CHAPTER TWO

LITERATURE REVIEW

1.1 General Overview

This study developed a good machine learning-based method. With the use of a wide variety of

data sources, such as genetic information, medical imaging, electronic health records, and

lifestyle variables, the initiative aims to overcome the shortcomings of conventional diagnostic

techniques. In order to give context for the study on machine learning applications in heart

disease diagnosis and to guide the creation of a strong methodology by incorporating lessons

from previous studies, the review's main goal is to present a thorough overview of the body of

research. This chapter consists of:

i. General Overview

ii. Conceptual Review

iii. Theoretical Review which describes the theories and systems associated with the project

and

iv. Empirical Review that shows related works to the project

1.2 Conceptual Review

This study's conceptual overview explores the underlying theories, fundamental ideas, and

pertinent frameworks that influence the investigation of machine learning applications in the

diagnosis of heart disease. This review seeks to provide a solid conceptual framework for the

research by clarifying these fundamental components and offering insight into the theoretical

environment that influences and directs the investigation.

2.2.1 Diseases

The human body's delicate and intricate balance is what determines health. In general, diseases

are upsets of this equilibrium that frequently impair the regular operation of systems and organs.

Maintaining a comprehensive perspective on wellbeing is essential.

A particular class of disorders includes problems with the cardiovascular system. The heart and

blood arteries are part of this complex network, which is essential for the body's transportation of

hormones, nutrients, and oxygen.

It's important to take into account the variables that may contribute to the development of

illnesses while talking about them. Our health outcomes are shaped by a combination of genetic

predispositions, environmental factors, and lifestyle choices.

Now, let's discuss a particular component without giving it a name: a heart-related ailment. This

organ is the cardiovascular system's main workhorse, pumping blood nonstop so that each and

every cell in the body gets fed. Any condition that affects the heart can have a significant impact

on general health.

These disorders are linked to a number of risk factors, such as physical activity, stress levels,

dietary practices, and underlying medical problems. Preventing the beginning or advancement of

such health issues is mostly dependent on routine examinations and sustaining a healthy lifestyle.

When it comes to cardiovascular health, education and awareness are powerful instruments.

Maintaining a strong cardiovascular system may be greatly aided by realizing the significance of

a balanced diet, consistent exercise, and stress management.

1.2.1 History of Diseases

The story of illnesses throughout history, heart disease included, is weaved together with the

threads of changing society norms, medical advancements, and changing lifestyles. Venturing

into the past, we observe a journey characterized by the confluence of human perseverance,

culture, and science.

The intricate workings of the circulatory system were mysterious to the ancient world. Ancient

societies held the heart in high regard as the home of the soul, and it was more frequently linked

to philosophical ideas than to actual scientific understanding. Our understanding of the human

body grew over the centuries.

Scientific inquiry had a boom during the Renaissance, when explorers such as Leonardo da Vinci

dissected human corpses and established the basis for our understanding of anatomy. But the

19th and 20th centuries saw the real advances in our understanding of cardiac disorders.

Technological developments in medicine, such as René Laennec's 1816 creation of the

stethoscope, made it possible for doctors to identify irregular heartbeats, which led to the

diagnosis of cardiac disorders. Our knowledge was further expanded by the groundbreaking

work of people like William Harvey, who clarified the circulatory system, and the identification

of blood circulation mechanics.

In the modern day, heart-related conditions, such as cardiovascular disorders, have emerged as

major worldwide health issues. An concerning increase in heart-related illnesses has been

attributed to sedentary lifestyles, rapid urbanization, and dietary changes. The development of

life-saving procedures and drugs, as well as the introduction of cardiac catheterization,

demonstrate our unwavering quest to defeat these illnesses.

We stand on the shoulders of centuries of medical advancement today as we traverse the

challenging terrain of cardiovascular health. The history of heart disease serves as a wake-up call

and a monument to human resiliency. It exhorts us to take on the difficulties of our contemporary

lifestyle, promote preventative measures, and keep looking for novel remedies to protect the

beating core of our existence – our heart.

