Data Analytics for Pandemics

A COVID-19 Case Study

Gitanjali Rahul Shinde, Asmita Balasaheb Kalamkar, Parikshit N. Mahalle, Nilanjan Dey

• Publisher: CRC Press
• Year: 2020
• Print ISBN: 9780367558468
• eBook ISBN: 9781000204452
• Edition: 1
• Topic: Computer Science
• Subtopic: Computer Science General
• Index: Computer Science

Epidemic trend analysis, timeline progression, prediction, and recommendation are critical for initiating effective public health control strategies, and AI and data analytics play an important role in epidemiology, diagnostic, and clinical fronts. The focus of this book is data analytics for COVID-19, which includes an overview of COVID-19 in terms of epidemic/pandemic, data processing and knowledge extraction. Data sources, storage and platforms are discussed along with discussions on data models, their performance, different big data techniques, tools and technologies. This book also addresses the challenges in applying analytics to pandemic scenarios, case studies and control strategies. Aimed at Data Analysts, Epidemiologists and associated researchers, this book:

• 
  
  

• discusses challenges of AI model for big data analytics in pandemic scenarios;

• 
  
  

• explains how different big data analytics techniques can be implemented;

• 
  
  

• provides a set of recommendations to minimize infection rate of COVID-19;

• 
  
  

• summarizes various techniques of data processing and knowledge extraction;

• 
  
  

• enables users to understand big data analytics techniques required for prediction purposes.

1
COVID-19 Outbreak

1.1 Introduction

The key to understanding a pandemic starts with an understanding of the disease itself and the progression of the natural course of the disease. The word “disease” is defined as the state that negatively affects the body of a living person, plant, or animal. A disease affects the body because of a pathogenic infection. The natural course of the disease starts before the onset of the infection, after which it progresses through the pre-symptomatic stage. The last stage is the clinical phase. In the clinical phase, a patient receives the prognosis of the disease. After successful treatment of the disease, the patient enters into the remission stage. Remission refers to a decrease in the symptoms or a complete disappearance of the disease. The patient needs to strictly follow instructions given by the doctor during the remission stage. This will ensure that the disease does not recur. If treatment is not successful, the patient can die or be chronically disabled. The following are some important terms that are used to represent the disease state:

1. (i) Case-fatality rate: It is defined as the ratio of the number of patients who die due to the disease to the number of people affected by it.
2. (ii) Observed survival rate: It is the prediction of the probability of survival.
3. (iii) Relative survival rate: It is defined as the percentage of the observed survival to the survival rate expectation.

Diseases are mainly categorized into two types:

1. (i) Congenital diseases
2. (ii) Acquired diseases

Congenital diseases exist in the body right from birth. These diseases are generally activated through genetic disorders, environmental factors, or a combination of both. These diseases are generally hereditary, i.e. passed on through generations, for example, hearing conditions and Down syndrome. In contrast to the former, acquired diseases spread through living organisms. These are not hereditary.

The acquired disease category is further classified into two types:

1. (i) Infectious diseases
2. (ii) Non-infectious diseases

Infectious diseases are induced by pathogens or viruses. They are also called communicable diseases. As the name suggests, these diseases are infectious. It means that if one person has contracted the infectious disease then the disease can be passed on to another person through air, food, water, touch (physical contact), etc. SARS and SARS COVID-19 are examples of infectious diseases.

Similarly, as the name suggests, non-infectious diseases do not occur due to any kind of infection. It means that a person with a non-infectious disease will not be able to spread the disease to a healthy person. Diseases such as cancer and auto-immune disorders are examples of non-infectious diseases.

Infectious disease can affect a healthy person in two ways.

1. (i) Direct transmission
2. (ii) Indirect transmission

When the pathogens travel from a patient to a healthy person without any middle carrier, then the transmission is referred to as direct transmission. Direct transmission can happen in the following ways:

• Coming in contact with the infected person.
• Via droplet infection (coughing, sneezing, and spitting).
• Coming in contact with the soil.

