Impact of Patient Health Education on the Screening for Disease Test-Outcomes

Screening for diseases is a medical process to predict, prevent, detect, and cure a disease in people at high risk. However, it is limited in the quality and accuracy of the outcomes. The reason for this is the lack of long-term data about the health condition of the patient. Launching modern information and communication technology in the screening process has shown promise of improving the screening outcomes. A previous study has shown that patient education can positively impact the patient behavior face to a disease and can empower the patient to adopt a healthy lifestyle and thus avoid certain diseases. Offering medical education to the patient can positively impact screening outcomes since educated and empowered patients are more aware of certain diseases and can collect significant information. This can minimize the rate of false positive as well as false negative screening results. This chapter analyzes how medical education can contribute to improving screening outcomes.

Clinical Decision Support System for Early Disease Detection and Management

Medical error is an adverse event of a failure in healthcare management, causing unintended injuries. Proper clinical care can be provided by employing a suitable clinical decision support system (CDSS) for healthcare management. CDSS assists the clinicians in identifying the severity of disease at the time of admission and predicting its progression. In this chapter, CDSS was developed with the help of statistical techniques. Modified cascade neural network (ModCNN) was built upon the architecture of cascade-correlation neural network (CCNN). ModCNN first identifies the independent factors associated with disease and using that factor; it predicts its progression. A case progressing towards severity can be given better care, avoiding later stage complications. Performance of ModCNN was evaluated and compared with artificial neural network (ANN) and CCNN. ModCNN showed better accuracy than other statistical techniques. Thus, CDSS developed in this chapter is aimed at providing better treatment planning by reducing medical error.

Innovative Approaches for Pre-Screening and Sensing of Diseases

Prescreening and sensing of diseases offers a number of benefits that can help in prevention of major diseases. The aim of disease pre-screening is to detect possible disorders or diseases in people who do not have any symptoms. Earlier screening methods for the detection of diseases was invasive, complicated, and would require extensive tests. Some conventional methods used in clinical diagnoses include many invasive and potentially hazardous biopsy procedures, endoscopy, computed tomography; numerous innovative approaches have evolved to overcome the limitations of traditional techniques. Non-invasive biomedical sensor, genomics, electronic nose, nano-material, plasmonicsensor devices, microfabrication-based technologies, flat-panel detectors, digital breast object models, endomicroscopy, breath biopsy, and wavelet-based enhancement methods are some of the emerging frontiers in prescreening and sensing of diseases. This chapter will provide an in-depth discussion of the abovementioned innovative techniques related to prescreening and sensing of diseases.

Safety and Regulatory Aspects of Systems for Disease Pre-Screening

Pre-screening solutions for disease prediction fall under medical device regulations because of the intended purpose of diagnosis. The chapter begins with an overview of the medical device regulations focusing on the two major regulations. The definition of a medical device to the guideline of how a medical device is classified is then discussed. The later part of the chapter covers the design control process with stages of user needs translating to requirements, the design process with the design outputs, design verification conforming that the design is right, followed by design validation that proves that a right medical device is made. The risk management, usability engineering, and security and privacy risk management are part of the product realization process. Having a clear regulatory strategy and plan beginning with the list of target countries and intended use followed by identification of all the applicable product standards is vital. The process thus culminates in the design and development file which is a formal document that describes the design history of the medical device.

Applications of Machine Learning in Disease Pre-screening

Computers in disease prescreening are utilized to interpret medical information. This is known as computer-aided pre-screening tool (CAPST). CAPST helps in improving the accuracy of diagnosis in medicine. The medical experts usually take the outcome of the CAPST as a second opinion to make the final diagnostic decisions. Fast and accurate prediction of disease risk and diagnosis is crucial step for the successful treatment of an individual. The AI-based machine learning technology has undergone significant developments over the past few years and is successfully used in many intelligent applications covering problems of variety of domains. One of the most stimulating questions is whether these techniques can be successfully applied to medicine in disease pre-screening and diagnosis and what kind of data it requires to be trained and learned. There are so many real-time examples of the problems where machine learning methods are applied successfully, especially in medicine. Many of them showed significant improvement in classification accuracy.