1.2.2 Heart Disease (Cardiovascular disease)

Cardiovascular diseases (CVDs) encompass a range of conditions affecting the heart and blood

vessels. These conditions pose a significant global health burden, contributing to morbidity and

mortality worldwide. Cardiovascular diseases encompass a range of conditions affecting the

heart and blood vessels. Here are key cardiovascular diseases in the context of this project:

1. Coronary Artery Disease (CAD): CAD is a common cardiovascular disease characterized

by the accumulation of plaque in the coronary arteries, leading to reduced blood flow to

the heart. Understanding risk factors, symptoms, and diagnostic methods for CAD is

crucial.

2. Heart Failure: Heart failure occurs when the heart is unable to pump blood effectively,

leading to inadequate oxygen supply to the body. Explore the different types of heart

failure, causes, symptoms, and approaches to diagnosis and management.

3. Arrhythmias: Arrhythmias involve irregular heartbeats, which can be too fast, too slow,

or erratic. Investigate various types of arrhythmias, their impact on cardiovascular health,

and the role of machine learning in detecting and predicting arrhythmias.

4. Valvular Diseases: Valvular diseases affect the heart valves, impairing the flow of blood.

Explore conditions such as aortic stenosis, mitral regurgitation, and their clinical

manifestations. Understand the diagnostic methods and treatment options.

5. Hypertension (High Blood Pressure): Hypertension is a prevalent cardiovascular risk

factor characterized by elevated blood pressure. Explore the impact of hypertension on

heart health, its role in the development of other cardiovascular diseases, and strategies

for management.

6. Peripheral Artery Disease (PAD): PAD involves the narrowing of arteries outside the

heart, typically in the legs. Understand the symptoms, risk factors, and diagnostic

methods for PAD, and explore how machine learning can contribute to early detection.

7. Cardiomyopathies: Cardiomyopathies are conditions that affect the heart muscle, leading

to structural and functional abnormalities. Explore different types of cardiomyopathies,

their causes, and the implications for heart disease detection.

8. Myocardial Infarction (Heart Attack): Myocardial infarction occurs when blood flow to a

part of the heart muscle is blocked, leading to tissue damage. Understand the risk factors,

symptoms, diagnostic methods, and the importance of early intervention in heart attacks.

It is important to note that symptoms can vary among individuals, and some people may

experience atypical symptoms or even no symptoms at all. Additionally, women may

sometimes have different heart attack symptoms than men. But here's a consolidated list of

common symptoms associated with various cardiovascular diseases:

  Chest pain or discomfort (angina)

 Shortness of breath

 Fatigue

 Rapid or irregular heartbeat

 Fluid retention, leading to swelling in the legs, ankles, or abdomen

 Dizziness or light-headedness

 Leg pain or cramping, particularly during physical activity (claudication)

 Nausea or vomiting

These symptoms encompass a range of cardiovascular conditions and should prompt

individuals to seek prompt medical attention for proper evaluation and diagnosis.

1.2.3 Importance of detecting Heart Diseases

Early detection of heart disease holds immense importance across various dimensions,

profoundly influencing patient outcomes and healthcare systems. At its core, timely

identification serves as a linchpin for a cascade of benefits, ranging from preventive measures

and enhanced treatment efficacy to improved quality of life and substantial economic

considerations.

One of the paramount aspects is the prevention of complications associated with heart disease.

Early detection acts as a crucial shield against life-threatening events such as heart attacks, heart

failure, and strokes, averting the progression to severe and potentially irreversible stages. The

proactive identification of risk factors enables healthcare providers to implement targeted

preventive measures, mitigating the trajectory of the disease before it inflicts debilitating

complications.