Animal bites are also one of the causes of direct transmission.

Whenever there is a reservoir of infection that can transmit the disease from a patient to a healthy person with a middle agent, then that transmission is known as indirect transmission. Indirect transmission can happen in the following ways.

• If pathogens are transmitted through food, water, etc., it is known as vehicle-borne disease.
• If pathogens are transmitted through the air, then it is known as airborne disease.
• If pathogens are transmitted through contaminated items like clothing, utensils, books, etc., it is known as fomite-borne disease.

After the diagnosis of the disease comes the most important part: the treatment. Treatment generally consists of targeting the biochemical reactions occurring due to pathogens. There are two ways to stop that reaction so that the infection will not spread:

1. (i) Prevention
2. (ii) Cure

Through prevention, symptoms of the infection can be reduced using painkillers so that patients can be at ease. Preventive measures also include immunization and vaccination. Through cure, particular drugs are used to kill the pathogen [1].

1.2 Epidemic and Pandemic Overview

1.2.1 Stages of Disease

Before studying the latest pandemic, it is very important to study basic terminologies associated with the pattern of disease spread. A diagrammatical overview of stages of the disease is depicted in Figure 1.1.

Figure 1.1 Stages of the disease.

1. (i) Sporadic
   When the occurrence of the disease is not regular and is infrequent, it is termed as sporadic.
2. (ii) Endemic
   When the presence of the disease is constant in a particular geographical area, it is known as endemic. Endemic turns into a hyperendemic situation when a high level of disease occurrence is observed.
3. (iii) Epidemic
   When there is a sudden rise in the number of patients with the same disease and within a particular area, it is termed as an epidemic.
4. (iv) Pandemic
   When epidemics affect larger geographical areas (including multiple countries and continents), it is known as a pandemic.

A disease takes the form of an epidemic when the following two conditions are met. First is when several people are affected by an illness/disease that has a similar nature of the disease and the same root cause, and the second is when the number of infected people rapidly increase over a period. When the epidemic crosses local boundaries and covers a wide geological area at the same time, it becomes a pandemic. A disease is listed under the category of pandemic because of its infectious nature. A pandemic does not give any information about the severity and impact of the disease. It merely states the fact that people across a wide geographical area are being infected with the disease.

One more term that is majorly used while studying infectious diseases is “outbreak.” Outbreak happens when a sudden rise in the number of patients is observed. Outbreaks can last a few days, weeks, or months. A pandemic is also sometimes referred to as an outbreak.

1.2.2 Pandemic Phases

When the World Health Organization (WHO) declares a pandemic alert for a disease, it follows six different phases.

• Phase 1: A pathogen/virus that exists in animals has not caused any kind of infection to humans.
• Phase 2: A pathogen/virus has infected humans.
• Phase 3: Small groups of people or random persons are infected with the virus.
• Phase 4: Human to human transmission is observed due to the outbreak at the community level.
• Phase 5: The disease has spread in multiple WHO regions.
• Phase 6: There is an outbreak of the disease in one or more regions different from the ones enlisted in Phase 5 [2].

1.2.2.1 Pandemic Risk Factors

A combination of spread risk and spark risk plays a primary role in pandemic risks. The spark risk occurs due to the transmission of the pathogen from animals to humans. These animals can be domestic animals or wild animals. The spread of the disease due to domestic animals is generally confined to densely populated areas. The key drivers of spark risks are live animal markets, wildlife reservoirs, etc. [3, 4]. The spark risk is usually followed by the spread risk. As the name suggests, it concerns the transmission of the virus along with the genetic adaptation of the virus. The spread risk is influe...

Table of contents

• Cover
• Half-Title
• Series
• Title
• Copyright
• Contents
• Preface
• Acknowledgment
• Authors
• 1 COVID-19 Outbreak
• 2 Data Processing and Knowledge Extraction
• 3 Big Data Analytics for COVID-19
• 4 Mitigation Strategies and Recommendations
• Index