Skip to main content
main-content

Über dieses Buch

This book covers topics related to medical practices from communications technology point of view. The book provides detailed inside information about the use of health informatics and emerging technologies for the well-being of patients. Each chapter in this book focuses on a specific development in the use of informatics in healthcare. In general, each chapter uses various emerging technologies such as Internet of Things (IoT), Big Data, Cloud computing, Wireless Body Area Networks (WBAN), for various health-related illness, such as tuberculosis, heart diseases, asthma and various epidemic outbreaks. The book is intended both for communications engineers with a healthcare focus and medical researchers.

Inhaltsverzeichnis

Frontmatter

Quality Assessment and Classification of Heart Sounds Using PCG Signals

Abstract
The PCG signals provide valuable information about the heart condition for accurate detection of heart diseases. The noise incorporated in PCG signals during acquisition process makes the detection process a challenging task. In this paper, a complete framework for heart sound classification is proposed. The proposed system introduces the concept of quality assessment before extraction of features and classification of heart sounds. The signal quality is assessed by predefined criteria by based upon number of peaks and zero crossing of PCG signal. Both time and frequency domain features have been extracted to use for classification, which is done using KNN classifier. The results are validated through fivefold cross validation. The algorithm is tested on dataset provided by Pascal classifying heart sound challenge. The average accuracy of the classifier is significantly improved from 0.86 ± 0.0014 to 0.88 ± 0.00117 by introducing the quality assessment of PCG signals and leaving non-suitable/too noisy signals.
Qurat-ul-ain Mubarak, Muhammad Usman Akram, Arslan Shaukat, Aneeqa Ramazan

Classification of Normal Heart Beats Using Spectral and Nonspectral Features for Phonocardiography Signals

Abstract
This study explores the features based on spectrum, energy, and probability for heart beat classification using PCG signals. Features extracted from heart beat signals are fed to a feed-forward artificial neural network to discriminate between the heart sounds S1, S2, and noise. Evaluations are carried out on a publicly available dataset, and the system performance on individual as well as combined features is studied with and without the application of principal component analysis (PCA). An average classification rate of around 84% is reported, and high classification rates are maintained by using only a small proportion of the feature set.
Shahid Ismail Malik, Imran Siddiqi

Segmentation of Chest Radiographs for Tuberculosis Screening Using Kernel Mapping and Graph Cuts

Abstract
Segmentation of lung region is specifically difficult because of the large variation in quality of an image. Accurate identification of lung region is very important for clinical applications. The aim of this paper is to make segmentation of lung region accurately. In this paper, lung mask is calculated by taking the average of manual masks of most similar training images, and graph cut segmentation is applied with kernel energy to extract accurate boundaries. Kernel function is used to transform image data into higher dimension data in order to make piecewise constant model of graph cut formulation that becomes applicable then. Minimization of energy function contains graph cut iterations of image partitioning and iterations of updating the region parameters. Performance is evaluated by Dice coefficient. Dice coefficient is used to measure the similarity between manual and segmented mask. Experimental results of proposed methodology state the accuracy of 92.19%. It is observed that all the cases obtain the score more than 0.88 which is sufficient to detect lung region efficiently.
Ayesha Fatima, Anam Tariq, Mahmood Akhtar, Hira Zahid

Survey Analysis of Automatic Detection and Grading of Cataract Using Different Imaging Modalities

Abstract
Cataract is the most common ocular disease mainly developed during old age. It occurs due to the buildup of protein at lens over a long period of time which makes the lens cloudy. Early and accurate diagnosis of cataract helps prevent vision loss. To alleviate the burden of ophthalmologist, many researchers working in the field of biomedical imaging developed a number of techniques for the automatic detection and grading of cataract. Imaging modalities used for this purpose includes slit-lamp images, retro-illumination images, digital/optical eye images, retinal images, and ultrasonic Nakagami images. In this paper, we review cataract detection and grading methodologies using these imaging modalities. For each imaging type, we analyze the possible methods and techniques applied so far. We also investigated the advantages and shortcomings of these techniques and methods and suggested the ways to improve the existing methods.
Isma Shaheen, Anam Tariq

A Privacy Risk Assessment for the Internet of Things in Healthcare

Abstract
The Internet of Things (IoT) brings connectivity to about every object found in the physical space. It extends connectivity not only to mobile and wearable devices but also to everyday objects. From connected fridges and cars to fully interconnected smart cities, the IoT creates opportunities in numerous domains. This paper briefly highlights the promising applications of IoT in healthcare. The privacy challenges, risks, and vulnerabilities posed by the diversity and heterogeneity of communications in the IoT are then identified, followed by a privacy risk assessment.
Mahmoud Elkhodr, Belal Alsinglawi, Mohammad Alshehri