In the realm of treatment, the significance of early detection is evident in its ability to optimize

therapeutic interventions. Whether through medications, lifestyle modifications, or surgical

procedures, initiating these measures at the early stages of heart disease proves more efficacious

in managing the condition and forestalling further damage to the heart. The ripple effect extends

to an improved quality of life for individuals as symptoms are managed, cardiac function is

optimized, and risk factors are addressed comprehensively.

Economic considerations underscore the importance of early detection, with a direct impact on

healthcare costs. Preventing severe complications that necessitate extensive medical procedures

or hospitalizations translates to a more cost-effective healthcare paradigm. Early interventions,

being generally more affordable than treating advanced stages of heart disease, contribute to a

sustainable and efficient allocation of healthcare resources.

Moreover, the concept of tailored treatment approaches comes to the forefront. Early detection

allows healthcare professionals to customize treatment plans based on specific types of heart

disease and individual variations. This personalized approach takes into account genetic

predispositions, lifestyle choices, and coexisting conditions, ensuring that interventions are

precisely calibrated for maximum efficacy.

The optimization of resource allocation is another key facet of the importance of early detection.

By swiftly identifying cases and prioritizing interventions based on severity and urgency,

healthcare systems can ensure that critical resources, including emergency services and
specialized treatments, are directed where they are most needed. This strategic allocation fosters

efficiency and responsiveness within healthcare delivery.

The empowerment of individuals through education is an intrinsic benefit of early detection.

Armed with knowledge about their heart health status, individuals can make informed decisions

regarding lifestyle choices, medication adherence, and active participation in their own care. This

empowerment nurtures a proactive approach to heart health, creating a symbiotic partnership

between patients and healthcare providers.

Ultimately, the reduction in mortality rates stands as the pinnacle of the importance of early

detection. Swift identification and management of cardiovascular issues directly contribute to

increased life expectancy and a higher likelihood of survival. It is through the collective

realization of these multifaceted benefits that the imperative of early detection emerges as a

cornerstone in the pursuit of cardiovascular health and overall well-being.

1.2.4 Heart diseases among the Elderly

Heart diseases among the elderly constitute a significant and complex health challenge, as aging

is intricately linked to an increased susceptibility to cardiovascular conditions. The aging process

itself brings about physiological changes that can impact the cardiovascular system, including

arterial stiffness, diminished elasticity of blood vessels, and alterations in cardiac structure and

function. These age-related changes often contribute to a higher prevalence of conditions such as

coronary artery disease, heart failure, and atrial fibrillation among the elderly population.

Furthermore, the aging heart may experience a decline in its ability to respond to stress and adapt

to fluctuations in demand, making it more susceptible to the impact of risk factors like

hypertension and high cholesterol. Beyond these intrinsic factors, lifestyle choices accumulated

over a lifetime, such as dietary habits, physical activity levels, and tobacco use, play a pivotal
role in shaping cardiovascular health in later years. The elderly also commonly contend with

comorbidities like diabetes and arthritis, which can further complicate the cardiovascular

landscape. The interplay of these factors necessitates a nuanced and holistic approach to

managing heart diseases among the elderly, encompassing tailored interventions, regular health

monitoring, and strategies that account for the unique physiological and lifestyle considerations

of this demographic. As the global population continues to age, understanding and addressing the

intricate dynamics of heart diseases in the elderly becomes paramount for healthcare systems.

Comprehensive geriatric assessments, including cardiovascular risk profiling and management,

become integral components of healthcare for the elderly. Moreover, fostering awareness about

heart-healthy behaviors and facilitating access to preventive care can empower the elderly to take

an active role in maintaining their cardiovascular well-being. Recognizing the diverse nature of

cardiovascular conditions in the elderly, from the subtle manifestations to acute events,

underscores the need for personalized and patient-centered care. Advances in medical research

and technology continue to provide new avenues for understanding and addressing heart diseases

in the elderly, emphasizing the importance of ongoing scientific exploration and innovation.

