Machine Intelligence for Internet of Medical Things: Applications and Future Trends

Recently, the internet of medical things has been the widely utilized approach to interconnect various machines. While, IoT in combination with machine intelligence, has given new directions to the healthcare industry. Machine intelligence techniques can be used to promote healthcare solutions. The merger of IoT in medical things is a completely advanced approach. The intelligent behavior of machines provides accurate decisions, which greatly helps medical practitioners. For real-time analysis, artificial intelligence improves accuracy in different medicinal techniques. The use of telemedicine has increased so much due to COVID-19. Gathering unstructured data where the concept of electronic databases should be used in the health care industry for advancement. Big data and cyber security play an important role in IoMT. An intrusion detection system is used to identify cyber-attacks which helps to safeguard the entire network. This article provides a detailed overview of the internet of medical things using machine intelligence applications, future opportunities, and challenges. Also, some of the open research problems are highlighted, which gives insight into information about the internet of medical things. Different applications are discussed related to IoMT to improve communication standards. Apart from that, the use of unmanned aerial vehicles is increased, which are mostly utilized in rescuing and sending medical equipment from one place to another.

The traditional healthcare system model is now out of date. As the digital era progresses, new advanced technologies and service platforms are highly demanded. The Internet of Medical Things (IoMT), a subset of the Internet of Things, is one such technology. The Internet of Things (IoT) is a network of wireless, interconnected, and linked digital devices that can collect, send and store data without requiring human-tohuman or human-to-computer interaction. Understanding how established and emerging IoT technologies help health systems provide safe and effective care is more important than ever. For example, the rapid spread of Coronavirus disease (COVID-19) has alerted the entire healthcare system. The Internet of Medical Things (IoMT) has dramatically improved the situation, and COVID-19 has inspired scientists to create a new 'Smart' healthcare system focused on early diagnosis, prevention of spread, education, and treatment to facilitate living in the new normal. This paper provides an overview of the IoMT design and how cloud storage technology can help healthcare applications. This chapter should assist researchers in considering previous applications, benefits, problems, challenges, and threats of IoMT in the healthcare field and the role of IoMT in the COVID-19 pandemic. This review will be helpful to researchers and professionals in the field, allowing them to recognize the enormous potential of IoT in the medical world.

As the number of devices connected to the Internet (Internet of Things: IoT) grows, ensuring reliable security and privacy becomes more difficult. With the widespread usage of online medical facilities, security and privacy in the medical arena have become a severe problem that is only becoming worse. The criticality and sensitivity of data in the healthcare industry make guaranteeing the security and privacy of the Internet of medical things (IoMT) even more difficult. The privacy of the patients will be threatened, and their lives may be threatened if effective measures are not implemented in IoMT. Also, it provides novel services, such as remote sensing, elder care assistance, and e-visit, improving people’s health and convenience while lowering medical institution costs per-patient. However, with the rise of mobile, wearable, and telemedicine options, security can no longer be assessed just inside the confines of clean physical walls. Nonetheless, by implementing recognized and applicable safeguards, the risk of exploiting vulnerabilities can be greatly decreased. This article provides an outline of the key security and privacy measures that must be implemented in current IoMT environments to protect the users and stakeholders involved. The overall approach can be seen as a best-practice guide for safely implementing IoMT systems.

Booming growth of ubiquitous connections and clinical computerization in the 5th generation mobile communication era, the explosive increase and heterogeneity of clinical information have delivered enormous demanding situations to information processing, privacy and security, as well as data access in (IoMT) Internet of Medical Things. Our paper gives a complete evaluation of the way to understand the analysis and timely processing of big data in medical applications and the dropping of healthcare resources in high quality under the limitations of previous medical equipment and the medical environment. We mostly concentrate on the benefits carried via the artificial intelligence, edge computing and cloud computing concepts to IoMT. We also explain how to use clinical resources while keeping the privacy and security of clinical information, so that extremely good clinical services can be given to patients.