Parallel Computation on Large-Scale DNA Sequences

Abstract
With the advent of next-generation DNA sequencing technology, the field of bioinformatics and computational biology is becoming increasingly complex and computationally intensive. The bioinformatics community faces the challenge of finding suitable methods to solve growing computational issues, for instance, processing of massive volumes of DNA sequences. Such method can be found in the field of high-performance computing through parallel processing. In this paper we have proposed parallel approach which is built on top of modified VSM. The proposed method is parallelized computation on a number of available processing cores in order to minimize computation time and support analysis of a large number of DNA sequences analysis.
Abdul Majid, Mukhtaj Khan, Mushtaq Khan, Jamil Ahmad, Maozhen Li, Rehan Zafar Paracha

Augmented and Virtual Reality in Mobile Fitness Applications: A Survey

Abstract
Obesity is a major issue around the world. It is the main reason for several chronic diseases. Obesity can be stopped by encouraging people to do physical activities and making behaviour intervention regarding lifestyle. Mobile fitness apps are emerging because of the unique features that are provided. They are seen as a vital tool to motivate people suffering from obesity to perform physical activities and make behaviour intervention regarding health and fitness. Augmented reality (AR) and virtual reality (VR) technologies have been used successfully in different kinds of mobile apps. This paper presents a systematic review of some of the most recent AG and VR researches in mobile apps. It discusses the main findings of applying both technologies in different fields of mobile apps. Based on this systematic review, a fitness mobile app for obese individuals that consider both AR and VR technology will be developed.
Ryan Alturki, Valerie Gay

Cloud-Assisted IoT-Based Smart Respiratory Monitoring System for Asthma Patients

Abstract
In the modern era of technology, smart, secured, interactive, and comprehensive healthcare is essential. The exponentially growing Internet of things (IoT) technologies with the growing attention of patients has played an essential part in the smart healthcare system. To prevent the avoidable deaths, a real-time monitoring healthcare framework is required to analyze the patient’s health condition. HealthcareIoT has substantial potential to achieve such kind of monitoring and care. HealthcareIoT is the integration of several communication technologies, people, sensors, and devices and connected applications to capture, track, store, and monitor patient information. In this paper, we present a smart HealthcareIoT solution for asthma patients, where respiration rate is captured through smart sensors and securely transmitted to the cloud. Where healthcare advisors can access and provide medication after analyzing patient information. Watermarking and signal enhancement techniques are used to secure and reduce identity theft in the transmission. The proposed work has been authenticated by both simulation and experimental results.
Syed Tauhid Ullah Shah, Faizan Badshah, Faheem Dad, Nouman Amin, Mian Ahmad Jan

Blood Cell Counting and Segmentation Using Image Processing Techniques

Abstract
The accurate count of a patient’s blood cells is vital for successful diagnosis of a plethora of diseases. Current systems deployed in Pakistan either rely on heavy and expensive machinery or is sometimes conducted manually. We propose the use of digital image processing techniques to build a cheaper alternative, that rely on digital images of blood smears, which are economical to produce, and are in fact a costless feature built-in to most existing lab microscopes. In this work, morphological image processing is deployed to segment the image and to differentiate and extract the blood cells from the plasma. The algorithm will exploit the shape and radius of blood cells for counting. After segmenting blood cells, their counting becomes a trivial task. The proposed system will be complementary to medical practitioners and provide a second opinion for their subjective diagnosis.
Ayesha Hoor Chaudhary, Javeria Ikhlaq, Muhammad Aksam Iftikhar, Maham Alvi

Smart Assist: Smartphone-Based Drug Compliance for Elderly People and People with Special Needs

Abstract
Aging is a natural phenomenon, and maintaining quality of life for elderly people and for people with special needs is a challenge. Many physiological functions tend toward decline, and people suffer from several chronic conditions in later stages of life, which usually lead to high drug consumption. Medication noncompliance remains a common healthcare problem and affects patient health adversely in the developed as well as in the underdeveloped world. Patients with chronic illnesses are often burdened with high medication intake and less awareness of their medical conditions and routine, creating a challenging environment to promote medication compliance. Technological assistance like the emergence of smartphone echoes opportunities for utilization of health services with minimal interaction, portability, and pervasiveness. This paper focuses on an augmented reality/computer vision-based solution for drug compliance for elderly people; with this, patients will be having greater control over medication management easily and flexibly keeping in view the usage/learning constraints of senior citizens via Smart Assist. Smart Assist has expected to fulfill the unrestricted conditions of healthcare applications.
Akif Khan, Shah Khusro