Ultimately, navigating the complexities of cardiovascular health among the elderly requires a

collaborative effort involving healthcare professionals, caregivers, and the elderly themselves to

optimize preventive strategies, enhance quality of life, and promote healthy aging.

1.2.5 Heart diseases among other Groups

Heart diseases manifest with varying nuances across different demographic groups, presenting

unique challenges and considerations. Among men, there exists a historical recognition of a

higher susceptibility to heart diseases, often experiencing cardiac issues at an earlier age than

their female counterparts. This gender disparity is linked to factors such as hormonal differences
and varied lifestyle patterns. Postmenopausal women, on the other hand, face an altered

cardiovascular landscape due to hormonal changes, highlighting the critical role of estrogen in

heart health. Individuals with a family history of heart diseases navigate a genetic terrain that

may predispose them to cardiovascular conditions, emphasizing the importance of early

screening and proactive management. Those with high blood pressure contend with a heightened

risk, as hypertension is a leading contributor to heart diseases. Similarly, individuals with

elevated cholesterol levels, particularly LDL cholesterol, confront an increased likelihood of

atherosclerosis and coronary artery disease. Diabetes amplifies cardiovascular risks, showcasing

the intricate interplay between metabolic health and heart health. Smoking, a prevalent risk

factor, inflicts damage on blood vessels and heightens the risk of heart attacks. Inactive or

sedentary individuals grapple with obesity and related risk factors, underscoring the pivotal role

of physical activity in cardiovascular well-being. Poor dietary habits further contribute to the

multifaceted landscape of heart diseases, with excessive intake of saturated fats, salt, and sugars

influencing cardiovascular risk. Recognizing these diverse risk profiles necessitates targeted and

tailored approaches to prevention, intervention, and education within each demographic group,

ensuring a comprehensive strategy to mitigate the impact of heart diseases across the spectrum of

age, gender, and lifestyle.

Moreover, the distinctive cardiovascular challenges faced by each demographic group reflect the

intricate interplay of biological, environmental, and lifestyle factors. For men, the traditional

association with higher risk underscores the need for early awareness campaigns and routine

screenings to catch potential issues before they escalate. Postmenopausal women, with hormonal

shifts altering their cardiovascular dynamics, benefit from specialized care that considers the

unique challenges and vulnerabilities associated with this life stage. Those with a family history
are encouraged to adopt proactive health measures, given the genetic predisposition that may

heighten their susceptibility to heart diseases. Managing high blood pressure becomes not only a

health priority but also a preventative measure, as hypertension serves as a gateway to various

cardiovascular complications.

Individuals grappling with high cholesterol face a nuanced journey, with a focus on dietary

modifications, medication adherence, and regular monitoring to mitigate the risk of

atherosclerosis and related issues. The intricate relationship between diabetes and heart diseases

demands a comprehensive approach, acknowledging the bidirectional influence between

metabolic health and cardiovascular outcomes. Smokers, faced with a higher incidence of heart

attacks, benefit not only from smoking cessation interventions but also from targeted

cardiovascular screenings to assess and address potential damage.

Inactivity and sedentary lifestyles, pervasive concerns in modern society, contribute significantly

to obesity and cardiovascular risks. Tailored exercise regimens, coupled with lifestyle

modifications, emerge as pivotal components in the prevention and management of heart

diseases for this demographic. Similarly, individuals with poor dietary habits find empowerment

through nutritional education, advocating for heart-healthy choices and emphasizing the impact

of diet on long-term cardiovascular health.

This intricate tapestry of risk factors and considerations mandates a multifaceted and inclusive

approach to cardiovascular health. From targeted educational initiatives and preventive measures

to personalized treatment strategies, addressing the diverse needs of each demographic group is

imperative for comprehensive and effective heart disease management. As scientific

advancements continue to shed light on the specificities within these groups, the evolving
landscape of cardiovascular care strives for a more precise, nuanced, and patient-centered

approach to safeguarding heart health across diverse populations.