Medical data can be stored and analyzed using the Internet of Medical Things (IoMT), which is a collection of smart devices that link to a wireless body area network (WBAN) using mobile edge computing (MEC). The Wireless Body Area Network (WBAN) is the most practical, cost-effective, easily adaptable, and noninvasive electronic health monitoring technology. WBAN consists of a coordinator and several sensors for monitoring the biological indications and jobs of the human body. The exciting field has led to a new research and standardization process, especially in WBAN performance and consistency. In duplicated mobility or WBASN scenarios, signal integrity is unstable, and system performance is greatly reduced. Therefore, the reduction of disturbances in the project must be considered. WBAN performance may compromise if co-existing other wireless networks are available. A complete detailed analysis of coexistence and mitigation solutions in WBAN technology is discussed in this paper. In particular, the low power consumption of IEEE 802.15.6 and IEEE 802.15.4, 3 of one of WBAN's leading Wi-Fi wireless technologies, have been investigated. It will elaborate on a comparison of WBAN interference mitigation schemes.

One of the greatest issues confronting the globe now is the pandemic disease calamity. Since December 2019, the world has been battling with COVID-19 pandemic. The COVID-19 crisis has made human life more difficult. Decision-making systems are urgently needed by healthcare institutions to deal with such pandemics and assist them with appropriate suggestions in real-time and prevent their spreading. To avoid and monitor a pandemic outbreak, healthcare delivery involves the use of new technologies, such as artificial intelligence (AI), the internet of things (IoT) and machine learning (ML). AI is reshaping the healthcare system to tackle the pandemic situation. AI is the science and engineering of creating intelligent machines to give them the ability to think, attain and exceed human intelligence. The advancement in the use of AI and IoT-based surveillance systems aids in detecting infected individuals and isolating them from non-infected individuals utilizing previous data. By assessing and interpreting data using AI technology, the IoT-based system employs parallel computing to minimize and prevent pandemic disease. In a pandemic crisis, the ability of ML or AI-based IoT systems in healthcare has provided its capacity to monitor and reduce the growth of the spread of pandemic disease. It has even been shown to reduce medical expenditures and enhance better therapy for infected individuals. This chapter majorly focuses on the applications of AI-based IoT systems in tracking pandemics. The ML-based IoT could be a game-changer in epidemic surveillance. With the proper implementation of proposed inventions, academicians, government officials and experts can create a better atmosphere to tackle the pandemic disease.

In the era of digitalization, artificial intelligence and IoT play an important role in COVID-19. Collecting real-time data using the internet of things has removed barriers and improved end-to-end delays between patients & doctors. During COVID- 19, IoT connected people through wireless communication technology. However, by utilizing AI, different diseases can be identified easily. This research article has merged IoT with AI, which is called the Artificial Internet of Things (AIoT). Monitoring of patient health can be made possible due to the sub-class of AI known as machine learning. Industry 5.0 has combined big data, IoT, AI, 5G and cognitive ICT technologies to exchange information. Due to the widespread of dangerous diseases, people face several challenges, including inadequate preparation, shortage of medicines and poor resources, and increasing death rates. Data collection is the initial step toward research and innovation. Therefore, many applications are discussed properly, which include tele-medicine, early warning systems, wearable devices, and UAVs that help to support the healthcare industry.

Bone provides support to the skeletal system, associated with joints, cartilage, and muscles attached to bones to help move the body and protect the human internal organs. Bone fracture is a common ailment in the human body due to external force on the bone. The structure of the bone is disturbed, which causes pain, frailness, and bone not functioning properly. Avulsion fracture, Greenstick fracture, Comminuted fracture, Compression fracture, Simple fracture, and Open fracture are different types of fractures. The literature presents a significant number of research papers covering the detection of different kinds of fractures (wrist, hand, leg, skull, spine, chest, etc.). There are different medical imaging tools available such as X-ray, Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and ultrasound, which detect different types of fractures. This paper represents a review study to discuss various bone fracture detection and classification techniques between fracture and non-fracture bone.

The field of medicine is one of the most respected and oldest professions in human history. It has a direct impact on human life. The main purpose of this chapter is to present a brief introduction to the use of advanced computer science technologies like machine learning in the process of disease detection. The chapter also discusses different machine learning algorithms which are used in the process of disease detection. It also points out which algorithms give better accuracy. This chapter lists all major and most commonly used machine learning libraries to detect various lifethreatening diseases. Lastly, a discussion on the future trends of technology which can be used in disease detection, and viral disease control is presented.

