection, security, and privacy concerns may result from a delay in the progress of treatment, diagnosis, and even endangering the life of the patient. Therefore, this chapter presents a summary of the IoT, comprising its architecture, and reveals the IoT-based healthcare application privacy and security concerns. The chapter also proposed a framework to secure healthcare information in the IoT environment. This will help to protect healthcare data on the IoT platform and meet the strict security and privacy needs of ubiquitous medical requests.

The Internet of Things is computation where devices are equipped with sensors, transmitters, receivers and microcontrollers. This chapter discusses the utilization of IoT in the healthcare system eliminating the risk for healthcare professionals. IoT provides ubiquitous monitoring systems that can be used for disease management. Many devices are connected and communicate with each other following the protocol designed. The medical information is collected, transmitted to be stored and retrieved to be analysed. Tools empowered with IoT can help medical staff to monitor patients regularly remotely and treat them. The interaction cost is reduced, and the data collected are analysed and used for future research studies. Medical emergencies can be predicted, and alert message notifications can be sent to corresponding people or authorities. Doctors and patients can check drug doses. Patients can receive reminder alerts at the time of medication or treatment. Furthermore, this chapter highlights IoT opportunities in the healthcare field and research challenges in current and near future.

Given the limited access to the healthcare services in India and the vulnerabilities therein, the physical well-being of the people in India is a matter of grave concern as is in other developing economies in the world. Though there has been advent of improvements in medical sciences and novel technological innovations therein, yet the reach of the same to the masses is questionable. Statistics indicate that there has been an increase in the people falling at a higher age bracket, all throughout the world. In India, the rural population embracing almost 6,40,000 villages have an unfortunate tale to narrate with more than 11% having no admittance to any sort of healthcare facilities. With the outbreak of Covid-19 and the subsequent need for far reaching screening to contain the same, there are new challenges of outreach constraints in densely populated countries like India. What further poses grave concern is the rural urban divide in the availability of healthcare amenities. All this calls for a progressive transformation and integration of medical sciences with information technology. The divide can be lessened with the aid of telehealth monitoring systems using IOT. In countries like India, where there is little access to doctors and medical infrastructure, such system would be an apt solution for interaction between the patients and the medical practitioners. Most of the villages in India are deprived of even rudimentary Public Health Centers, thus making it difficult for the resident villagers to receive even preliminary treatment. The telehealth monitoring system comes to rescue in such apathetic situations where it facilitates monitoring and measuring the physical vitals like pulse, levels of oxygen in the blood, rate of breath, glucose levels, temperature, lung capacity, ECG, and so on. The information so collected is stored in the cloud database which is then evaluated by the doctors and would eventually lead to generating prescriptions for the same and any other intervention as may be needed including emergency and EMRI services. The said project has created a website www.​sfpieee.​in which would help in dissemination of the information to be used by the physician. Under the call for proposals for combating Covid-19, with the support received from IEEE SIGHT/HAC and the Unnat Bharath Abhiyaan (UBA), this project has been conceptualized, designed, and implemented in Taramatipet Village of Telangana State.

Application of Artificial Intelligence (AI) has revolutionized many sectors like healthcare, agriculture, finance, computer vision, ecommerce, social media, data security, and education. AI plays a vital role in the health sector, like detecting, diagnosing, predicting diseases in advance to reduce the suffering and mortality rate. Besides, application of AI techniques improves hospital management and detection of health insurance fraud. With increased automation in the medical sector, advancements in image acquisition devices and availability of personal wearable devices at affordable cost, voluminous data are being generated. Deep learning techniques can leverage this big data with powerful Graphical Processing Unit (GPU) based systems to analyze and detect hidden patterns in the data and gain insights. Deep learning techniques can learn features from big data sets to get insights that will assist doctors in early diagnosis and treatment. Medical data analysis faces many challenges like limited data availability due to privacy issues, unbalanced data sets for diseases like cancer and rare disease, unavailability of specialists for labeling the data, variation in the experts’ opinion in decision making, variability in genes, environment, and lifestyle of individuals. This chapter discusses the techniques for dealing with the challenges of medical data processing. It also presents the AI techniques for identifying and predicting different types of cancer, diabetes, cardiac, and rare diseases at an early stage using data sets of different formats like clinical data, gene expression data, and medical images. The chapter includes the sections that discuss the methods to deal with unbalanced, small, and high-dimensional data sets, data and label denoising methods, and feature representation learning using neural networks.

All COVID-19 affected countries putting their efforts to deal with the outspread of this death-dealing disease in terms of infrastructure, economics, medical treatments and many other resources. Nowadays, there are number of coronavirus analysis and prediction models are available to make decisions and to informed, aware people. But, absence of necessary data, these models are not able to show precise values. Based on the datasets, reports and on account of the uniform nature of the coronavirus and variations in its behaviour from place-to-place, this study recommend ML as well as deep learning as worthwhile tool to model the outbreak. To come up with for the well-being of living society, we prefer to utilize the ML and deep learning models with the focus for understanding its everyday exponential behaviour in addition to the prediction graphs of further growth of the COVID-2019 over the world by utilizing the available facts and dataset.

In March 2020, the World Health Organization (WHO) declared COVID-19 as a pandemic that covers around 185 countries and territories in the world where the coronavirus infirmity is present. The COVID-19 epidemic is dispersing all over the world in a few months. The traditional health care systems face new challenges associated with the constant increase of patients with this disease. This epidemic has caused a mess worldwide. In India, cases are increased day by day. Due to COVID-19, countries have a huge loss which cannot be estimated both in the economy and life of citizens. To recover this economic loss and save the life, deployment of emerging technologies is used to battle this invisible enemy. During this period, several researchers have written lots of research papers in various fields. The main aim of this chapter is to summarize the existing literature addressing the use of computational intelligence (CI) technologies to battle COVID-19 infection. Nowadays researchers have been analyzed the data related to COVID-19 and draw some conclusions by applying emerging technologies like AI, IoT, deep learning, Blockchain, Neural Network, Fuzzy, and machine learning algorithms. These strategies help policymakers and frontline people to take additional steps by avoiding the unfold of the virus and manage the disease. Researchers also suggest the use of Artificial Intelligence (AI) and the Internet of Things (IoT) to fight this pandemic and do all necessary work by following the guidelines given by the government.

This article focuses on the role of artificial intelligence in healthcare management and in particular, the support it can provide to efficiently improve medical imaging and radiology procedures. This highlights the utilization of artificial intelligence in healthcare to help solving problems and making best decisions for private and public health by reducing human errors and discovering diseases in early stages. Furthermore, this study uses artificial intelligence in the radiology department to help radiologists better diagnose diseases and increase efficiency using reliable database generated by such technology. This advanced technology is undoubtedly playing a role in dealing with Coronavirus pandemic, a technology that can contribute in many health facilities including medical imaging. A survey was used to reach to findings targeting a sample of medical students and staff with medical backgrounds. Three main factors that were found important in the study that need to be addressed are awareness, technology, and prediction of future crisis.