Furthermore, the intersectionality of risk factors necessitates a holistic understanding of how

various elements converge within each demographic group. For instance, individuals with a

combination of risk factors, such as those with both diabetes and a family history of heart

diseases, require integrated healthcare strategies that acknowledge the synergistic impact of these

influences. It underscores the importance of personalized medicine, where treatment plans are

tailored to the unique constellation of factors shaping an individual's cardiovascular profile.

Addressing heart diseases among these diverse groups also requires a societal commitment to

health equity. Disparities in access to healthcare, preventive measures, and educational resources

can exacerbate the impact of cardiovascular diseases, particularly in vulnerable populations.

Bridging these gaps involves not only advancing medical interventions but also fostering

environments that promote healthy living, encourage regular screenings, and provide equal

opportunities for cardiovascular care.

In conclusion, the landscape of heart diseases among different demographic groups is intricate

and multifaceted. The evolving understanding of genetic, environmental, and lifestyle factors

brings forth a new era in cardiovascular care that goes beyond a one-size-fits-all approach. As we

navigate this complex terrain, continuous research, education, and advocacy become

instrumental in shaping a future where heart health is safeguarded for individuals across age,

gender, and diverse lifestyles. Through collaborative efforts in healthcare, public health

initiatives, and individual empowerment, we embark on a collective journey towards a heart-

healthy society where everyone has the opportunity to thrive.

1.2.6 Side effects of Heart Diseases

Heart diseases, encompassing a range of conditions affecting the cardiovascular system, can

manifest various side effects that impact overall health and well-being. Let's explore some

common side effects associated with heart diseases and delve into their implications:

1. Fatigue:

Fatigue is a prevalent side effect of heart diseases and is often a result of the heart's

compromised ability to pump blood effectively. When the heart is weakened or

encounters increased resistance in the blood vessels, the body may not receive an

adequate supply of oxygen and nutrients, leading to fatigue. This can significantly impact

daily activities, reducing overall quality of life.

2. Shortness of Breath:

Heart diseases can lead to a condition known as heart failure, where the heart's pumping

capacity is impaired. As a result, fluid may accumulate in the lungs, causing shortness of

breath. This symptom is particularly noticeable during physical exertion or even at rest,

depending on the severity of the heart condition.

3. Edema (Swelling):

Swelling, especially in the legs, ankles, or abdomen, is a common side effect of heart

diseases. It occurs when the heart is unable to effectively pump blood, causing fluid to

accumulate in the body's tissues. Edema is often a sign of heart failure and can contribute

to discomfort and reduced mobility.

4. Chest Pain (Angina):

 Angina is chest pain or discomfort that occurs when the heart muscle doesn't receive

enough blood and oxygen. It is a common side effect of coronary artery disease, where

the arteries supplying blood to the heart become narrowed or blocked. Angina can vary in

intensity and may be triggered by physical exertion or stress.

5. Irregular Heartbeat (Arrhythmias):

Heart diseases can lead to irregular heartbeats or arrhythmias, disrupting the normal

rhythm of the heart. This can manifest as palpitations, fluttering sensations, or a racing

heart. Arrhythmias can be associated with various heart conditions and may increase the

risk of more severe cardiac events.

6. Dizziness and Fainting:

Insufficient blood flow to the brain, often resulting from heart diseases, can lead to

dizziness or fainting. When the heart's pumping capacity is compromised, the brain may

not receive an adequate supply of oxygen, causing these symptoms. Fainting episodes can

pose significant risks, especially if they occur unexpectedly.

7. Cognitive Impairment:

In severe cases, chronic inadequate blood flow to the brain due to heart diseases may

contribute to cognitive impairment. This can manifest as difficulties in memory,

concentration, and overall cognitive function. The brain's dependence on a consistent

oxygen supply makes it vulnerable to the effects of impaired cardiovascular health.