Disease diagnosis is the most important concern in the healthcare field. Machine Learning (ML) classification approaches can greatly improve the medical industry by allowing more accurate and timely disease diagnoses. Recognition and machine learning promise to enhance the precision of diseases assessment and treatment in biomedicine. They also help make sure that the decision-making process is impartial. This paper looks at some machine learning classification methods that have remained proposed to improve healthcare professionals in disease diagnosis. It overviews machine learning and briefly defines the most used disease classification techniques. This survey paper evaluates numerous machine learning algorithms used to detect various diseases such as major, seasonal, and chronic diseases. In addition, it studies state-of-the-art on employing machine learning classification techniques. The primary goal is to examine various machine-learning processes implemented around the development of disease diagnosis and predictions.

The cardiovascular system includes the heart and its associated blood vessels. Disorders of this cardiac system are called Cardiovascular disorders (CVD). Management of CVDs is often complex due to challenges like inadequate patient care, readmissions, low cost-effectiveness, and cost reductions in preventions, treatments, and lifestyle modifications. Hence, to overcome these challenges, Artificial Intelligence (AI) is being developed. They addressed emerging problems in clinical and health care settings and had a tremendous impact on the public. Implementation of AI in cardiovascular medicine affects more on new findings. It also provides a high level of supporting evidence that may be useful within the evidence-based research paradigm. A review of available free full-text literature in the PubMed database was carried out to study the influence of AI on health care settings. This work reviews AI-based algorithms used in cardiac practice and the applications of AI in cardiovascular medicine in terms of interpretation of results and medical image analysis. 

According to the World Health Organization (WHO), there are millions of visually impaired people in the world who face a lot of difficulties in moving independently. 1.3 billion people are living with some visual impairment problem, while 36 million people are completely visually impaired. We proposed a system for visually impaired people to recognize and detect objects based on a convolutional neural network. The proposed method is implemented on Raspberry Pi. The ultrasonic sensors detect obstacles and potholes by using a camera in any direction and generate an audio message for feedback. The experimental results show that the Convolutional Neural Network yielded impressive results of 99.56% accuracy.

Brain Computer Interface (BCI) systems are able to communicate directly between the brain and computer using neural activity measurements without the involvement of muscle movements. For BCI systems to be widely used by people with severe disabilities, long-term studies of their real-world use are needed, along with effective and feasible dissemination models. In addition, the robustness of the BCI systems' performance should be improved, so they reach the same level of robustness as natural muscle-based health monitoring. In this chapter, we review the recent BCIrelated studies, followed by the most relevant applications. We also present the key issues and challenges which exist in regard to the BCI systems and also provide future directions.

Brain tumor (BT) is a serious cancerous disease caused by an uncontrollable and abnormal distribution of cells. Recent advances in deep learning (DL) have helped the healthcare industry in medical imaging for the diagnosis of many diseases. One of the major problems encountered in the automatic classification of BT when using machine learning (ML) techniques is the availability and quality of the learning from data; these are often inaccessible, very confidential, and of poor quality. On the other hand, there are more than 120 types of BT [1] that we must recognize. In this paper, we present an approach for the automatic classification of medical images (MI) of BT using image fusion (IF) with an auto-coding technique for data augmentation (DA) and DL. The objective is to design and develop a diagnostic support system to assist the practitioner in analyzing never-seen BT images. To address this problem, we propose two contributions to perform data augmentation at two different levels: before and during the learning process. Starting from a small dataset, we conduct the first phase of classical DA, followed by the second one based on the image fusion technique. Our approach allowed us to increase the accuracy to a very acceptable level compared to other methods in the literature for ten tumor classes. 

The traditional technologies and digital systems of managing and maintaining data are inherently prone to manipulation at various levels. Ensuring the anonymity of the patient's identity, the safety of the medical records, and preventing the patient data from accidental and intended manipulations have been the industry's biggest challenges for decades. Failing to control the integrity of the Patient Health Records (PHRs) and Medical Health Records (MHRs) in the Healthcare Data Management System (HDMS)/ Healthcare Information System (HIS) may create challenges in identifying, diagnosing, and treating the disease and puts the patient at a greater risk. The frequency of healthcare data breaches, the magnitude of compromised records, and the financial impact rapidly increase with time. This chapter systematically and critically reviews the issues and challenges faced by various healthcare stakeholders in PHRs/MHRs-based HDMS/HIS systems. Blockchain powered patient health record and sharing schemes can be used to ensure the integrity and safety of healthcare data and share data among various healthcare ecosystem stakeholders using smart contracts to promote transparency, tamper-proofing, and consented access to data in distributed multi-stakeholder environment. This chapter highlights the need for post-quantum cryptography and recommendations for future improvements in blockchain-based patient health records and sharing system.