Smart Systems for E-Health

Limb loss can occur at different levels and for different reasons. The leading cause of limb amputation can be related to accidents like traffic accidents or work accidents; it can be also caused by disease such as diabetes, dysvascular amputation, trauma-related amputation, cancer-related amputation, and congenital-related incidences. Amputees can also be victims of military conflict and many other reasons. Loss can affect upper-limb or lower-limb at different levels. The lower-limb replacement differs from that of an upper-limb in that hand prosthesis performs wider range of movements and has more muscle tissue to be stimulated. For example, the inability to have a firm handshake may have an adverse impact on the quality of the amputee’s social and vocational life. For this reason, an intelligent esthetic prosthetic hand design is important especially in a region like the Middle East in which conflict and war are increasing day after day and amputation become widely spread. Our work proposes a control system of multifunctional multiarticulate prosthetic hand based on EMG signal processing and classification. This work uses the open dataset described in Sapsanis et al. (Improving EMG based classification of basic hand movements using EMD” in 35th annual international conference of the IEEE engineering in medicine and biology society ’13, 2013 [1]) to classify six basic daily hand motions acquired from five normal patients (two males and three females). This chapter is divided into four parts, the first part consists of presenting the need for this technology, problems encountered by prosthetic hand designers, specifications of existing commercialized prosthetics, and the contribution of our prosthetic hand in making this technology available and comfortable for amputees with respect to the intelligent command and esthetic look. In the next stage, we present different techniques used for pre-processing the electromyogram (EMG) signal in order to improve the classification results. Those techniques include filtering, envelope detection, and feature extraction methods in time domain, frequency domain, and time–frequency domain. Then, dimensionality reduction methods help in reducing information redundancy and increasing inter-class separability. The third section illustrates the intelligent command techniques used to classify hand movement like support vector machine (SVM), K-nearest neighbours (KNN), artificial neural network (ANN), and linear discriminant analysis (LDA). The results are promising and some validation techniques are used to verify the consistency and the reliability of these results. The final part is the implementation of our prosthetic hand. In this stage, we describe technical specifications of this prosthesis and the integration of different parts of the whole system, software, and hardware. We discuss also the relevant feature that makes this prosthetic one of the most appreciated design.

Since most people spend a considerable part of their time indoors, the indoor environment has a determining influence on human health. In several instances, the air quality parameters are extremely distinctive from those defined as healthy values. Using real-time monitoring, occupants or the build manager can administer interventions in order to improve indoor air quality (IAQ). The constant scientific improvements in numerous areas such as Ambient-Assisted Living and the Internet of Things (IoT) make it possible to build smart things with significant features for sensing and connecting. Therefore, the authors introduce an IoT architecture for real-time monitoring of IAQ. This system named iAQ Wi-Fi+ uses an open-source Arduino UNO as processing unit, an ESP8266 for Wi-Fi 2.4 GHz as a communication unit, and incorporates a temperature and humidity sensor, a CO₂ sensor, a dust sensor, and a digital light sensor operating as a sensing unit. This solution is also composed of a smartphone application for data consulting. The monitored data can be discussed by clinicians to support medical diagnostics for enhanced healthcare. Compared to other solutions, the iAQ Wi-Fi+ is based on open-source technologies and brings a Wi-Fi system, with several advantages such as its modularity, scalability, low-cost, and easy installation. The results obtained are very encouraging, representing a meaningful contribution to IAQ monitoring systems based on IoT.

Supervised image restoration is a process of reconstructing or recovering an image that has been degraded by using a priori knowledge of the degradation phenomenon. This includes deblurring images degraded by the limitations of sensors or source of captures, in addition to noise filtering and correction of geometric distortion due to sensors. Generally, restoring original images from their distorted form is a necessary step in many domains such as medical domain. In the literature, there are several classical medical images restoration techniques such as Wiener filtering. Thus, restoration techniques are oriented toward modeling the degradation and applying the inverse process in order to find an estimate of the original image. To recover the original medical image, Wiener filter needs a prior knowledge of the degradation phenomenon caused by the imaging system, the blurred image, and the statistical properties of the noise process. In this work, we propose a new fast algorithm for supervised medical images restoration that does not require a priori knowledge about the noise distribution. The degraded image is first deconvoluted in Fourier space by parametric Wiener filtering, then it is smoothed by the wave atom transform after applying a local adaptive shrinkage to its coefficients. Experiment results are very interesting and show the efficiency of the suggested method based on a comparison study.