8. Increased Risk of Blood Clots and Stroke:

Certain heart conditions, such as atrial fibrillation, can disrupt the normal blood flow,

leading to the formation of blood clots. These clots can travel to the brain, causing a
 stroke. The increased risk of clot formation underscores the systemic consequences of

heart diseases beyond the cardiovascular system.

9. Sleep Disturbances:

Heart diseases can contribute to sleep disturbances, including insomnia or frequent

awakenings during the night. Conditions such as heart failure may cause discomfort and

difficulty breathing when lying down, leading to disrupted sleep patterns. Additionally,

the overall stress and anxiety associated with managing heart conditions can impact sleep

quality.

10. Reduced Exercise Tolerance

Individuals with heart diseases often experience a decline in exercise tolerance. The

compromised ability of the heart to pump blood efficiently can limit physical activities.

This reduction in exercise capacity can lead to a sedentary lifestyle, exacerbating

cardiovascular risks and further impacting overall health.

Understanding these side effects is crucial for early detection and management of heart

diseases. Regular medical check-ups, monitoring of symptoms, and lifestyle modifications

play pivotal roles in mitigating these side effects and improving the overall prognosis for

individuals living with heart conditions. It's essential to recognize that the side effects of

heart diseases can vary depending on the specific condition, its severity, and individual

factors. Addressing these side effects involves a comprehensive approach that includes

medical management, lifestyle modifications, and ongoing monitoring to enhance overall

well-being and quality of life.

1.2.7 Artificial Intelligence

In contrast to the natural intelligence exhibited by people and other animals, artificial

intelligence, also known as machine intelligence, is intelligence demonstrated by machines. It is

intended to do a variety of tasks, including speech recognition, learning, planning, and problem-

solving. Robotics is the study of the relationship between perception and action, thus if that

relationship is to be intelligent, Artificial Intelligence must play a major part in robotics. The

fundamental issues of what knowledge is necessary for any part of thinking, how that knowledge

should be represented, and how that knowledge should be applied are addressed by artificial

intelligence. By requiring AI to engage with actual items in the real world, robotics puts AI to

the test. (SALEH, 2019)

Branches of artificial intelligence

1. Computer vision: The goal of computer vision, one of the most well-known disciplines of

artificial intelligence at the moment, is to provide methods that let computers recognize and

comprehend digital images and videos. Computers can recognize objects, faces, people, animals,

and other features in photos by applying machine learning models to them. Computers can learn

to discriminate between different images by feeding a model with adequate data. Algorithmic

models assist computers in teaching themselves about the contexts of visual input. Along with a

model, a conventional neural network breaks down images into pixels and assigns tags or labels.

After performing convolutions, which is a mathematical process on two functions to create a

third function, the neural network utilizes the labels to generate predictions about what it sees.

(GARANHEL, 2023)Computer vision has applications across industries, such as:

 1. Object tracking is one example of how computer vision is used in several sectors. tracking

or after objects that have been found.

 categorization of images. An image is categorized and appropriately assigned to one of

several classes.

 identification of faces. Smartphones with face unlock identify users by mapping and

matching facial traits.

2. FUZZY LOGIC: Fuzzy logic is a method for resolving questions or assertions that can be true

or untrue. This approach mimics human decision-making by taking into account all viable

options between digital values of "yes" and "no." In plain terms, it gauges how accurate a

hypothesis is. This area of artificial intelligence is used to reason about ambiguous subjects. It's

an easy and adaptable way to use machine learning techniques and rationally mimic human

cognition. (GARANHEL, 2023)The architecture of fuzzy logic is divided into four sections:

 foundation rules. has every guideline and if-then condition.

 Fuzzification. helps with input conversion.

 engine for inference. determines the degree to which fuzzy inputs and rules are compatible.

 Defuzzification. Fuzzy sets are transformed into crisp values.

