Healthcare IoT Architectures, Technologies, Applications, and Issues

The internet of things (IoT) revolution is improving the proficiency of human healthcare infrastructures, and this chapter analyzes the applications of IoT in healthcare systems with diversified aspects such as topological arrangement of medical devices, layered architecture, and platform services. This chapter focuses on advancements in IoT-based healthcare in order to identify the communication and sensing technologies enabling the smart healthcare systems. The transformation of healthcare from doctor-centric to patient-centric with the diversified applications of IoT is discussed in detail. In addition, this chapter examines the various issues to be emphasized on designing an effective IoT-based healthcare system. It also explores security in healthcare systems and the possible security threats that may be vulnerable to the security essentials. Finally, this chapter summarizes the procedure of applying machine learning techniques on healthcare streaming data which provides intelligence to the systems.

Data Analysis and Integration in Healthcare

Healthcare providers treat a plethora of conditions associated with the human body for a patient to achieve optimal healthiness. However, aspects of a patients' entire wellbeing can often be overlooked, which leads to issues such as drug interactions, missed diagnoses, and other gaps in care. Healthcare can benefit from implementing better data management and integration to improve data analysis, which could bridge gaps in care. This chapter will explain data analysis and data integration, why they are pertinent in the healthcare system, and their associated rewards and challenges. After analyzing these healthcare facets, this chapter will conclude with a proposal for healthcare providers to leverage technology for patients' general wellbeing and a healthier population.

Deep Learning and Medical Imaging

Deep learning (DL) is a special type of machine learning that attains great potency and flexibility by learning to represent input raw data as a nested hierarchy of essences and representations. DL consists of more layers than conventional machine learning that permit higher levels of abstractions and improved prediction from data. More abstract representations computed in terms of less abstract ones. The goal of this chapter is to present an intensive survey of existing literature on DL techniques over the last years especially in the medical imaging analysis field. All these techniques and algorithms have their points of interest and constraints. Thus, analysis of various techniques and transformations, submitted prior in writing, for plan and utilization of DL methods from medical image analysis prospective will be discussed. The authors provide future research directions in DL area and set trends and identify challenges in the medical imaging field. Furthermore, as quantity of medicinal application demands increase, an extended study and investigation in DL area becomes very significant.

Evolution of Digital Technologies and Use of Virtual Assistants in Drug Development

The drug development phase is one of the most time-consuming and expensive stages in the lifecycle of a drug. Marred by patent expirations, price regulations, complexities in disease conditions, life sciences companies are facing a daunting task to bring new molecular entities into the market. Digital health technologies are playing a critical role in addressing some of the challenges faced during drug development. In this chapter, the author talks about the challenges and key trends in the world of drug development, use of new digital health technologies, and the future of drug development. As an example, the author dives into a specific case study on the use of virtual assistants in clinical trials and the benefits of its usage on patients, healthcare professionals, and life sciences companies.

An Ambient Multi-Agent System for Healthcare Monitoring of Patients With Chronic Diseases

Chronic diseases are a major cause of death in the world. Thus, many guidelines have been proposed to prevent these diseases. In addition, various systems have been developed to ease health monitoring. However, they are generally behaving as reminders or as anomaly detection systems. After giving an overview of the existed solutions and discussing their drawbacks, the authors present their system which is called ambient healthcare monitoring system (AHMS). It provides a continuous, unobtrusive, and mobile health monitoring of patients with chronic diseases. It is based on the multi-agent paradigm that allows devices to be distributed and autonomous. In addition, it benefits from the characteristics of ambient intelligence (AmI) such as ubiquity and context-awareness. So, AHMS is a promising solution for unobtrusive healthcare monitoring, in which it offers efficient medical services, with less energy consumption, that can significantly reduce the healthcare cost by automating some routine tasks. Consequently, it reduces the latency as well it minimizes the overload on the caregiver.

Development of Human Speech Signal-Based Intelligent Human-Computer Interface for Driving a Wheelchair in Enhancing the Quality-of-Life of the Persons

For the past few decades, an increase in experimental research has been carried out in enhancing the quality-of-life of the persons with different levels of disabilities. To enhance the lifestyle of differently disabled in terms of their mobility or movement or transportation, a proper aid with appropriate human-computer interface system is needed. So, in this chapter, a hybrid classification model is proposed, which combines and uses hM-GM and ANN models, for classifying human speech signal, especially the word for driving a wheelchair for helping the people, who seek transportation. For classifying the correct word from the phase of sentence (i.e., the human speech signal) to corresponding trigger command for an electrically powered wheelchair prototype, under the certain experimental condition, the hM-GM model yields good recognition of words, but they suffer major limitations as it relies on strong statistical properties and probability. Hence, by combining hM-GM and ANN model-based classifier for enhancing the accuracy of classifying the word to corresponding trigger command.

Application of Big Data in Digital Epidemiology

Epidemiology is the study of dynamics of health and disease in human population. It aims to identify the occurrence, pattern, and etiology of human diseases so that the causes of these diseases can be understood, which in turn will help in preventing their spread. In traditional epidemiology, the data is collected by various public health agencies through various means. Many times, the actual figures vary a lot from the one reported. Sometimes this difference is due to human errors, but most of the time, it is due to intentional underreporting. Big data techniques can be used to analyze this huge amount of data so as to extract useful information from it. The electronic health data is so large and complex that it cannot be processed using traditional software and hardware. It is also not possible to manage this data using traditional data management tools. This data is huge in terms of volume as well as diversity and the speed at which it is being generated. The ability to combine and analyze these different sources of data has huge impact on epidemic tracking.

A Forecasting Model for Patient Arrivals of an Emergency Department in Healthcare Management Systems

Emergency departments (EDs) are one of the most valuable departments of healthcare management systems. Patient arrivals at the EDs are crucial for planning of the future. Accurate forecasting of patient arrivals contributes to better organized human resources and medical devices in the EDs. Therefore, in this chapter, the authors aim to develop a hybrid model including the methods of autoregressive integrated moving average with external variables (ARIMAX) and artificial neural network (ANN) in a hospital ED. The arrival data was collected from the hospital information system of a public hospital in eastern Turkey. The model incorporates factors related to ED arrivals such as climatic and calendar variables. By the aid of the proposed model, an insight to arrangement and planning of ED resources can be provided in a better way.

Telemonitoring Healthcare System-Based Mobile Agent Technology

Generally, distributed computing through a handheld/mobile device has to be considered with care because of the limited capabilities on these devices. Especially in ubiquitous telemonitoring healthcare, which refers to the disposition of any type of health services, such that medical staff members (physicians, emergency workers, other healthcare providers, etc.) through mobile computing devices can access them and expect data to be made available. In this chapter, the authors present a new system based on ubiquitous agents to assist telemonitoring employees, not only anytime and anywhere but also on any device.

Artificial Intelligence in Medical Science

The use of intelligent artificial devices has solved many real-world problems and also improved the living style of human beings. The capability of providing unbiased and accurate result has also increased the demand for these devices. For getting faster and well-organized outcomes, scientists and researchers are giving more and more interest in developing such devices. Use of expert systems, concepts from nature-inspired algorithms, neural networks, genetic algorithms, fuzzy logic, internet of things are used extensively to solve various problems in science and engineering. In medical science these techniques are used for data analysis, disease diagnosis, data retrieval, object detection, pattern analysis, data management, monitoring patient health status by physicians, interactions between patients and physicians, keeping record of the medications of the patients, and so on. This chapter performs a detailed analysis on the use of intelligent devices in medical science and about the root concepts on which these devices are designed.