The growing importance and maturity of Internet of Things (IoT) and wearable computing are revolutionizing healthcare diagnosis and body treatment by providing access to meaningful healthcare data and improving the effectiveness of medical services. In this context, personal health information must be exchanged via trusted transactions that provide secure and encrypted sensitive data of the patient. Moreover, healthcare smart devices need flexible, programmable, and agile networks to allow on-demand configuration and management to enable scalable and interoperable healthcare applications. Two complementary trends show promise in meeting these needs. First, blockchain is emerging as a transparent, immutable, and validated-by-design technology that offers a potential solution to address the key security challenges in healthcare domains by providing secure and pseudo-anonymous transactions in a fully distributed and decentralized manner. Second, software-defined networking (SDN) offers a significant promise in meeting the healthcare communication needs by providing a flexible and programmable environment to support customized security policies and services in a dynamic, software-based fashion. To that end, we present our ideas on SDN-enabled blockchains that can be used to develop and deploy privacy-preserving healthcare applications. First, we present a survey of the emerging trends and prospects, followed by an in-depth discussion of major challenges in this area. Second, we introduce a fog computing architecture that interconnects various IoT elements, SDN networking, and blockchain computing components that control and manage patients’ health-related parameters. Third, we validate our architecture in the context of three use cases involving smart health care, precision medicine, and pharmaceutical supply chain. Finally, we discuss open issues that need significant new research investigations.

The goal of this book chapter is to set the optimal safety possibility to use wearable biosensors for patient monitoring. This objective consists in minimizing the security risks by using the adequate methodology for working with personal sensitive data, anonymization and data analytics in the cloud. The possibilities of using data are to filter in a private cloud and to anonymize for analyzing in public cloud. The proposed methodology will ensure the security and privacy by using different level of protection for different type of user accounts (medical staff and patients). The anonymization of the patients’ information is relevant because data is used for a secondary purpose—predictive analysis modeling for understanding and anticipate the diseases behaviors or for preventive medical actions.

The Internet of Medical Things (IoMT) communication systems are increasingly using wireless networks. However, the use of these networks for such critical systems raised some issues and problems such as the need of allowing more autonomy to the patient with anywhere and anytime monitoring capabilities. Cognitive radio (CR) can be a suitable solution to adapt the wireless network for the IoMT requirements by providing permanent connectivity and, therefore, the spectral availability. In this chapter, we propose a novel design of cognitive radio-based Internet of Medical Things (CR-IMT) networks by providing an efficient, softly and trustworthy integration of cognitive radio technologies in the IoMT applications. Firstly, we propose a cooperative trustworthy spectrum sensing mechanism that enhances the trusty free-band detection accuracy by using a trust and reputation management system. Thus, we formulate two competition noncooperative game models to encourage the cognitive users to trustfully cooperate and to update dynamically the trust values. Moreover, we introduce an opportunistic spectrum scheduling model to ensure the transmission of critical medical data according to the game model outcomes. Extensive simulations validate our approach and prove that it outperforms the traditional established methods in terms of correct detection probability, error probability, data and sensing throughput, delay and residual energy.