3. ROBOTS: Robots are programmed robots that can perform intricate chains of operations

autonomously. They can be managed by people using external devices or by embedded control

systems. Humans use robots to assist in laborious and repetitive activities. Particularly, robots
with AI capabilities can support space research by organizations like NASA. The most recent

and well-known examples of robotic evolution are humanoid robots. Artificial intelligence and

neural networks are used to power Sophia, a robot created by Hanson Robotics. She can engage

with people and understands their emotions, gestures, and recognition of human faces.

Manufacturing, healthcare, retail, and other sectors are among the many industries where

robotics is frequently used in daily life. (GARANHEL, 2023)

1.2.8 Expert System

Expert systems are designed to provide "expert quality" performance in handling problems in a

specific domain. In this chapter, we look at the structure of expert systems focusing on the

classical rule-based system. We then look at the process of developing an expert system.

Definition

Expert systems are computer applications that embody some non-algorithmic expertise for

solving certain types of problems. For example, expert systems are used in diagnostic

applications servicing both people and machinery. They also play chess, make financial

planning decisions, configure computers, monitor real-time systems, underwrite insurance

policies, and perform many other services which previously required human expertise. (Merritt,

2018).

Expert Systems seek to embed the knowledge of a human expert (for example a highly skilled

physician or lawyer) in a computerized consulting service. They are more efficient because

expert systems do have the same limitations that humans have such as exhaustion and human

error and also, they preserve and disseminate the knowledge in a simple and structured manner

so that it can be useful to others.

An expert system provides advice derived from a knowledge base, using a reasoning process

embedded in its inference engine, the 'thinking' part of the system. The knowledge base and the

inference engine are components of the expert system. (BrainKart., 2018)

Figure 2.1 Expert system components and human features

Expert systems have several major system components and interface with individuals in various

roles. These are illustrated in Figure 2.1 above. The major components are:

 Knowledge base - a declarative representation of the expertise, often in IF-THEN rules.

 Working storage - the data that is specific to a problem being solved.

 Inference engine - the code at the core of the system, which derives recommendations

from, the knowledge base and problem-specific data in working storage.

  User interface - the code that controls the dialog between the user and the system.

The inference engine uses one of two methods for acquiring information from the knowledge

base:

1. Forward chaining reads and processes a set of facts to make a logical prediction about

what will happen next. An example of forward chaining would be making predictions

about the movement of the stock market.

2. Backward chaining reads and processes a set of facts to reach a logical conclusion about

why something happened. An example of backward chaining would be examining a set

of symptoms to reach a medical diagnosis.

To understand expert system design, it is also necessary to understand the major roles of

Individuals who interact with the system. These are:

 Domain expert - the individual or individuals who currently are experts in solving the

 problems the system is intended to solve;

 Knowledge engineer - the individual who encodes the expert's knowledge in a declarative

 form that can be used by the expert system;

 User- the individual who will be consulting with the system to get advice that would have

been provided by the domain expert.

 Figure 2.2 Structure of An Expert System
The inference engine is not explicitly shown; it however controls the flow of information around

the above modules, retrieving appropriate facts and rules during the reasoning process.

1.2.9 Operation of System

There are three modes to this:

 Knowledge acquisition

 Consultation

 Explanation
KNOWLEDGE ACQUISITION

The designer of the system must liaise with people to gain knowledge and these people must be

acknowledged experts in the appropriate area of activity, for example, physicians, lawyers, or

investment analysts. The knowledge engineer acts as an intermediary between the human expert

and the expert system.

Typical of the information that must be gathered is vocabulary or jargon, general concepts, and

facts, problems that commonly arise, the solutions to the problems that occur, and skills for

solving particular problems. This process of picking the brain of an expert is a specialized form

of data capture and makes use of interview techniques.

Having acquired the information, the knowledge engineer is also responsible for the self-

consistency of the data and several specific tests have to be performed to ensure that the

conclusions reached are sensible.