Fuzzy-Based Predictive Analytics for Early Detection of Diabetes

Today, diabetes is the most costly and burdensome chronic disease. The severity of diabetes is reducing with anticipation, premature recognition, and the early supervision impediments in people. These symptoms are the optimization of the diagnosis phase of the disease through the process of evaluating symptomatic characteristics and daily habits of patients. Big data analytical tools play a useful task in executing significant real-time investigation on the huge volumes of data and are also used to foresee the crisis situations earlier than it occurs. This chapter accomplished an efficient assessment of the applications of machine learning algorithms and tools in the diabetes investigation relating to genetic background and environment. With improving accuracy for early detection and prevention of diabetes, this chapter implemented a fuzzy linear and logistic regression model with fuzzy clustering for predicting early detection of diabetes.

Barriers to Adoptions of IoT-Based Solutions for Disease Screening

Change of disease patterns from communicable to chronic diseases has a tremendous impact on the healthcare ecosystem. For healthcare organizations to remain viable and economically sustainable during this transition, there is a desperate need of cost-effective solutions for chronic disease management. One important strategy for this is early diagnosis and management of diseases. With rapid technological advancements, IoT-based solutions are well-positioned to be an effective tool for disease screening and health monitoring provided that they are also able to bridge non-technical barriers in technology adoption. The three primary stakeholders for screening solutions are healthcare organizations, clinical fraternity, and end-users. The primary objective of this chapter is to review likely barriers in adoptions of the IoT solutions from the perspective of these three primary stakeholders.

A Fourier-Bessel Expansion-Based Method for Automated Detection of Atrial Fibrillation From Electrocardiogram Signals

This chapter presents a new methodology for detection and identification of cardiovascular diseases from a single-lead electrocardiogram (ECG) signal of short duration. More specifically, this method deals with the detection of the most common cardiac arrhythmia called atrial fibrillation (AF) in noisy and non-clinical environment. The method begins with appropriate pre-processing of ECG signals in order to get the RR-interval and heart rate (HR) signals from them. A set of indirect features are computed from the original and the transformed versions of RR-interval and HR signals along with a set of direct features that are obtained from ECG signals themselves. In all, 47 features are computed and subsequently they are fed to an ensemble system of bagged decision trees for classifying the ECG recordings into four different classes. The proposed method has been evaluated with 2017 PhysioNet/CinC challenge hidden test dataset (phase II subset) and the final F1 score of 0.81 is obtained.

Ubiquitous Wearable Healthcare Monitoring System Architectural Design for Prevention, Detection, and Monitoring of Chronic Diseases

Chronic diseases have become the leading cause of death and disability worldwide. Major chronic diseases currently account for almost 60% of all deaths, and this contribution is expected to rise up to 73% by 2020. An integrated approach is needed for detection, prevention, and monitoring of these diseases. For better and specialized healthcare services, there is a need to develop a technology that should be fast, reliable, secure, accurate, and economical. In this chapter, the authors have presented an architectural design for wearable healthcare monitoring systems. The main motivation behind this architectural design is to improve the efficiency, accuracy, and generosity of WHMS. The architecture design divides the system into three layers or subsystems. The chapter provides a detailed description of subsystems, components, functionalities, requirements, and realization mechanisms along with their merits and demerits. The resolution of design issues like data fusion, data delivery, data processing, security, accuracy, and efficiency are the main points of this architecture design.

Early Diagnostics Model for Dengue Disease Using Decision Tree-Based Approaches

Classification schemes have been applied in the medical arena to explore patients' data and extract a predictive model.This model helps doctors to improve their prognosis, diagnosis, or treatment planning processes.The aim of this work is to utilize and compare different decision tree classifiers for early diagnosis of Dengue. Six approaches, mainly J48 tree, random tree, REP tree, SOM, logistic regression, and naïve Bayes, have been utilized to study real-world Dengue data collected from different hospitals in the Delhi, India region during 2015-2016. Standard statistical metrics are used to assess the efficiency of the proposed Dengue disease diagnostic system, and the outcomes showed that REP tree is best among these classifiers with 82.7% efficient in supplying an exact diagnosis.