In recent years, scholarly work on cybersecurity in smart health has gained substantial attention from both practitioners and scholars. This is primarily due to the rapid growth in the field of information, communications and technology, protocols, an important aspect of smart health communication infrastructure. The smart health communication infrastructure is solely developed to provide data communication for specific networks such as wireless body area network (WBAN) which is developed for the health sector. The modern healthcare service delivery eliminates the need for real-time inspection of elderly and attention-need patients; that is, medical experts can monitor such people from a remote location through e-health communication infrastructure. The developed communication infrastructure is used by e-health organizations to store, process or transfer patient’s data which has high priority and requires confidentiality. The infrastructure used by e-health organizations must restrict unauthorized access to patient data against any intruder. e-health organizations are a major target for hackers as they hold a huge amount of private data as a source of wealth of information. The proposed security solutions for e-health organizations require specific policy developments and propose solutions for specific security layers. The smart, scalable and adaptable solutions are proposed by researchers to overcome several security challenges in e-health organizations. Some of the proposed solutions provide open use and sharing of critical e-health data without compromising patients’ rights to privacy and confidentiality. The deployment of these solutions faces several problems since hackers targeting network layer of these models. Development of new attack methodologies and technological enhancements strengthens hackers to attack with different motivations and compromise e-health organizations’ private data. For this reason, a new security framework is necessary for e-health organizations’ communication infrastructure. The privacy of the patient’s health data must be carefully addressed while developing a new framework. In order to maximize the healthcare quality and minimize the e-health cost, the ultimate goal of this chapter is to expose the limitations in the current e-health organization cybersecurity solutions and provide a new security framework to highlight existing gaps in communication infrastructure of e-health organizations. The comparison of cryptographic attacks against encryption algorithms to secure communication infrastructure, latest zero-day attacks in e-health sector, network layer attacks to e-health organizations and e-health threat intelligence will be investigated within the scope of this chapter. The e-health threat intelligence will be the main contribution of this chapter since threat intelligence provides insight about the possible threat and ensures that e-health organization can defend against zero-day vulnerabilities and protect the patient and other staff personal identification information.

In front of the continued growth of autistics number in the world, intelligent systems can be used by non-specialists such as educators or general physicians in autism screening. Moreover, it can assist psychiatrists in the diagnosis of autism to detect it as early as possible for early intervention. We propose in this chapter a tool for the diagnosis of autism: DAS-Autism. It is a knowledge-based system that handles qualitative knowledge in the multi-valued context. For this, we use our knowledge-based system shell RAMOLI, and its inference engine executes an approximate reasoning based on linguistic modifiers that we have introduced in a previous work. We have built a knowledge base that represents the domain expertise, in collaboration with a child psychiatry department of Razi hospital, the public psychiatric hospital in Tunisia. We have then conducted an experimental study in which we compared the system results to expert’s diagnoses. The results of this study were very satisfactory and promising.

Supervisory systems have become interesting solutions for monitoring the health of home-based people. Frail older people are at high risk of becoming dependent if they are not cared for quickly. Embedded devices at home or on the person are two possible options which, when  coupled, allow a more precise knowledge of behaviors and a faster triggering of the alert. The idea still applied is to model the person’s activities or health parameters in a continuous and automated way to detect deviations from the usual behavior. This clinico-technical approach has been developed and tested in different places and by several research teams with a real medical interest in having a longitudinal knowledge of a patient’s behavior. However, prevention and follow-up of home prescriptions must go beyond the purely technological and medical aspects and take economical and organizational dimensions into account. We consider that three types of complementary actions must be implemented: a fundamental action on the scientific and technological level to know how to build, from the data collected, “a profile of user activity;” detecting, in real time, all kinds of deviations from the normal pattern; training and ground demonstrations actions.

The purpose of this chapter is to provide a literature survey through an overview of the research fields relevant to cancer treatment and prediction approaches based on machine learning. The past few years have witnessed an exponential growth in databases and repositories due to the increase in scientific knowledge and the massive data production. Biomedical domain represents one of the rich data domains. An extensive amount of biomedical data is currently available with wealth of information, ranging from details of clinical symptoms to various types of biochemical data and outputs of imaging devices El Houby (J Appl Biomed, 2018 [1]). One of the important biomedical research domains, epidemiological cancer research, who is of high priority across the world. Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. Every sixth death in the world is due to cancer, making it the second-leading cause of death (second only to cardiovascular diseases) Schutte (Global, regional, and national age-sex specific mortality for 264 causes of death, 1980–2016: a systematic analysis for the Global Burden of Disease Study, 2017 [2]). The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The vast amount of hidden data in huge databases related to cancer with all his variability has created tremendous interests in the field of data mining. While data mining is a discipline resulting from the combination of classical statistics and computer science algorithms, such as machine learning, aim to the extraction of new and useful knowledge from a large amount of data, it has become a useful instrument in bioinformatics. It can depict variation of cancer incidence and mortality by region, ethnicity, gender and socioeconomic factors that contribute to the assessment of population health needs, while it can contribute to the study of cancer burden. Furthermore, in-depth analysis of the patient’s profile using data mining methods may uncover hidden, previously unknown relations between patient profile, cancer treatment and surveillance. This chapter will present recent approaches and works related to this context. It presents also a synthesis of current and future trends for smart systems for E-health.