Wearable Devices To Predict Anxiety Attacks

Electrical Electronics Engineering

Wearable devices have emerged as pivotal tools in modern healthcare, leveraging advanced sensor technologies to monitor physiological signals and predict potential health events, including anxiety attacks. These devices, equipped with biometric sensors such as heart rate monitors, galvanic skin response sensors, and accelerometers, offer real-time data collection and analysis, enabling the detection of subtle changes in physiological parameters associated with anxiety. By employing machine learning algorithms, these devices can recognize patterns indicative of an impending anxiety attack, alerting users in advance and empowering them to implement coping strategies or seek timely intervention. The integration of wearable technology in anxiety management not only facilitates personalized and proactive healthcare but also fosters a holistic approach to mental well-being, emphasizing early intervention and self-awareness to mitigate the impact of anxiety disorders.

ABSTRACT

Wearable devices (WD) are starting to increasingly be used for interventions to promote well-being by reducing anxiety attack (AA). Electrocardiogram (ECG) signal is one of the most commonly used biosignals for assessing the cardiovascular system as it significantly reflects the activity of the autonomic nervous system during emotional changes. Little is known about the accuracy of using ECG features for detecting AAs. Moreover, during our literature review, a limited number of studies were found that involve ECG collection using WD for promoting mental well-being. Thus, for the sake of validating the reliability of ECG features for detecting anxiety in wearable devices WD, we screened 1040 articles, and only 22 were considered for our study; specifically 6 on panic, 4 on post-traumatic stress, 4 on generalized anxiety, 3 on social, 3 on mixed, and 2 on obsessive-compulsive anxiety disorder articles. Most experimental studies had controversial results. Upon reviewing each of these papers, it became apparent that the use of ECG features for detecting different types of anxiety is controversial, and the use of ECG-WD is an emerging area of research, with limited evidence suggesting its reliability. This work is on using wearable devices to predict anxiety attack by providing a real time anxiety prediction using smartphone and cloud computing.

TABLE OF CONTENTS

COVER PAGE

TITLE PAGE

APPROVAL PAGE

DEDICATION

ACKNOWELDGEMENT

ABSTRACT

CHAPTER ONE

INTRODUCTION
BACKGROUND OF THE PROJECT
PROBLEM STATEMENT
AIM AND OBJECTIVE OF THE PROJECT
SIGNIFICANCE OF THE PROJECT
SCOPE OF THE PROJECT
LIMITATION OF THE STUDY
PROJECT ORGANISATION

CHAPTER TWO

LITERATURE REVIEW

OVERVIEW OF ANXIETY ATTACK
REVIEW OF ANXIETY ATTACK
TYPES OF ANXIETY DISORDERS
ANXIETY DISORDER SYMPTOMS
ANXIETY DISORDER CAUSES AND RISK FACTORS
OVERVIEW OF WEARABLE TECHNOLOGIES

CHAPTER THREE

MATERIALS AND METHODS

INTRODUCTION
HARDWARE DESIGN OF ECG PATCHES
ANDROID APP SOFTWARE DESIGN
ECG CLASSIFICATION ALGORITHM
CLOUD SOFTWARE DESIGN

CHAPTER FOUR

4.0 RESULT ANALYSIS

ALGORITHM PERFORMANCE
SYSTEM VERIFICATION

CHAPTER FIVE

CONCLUSIONS AND RECOMMENDATION

CONCLUSION
RECOMMENDATION
REFERENCE

CHAPTER ONE

1.0 INTRODUCTION

1.1 BACKGROUND OF THE STUDY

Anxiety attacks (AA) are the most common type of mental illness in the world, affecting 264 million worldwide according to World Health Organization [2017]. Every 10 years, there is an increase of AD by 14.9% [Vos, T, 2016]. Common mental illness such as anxiety and depression are increasing, especially in low- and middle-income countries [Friedrich, 2017]. These staggering statistics have motivated researchers to develop new and improved technologies to promote well-being and to reduce related morbidity, mortality, and health care costs. Moreover, the gold standard for assessing anxiety and other psychiatric disorders in children or adults is the clinical interview [Siegel, 2012]. Attaining an appointment with a mental health consultant is not an easy process that often takes time, and unfortunately by the time an appointment is reached with a psychologist a person’s life can be in danger.