The knowledge engineer may use specialized software systems to help monitor the performance

of an expert system under development. When the human expert who is the source of the

knowledge spots an error in the program's performance, in either the program's conclusions or its

line of reasoning, such a system assists in finding the source of the error in the database by

explaining the program's conclusions, retracing the reasoning steps until the faulty (or missing)

rule is identified. It may then assist in knowledge acquisition by modifying faulty rules or adding

new rules to the database.

CONSULTATION

The system is in this mode when a user is interacting with it using the user interface. The user

interacts by entering data in the native language (e.g., English Language) and the system

responds using a backward chaining (deductive reasoning) process to derive an answer to the

questions posed by. the user. This process is usually done using the information from the

knowledge base. The information is processed using the inference engine this is usually done

using IF-ELSE statements

As explained earlier the user may during this time be asked for information that can be used to

support the system's hypothesis, with appropriate backtracking if contradictory evidence to this

hypothesis is found.

EXPLANATION

This mode allows the system to explain its conclusions and its reasoning process. This ability

comes from the AND/OR trees created during the deduction process. As a result, most expert

systems can answer the following 'why' and 'how' questions:

 Why was a given fact used?

 Why was a given fact not used?

 How was a given conclusion reached?

 How was it that another conclusion was not reached?

This ability to provide explanations is the big advantage of Expert Systems over neural network-

based (NN) systems, and the reason why, despite the notable success of NN systems in many

current application areas, Expert Systems are likely to remain for a long time the Al technique of
choice for safety-critical applications such as medical diagnosis, and ones where for legal

reasons a verbal defense of a decision must be available if requested Bullinaria, 2005).

Figure 2.3 Typical Architecture of An Expert System

A simple example of deductive reasoning:

The knowledge base contains, amongst other facts: green (Fritz).

The rule base contains, amongst other rules:

IF green(x) THEN frog(x).

IF frog(x) THEN hops(x).

Query: Does Fritz hop?

Step 1: The knowledge base is examined to see if 'hops (Fritz)' is a recorded fact. It's not.

Step 2: Rule base is examined to see if there's a rule of the form IF A THEN hops(x); x=Fritz:
There is, with A=frog(x); ×-Fritz. But is the premise 'frog (Fritz)' actually true?

Step 3: The knowledge base is examined to see if 'frog (Fritz)' is a recorded fact. As with 'hops

(Fritz),' it's not, so it's again necessary to look instead for an appropriate rule.

Step 4: Rule base is examined to see if there's a rule of the form IF A THEN frog(x); x=Fritz.

Again, there is a suitable rule, this time with A=green(x); ×-Fritz. But now is 'green (Fritz)' true?

Step 5: The knowledge base is yet again examined, this time to see if 'green (Fritz)' is a recorded

fact, and yes - this time the premise is directly known to be true.

One can therefore finally conclude that the original assertion ‘hops (Fritz)' was also true.

Failure of a query

If the required fact 'green (Fritz)' had not been found in the knowledge base, the rule base would

have yet again been examined, this time looking for a rule of the form IF A THEN green(x);

X=Fritz. However, there is no rule in this database of this form, specifying a condition 'A' under

which things are green; this would cause the system to exit in fail mode, effectively concluding

that 'No, Fritz doesn't hop.'

Knowledge-Based System

The knowledge-based section of the expert system will consist of the knowledge acquired from

various books and journals as well as input from a domain expert.

The structure of the expert system which will be implemented in this project will be given below

which will include the knowledge base.

1.3 Theoretical Review

The theoretical framework examines known ideas that are pertinent to the study topic. It

exhibits a mastery of ideas and theories that are closely related to the main topic of the

research paper and reveals a profound comprehension of their relevance in wider fields of

study. This framework functions as a path through which the research problem is examined,

bringing the study into line with accepted theoretical viewpoints and assisting in the

development of a more sophisticated understanding of the topic in relation to the larger

scholarly community.

Heart Disease Detection models are important tools for detecting heart diseases among

groups of people.