An Overview of OCT Techniques for Detection of Ophthalmic Syndromes

Abstract
The retina is an essential part of the human eye. It is a very small part at the subsequent pole of the human eye, and it is composed of a tissue cell that can detect the presence of light. The tissue is sensitive enough to detect the amount of light present, its intensity, and a range of different wavelengths as well. These tissues generate nerve signals, and those signals are passed to the brain via the optic nerve. If the retina malfunctions, then different retinal disorders can occur such as diabetic retinopathy, glaucoma, and pathologic myopia. These can be considered the major causes of total loss of vision throughout the world.
Usually these diseases are treated by different ophthalmologists and specialist of the fields, but it has been seen that once the disease strikes, it becomes very different and in most of the cases impossible to reverse and gain full vision fitness. Thus, it is of the essence that earlier detection of the disease must be done so that the remedy can work. If the treatment starts in time, vision can be saved. In order to perfectly detect the disease, the ophthalmologists require some quantitative and qualitative analysis of the disease. These readings have to be noted at the start of the detection and throughout the process of the therapy. Depending upon these readings, the ophthalmologists can declare where the patient is heading, toward betterment or toward a worse condition.
The gathering of these qualitative and quantitative metrics through manual methods is insufficient and produces erratic and inconsistent outputs. Therefore, it can be said with a certain degree of confidence that a computerized automated system must be in place to do the job. In this review, a comprehensive analysis and evaluation of practices are accomplished of diverse computer vision and image processing techniques applied to OCT images for an automatic, computer-aided examination for the diagnosis of retinal disorder diseases. Disease origins and causes are also testified, and these can have proved a very basic understanding of the disease and how the computer-aided diagnosis (CAD) system can be made using this knowledge. Therefore, this review can provide a good understanding to analyze visual impairments found in OCT images. This can be of aid to any researcher in the future to design a system for detection retinal diseases.
Adeel M. Syed, Muhammad Usman Akbar, Joddat Fatima

Fully Automated Identification of Heart Sounds for the Analysis of Cardiovascular Pathology

Abstract
Cardiac disorders are spreading rapidly all over the world, and as per the World Health Organization (WHO), 17.5 million people die each year due to cardiovascular diseases (CVD). So there is a dire need to develop cost-effective, time-efficient, and fully automated solutions to diagnose cardiovascular abnormalities. Many researchers have worked on detecting CVD from electrocardiogram (ECG) signals. ECG signals give reliable information about cardiac pathology; however phonocardiogram (PCG) signal provides an easy, cost-effective, objective, and comprehensive information about cardiovascular abnormalities by measuring heartbeats. This paper presents a fully automated robust clinical decision support system that can identify cardiovascular pathology by analyzing heart sounds from PCG signals. The proposed system was tested on 55 PCG signals from which 24 samples contained healthy and 31 samples contained abnormal heart sounds. The proposed system correctly classified healthy and diseased samples with the accuracy, sensitivity, and negative predictive value (NPV) of 87.2%, 96.7%, and 94.7%, respectively.
Ghafoor Sidra, Nasim Ammara, Hassan Taimur, Hassan Bilal, Ahmed Ramsha

Modeling and Simulation of Resource-Constrained Vaccination Strategies and Epidemic Outbreaks

Abstract
Ongoing research on epidemic modeling is seeking for interventions to contain epidemic spread. Developing countries are at high risk of epidemics and pose a threat to developed countries as well. We have developed an epidemic scenario simulator to assist in choice of optimal vaccination strategy in case of scarce resources. The objective of this model is to explore the impact of different strategies on virus spread for different diseases. It is known that due to limited resources, vaccination of whole population is not feasible. Our simulation explores the extent to which the effect of vaccination of a subset of population can be effective to minimize the spread of disease. Further at any point in time, the model gives information regarding the health status of population.
Rehan Ashraf, Bushra Zafar, Sohail Jabbar, Mudassar Ahmad, Syed Hassan Ahmed

Big Data in Healthcare: A Survey

Abstract
Big Data is all about procedures, processes, tools and techniques used which an organization can manipulate, create and manage very large amount of data and storage facilities. Healthcare is one of the biggest domains of Big Data which has generated a very big amount of data which is driven by record-keeping. The recent technological developments have motivated healthcare organization to adopt data-centric models and architectures. This paper is a survey of existing research work from 2014 to 2017 and presents the characteristics, tools and techniques, challenges and limitations and architecture of the Big Data in healthcare.
Muhammad Mashab Farooqi, Munam Ali Shah, Abdul Wahid, Adnan Akhunzada, Faheem Khan, Noor ul Amin, Ihsan Ali

Internet of Things-Based Healthcare: Recent Advances and Challenges

Abstract
The Internet of Things (IoT) considers intelligent objects to be the fundamental building blocks for the enlargement of smart cyber-physical systems. The range of IoT applications is widespread, including smart healthcare. The IoT uprising is remodeling current healthcare to achieve a favorable economic, social, and technological vision. This chapter investigates improvements in IoT-based healthcare services and technologies and surveys the fundamental industrial trends, network platforms/architectures, and applications leanings in smart IoT–healthcare solutions. Moreover, this chapter investigates different IoT privacy and security structures, comprising risk models, security requirements, and attack taxonomies from the perspective of healthcare. It also discusses how various innovations such as ambient intelligence, wearables, and big data can be affected in the healthcare environment, addresses different eHealth and IoT regulations and strategies, and offers possibilities for future research on smart IoT-based healthcare and its various challenges and issues.
Syed Tauhid Ullah Shah, Hekmat Yar, Izaz Khan, Muhammad Ikram, Hussain Khan

Backmatter

Weitere Informationen