The increase of using wearable devices (WD), such as electrocardiogram (ECG) smart watches and belts, along with mobile apps, have given new opportunities for WDs to influence our decisions and behaviors. Moreover, the recent advances in analyzing ECG signals for WDs for algorithm development [Elgendi, 2013], detecting R peaks [Elgendi, 2013], compression [Elgendi, 2018], and visualization [Elgendi, M. Eventogram, 2016] create a more reliable technology. Wearable devices WDs can be used at any time and in any environment, enabling objective mental status feedback based on the collected ECG data. In general, WD technologies have been already used in health interventions, providing promising results [Elgendi, M. Eventogram, 2011]. However, so far, these interventions have not been adopted for addressing ADs. Thus, integrating wearable ECG sensors (or other sensors) into our clothes, phones, and accessories could help users at risk and could lead to relatively positive health outcomes. Note that in the literature, to our knowledge, there are three measures for assessing autonomic nervous system functioning in emotion: cardiovascular, electrodermal, and respiratory measures [Kreibig, 2010]. However, the focus of this study is investigating the cardiovascular measures, specifically using ECG signals.

Several reviews investigated the correlation of ECG features with different types of AD; however, these studies were often limited to clinic-based measurement, or a healthcare setting. No review has examined the quality of the ECG signal, the measurement setting, the ECG sensor location, or the portability of the device. Moreover, many papers published ECG features that contradicted with other findings on the same topic [Pittig, 2013]. In other words, the ECG features used in some papers to detect the presence or absence of anxiety attack in subjects were reported as not used to detect the presence or absence of anxiety attack in other papers. For these reasons, limited research has been carried out to assess the validity of ECG and its efficacy and robustness in detecting anxiety attack, especially for real-time feedback.

In this work, a wearable ECG patch device was designed to collect single-lead ECG signals and to continuously send the collected ECG data to an Android smartphone via Bluetooth. The Android APP displayed the ECG waveforms in real time and transmitted every 30s ECG data to a cloud server. The cloud server used the improved ECG classification algorithm to predict anxiety attack and pushed the ECG data and classification results to the web browser of a doctor when anxiety attack was detected. Finally, the Android APP displayed the doctor’s diagnosis.

1.2 PROBLEM STATEMENT

Anxiety attacks are group of mental illnesses that cause constant and overwhelming anxiety and fear. The excessive anxiety can make you avoid work, school, family get-togethers, and other social situations that might trigger or worsen your symptoms. Anxiety attacks come in different form such Panic, fear, and uneasiness, Sleep problem, not being able to stay calm and still, Cold, sweaty, numb, or tingling hands or feet, Shortness of breath, breathing faster and more quickly than normal. According to WHO (2017), anxiety attack (AA) are the most common type of mental illness in the world, affecting 264 million worldwide. When anxiety attack is not well managed it can lead to other sicknesses which can even cause heart attack which leads to sudden death. This study was carried out to predict anxiety attack in a victim using wearable devices.

1.3 AIM AND OBJECTIVES OF THE STUDY

The main aim of this work is to predict oncoming anxiety attacks using wearable devices. The objectives of this work are:

To save life
To highlight the electrocardiogram features and their challenges,

To predict anxiety attack using electrocardiogram (ECG) effectively with wearable devices

To provide a real time anxiety prediction using smartphone and cloud computing.

1.4 SIGNIFICANCE OF THE STUDY

This research work will throw more light on the techniques for controlling anxiety attack with improved technologies in other to promote well-being and to reduce related morbidity, mortality, and health care costs.

1.5 LIMITATION OF STUDY

As we all know that no human effort to achieve a set of goals goes without difficulties, certain constraints were encountered in the course of carrying out this project and they are as follows:-

Difficulty in information collection: I found it too difficult in laying hands of useful information regarding this work and this course me to visit different libraries and internet for solution.
Financial Constraint: Insufficient fund tends to impede the efficiency of the researcher in sourcing for the relevant materials, literature or information and in the process of data collection (internet, questionnaire and interview).

Time Constraint: The researcher will simultaneously engage in this study with other academic work. This consequently will cut down on the time devoted for the research work.

1.6 SCOPE OF THE STUDY

An anxiety attack usually involves a fear of some specific occurrence or problem that could happen. Symptoms include worry, restlessness, and possibly physical symptoms, such as changes in heart rate. There are different types of wearable devices foe medical use. This work is on a real-time telemonitoring systems based on cloud computing for healthcare or for detecting heart diseases. The cloud computing technology is a powerful tool to provide remote data transmission, complex computation, big data processing, and instant diagnosis. However, these cloud based telemonitoring systems still lack an algorithm for automatic AF detection.

1.7 PROJECT ORGANISATION

The work is organized as follows: chapter one discuses the introductory part of the work, chapter two presents the literature review of the study, chapter three describes the methods applied, chapter four discusses the results of the work, chapter five summarizes the research outcomes and the recommendations.