Download application of rule based reasoning system for council hiv

International Journal of Computer Engineering & Technology (IJCET)
Volume 7, Issue 4, July–Aug 2016, pp. 48–58, Article ID: IJCET_07_04_005
Available online at
http://www.iaeme.com/ijcet/issues.asp?JType=IJCET&VType=7&IType=4
Journal Impact Factor (2016): 9.3590 (Calculated by GISI) www.jifactor.com
ISSN Print: 0976-6367 and ISSN Online: 0976–6375
© IAEME Publication
APPLICATION OF RULE BASED
REASONING SYSTEM FOR COUNCIL
HIV/AIDS PATIENTS
Yirga Yayeh Munaye
MSC, Department of Information Technology,
Faculty of Engineering and Technology,
Assosa University, Assosa, Ethiopia
Getaneh Berie Tarekegn
PG, Department of Computer Science,
Faculty of Engineering and Technology, Assosa
University, Assosa, Ethiopia
ABSTRACTS
The complexity of the epidemic of human immunodeficiency virus (HIV)
infection has made the creation of effective prevention programs an evolving
and challenging task. Prevention of new HIV infections is an issue of
increasing importance as the prevalence of HIV infection continues to
increase.This study is aimed to design a prototype for HIV/AIDS advising
service for patients by using rule based system with the tool of prolog.
According to the result of this study it is important for patients in hospitals
and different health centers. Future research directions are also raised.
Key words: HIV/AIDS, Rule Based, Advising System
Cite this Article Yirga Yayeh Munaye and Getaneh Berie Tarekegn,
Application of Rule Based Reasoning System for Council HIV/AIDS Patients.
International Journal of Computer Engineering and Technology, 7(4), 2016,
pp. 48–58.
http://www.iaeme.com/ijcet/issues.asp?JType=IJCET&VType=7&IType=4
1. INTRODUCTION
Human Immunodeficiency Virus, well known by its acronym HIV, is the virus that
causes Acquired Immunodeficiency Syndrome (AIDS) in humans. HIV/AIDS is
today a major threat to the world's population- to its overall social, economic, and
political well being, as well as to the individual health of hundreds of millions of
people [3].
A fundamental part of becoming an empowered patient is learning to engage in
the day-to-day management of personal health. Attrition of HIV patients increased
http://www.iaeme.com/IJCET/index.asp
48
[email protected]
Application of Rule Based Reasoning System For Council HIV/AIDS Patients
from time to time. Our interviews, in the Knowledge acquisition indicated that fear of
stigma, transport cost, feeling healthy and opting for traditional medicines were the
main reasons for poor linkage to and retention in care. The counselors labor also on
many fronts to meet the enormous demand for the HIV/AIDS services. Despite their
effort, they are not able to meet all the patients’ needs [1].
So counseling HIV patients using computer system is one of the safest solutions to
help them immediately, with minimum time and effort and freely without any filling.
To solve the above mentioned problems, this study rests on one of the application of
Knowledge Base system, on which rule-based expert systems instantiated in
counseling service of HIV/ADIS disease. The application: accepts an input from the
user about the positive and negatives of the user, if the user is HIV positive, the
system ask the CD4 count and the amount of weight losses in percent, the system
displays the name of the tablet that the patient should take and ask the user weather
he/she needs advice or to see the side effect of the recommended treatment by
applying knowledge base rules, give the information needed accordingly, If the user is
HIV negative, the system gives different information about prevention, transmission
ways symptoms and the principles to manage HIV/ADIS.
2. STATEMENT OF THE PROBLEM
Economic and social impacts of HIV/AIDS in Ethiopia have not been
comprehensively quantified, they are significant and growing. By undermining major
determinants of economic growth and preventing increasing segments of the
population from participating in the economy, HIV/AIDS increases poverty, draught
on which it feeds in a vicious cycle [5].
HIV/AIDS has great impact on different economic sector such as agriculture,
education, and labor works and so on. The loss of a few workers at the crucial periods
of producing can significantly reduce the amount of economic production. For that
reason, it is significant to prevent the disease [4].
However, there are lots of challenges that hinder to avoid. Lack of professional at
rural areas, inaccessible to hospital, financial problem are inhibits to prevent
HIV/AIDS. Stigma and discrimination are among the biggest challenges for HIV
patients as they would be reluctant to access treatment, care and support for fear of
alienation. Preventing and reducing stigma is vital. So that, people are not
discouraged from using and helping others on Anti Retroviral Drugs (ART). Because
of stigma, patients are forced to take their medications in secrecy increasing the
likelihood of non-adherence. Regardless of factors amplifying stigma, patients on
ART will face real challenge to continue to take medications in secrecy and therefore
are strongly recommended to disclose their HIV status to close family members for
additional support. Such case is mostly in rural areas in Ethiopia. To reduce/minimize
the aforementioned trouble, this study is initiated to develop Knowledge Based
HIV/AIDS Counseling system.
3. OBJECTIVES
•
To investigate different related works
•
•
•
To understand prolog programming language in designing KBS system
To Design and implementing the prototype of the system
Recommending further research directions.
http://www.iaeme.com/IJCET/index.asp
49
[email protected]
Yirga Yayeh Munaye and Getaneh Berie Tarekegn
4. LITERATURE REVIEW
4.1. Knowledge-Based System approach
A Knowledge-Based System (KBS) has interdisciplinary approach of various
disciplines like computer science, cognitive science, hardware field etc. The society
and industry are becoming knowledge-oriented and rely on different experts’
decision-making abilities depending on the information available. When expertise is
unavailable, a KBS can act as an expert on demand to save time [11].
KBS can save money by leveraging expert, allowing users to function at higher
level and promoting consistency. Such system can potentially alleviate the immense
diagnostic workload of rural health workers and medical practitioners. Also, it can
assist in prevention of various diseases. In addition, by using such systems, user will
get the advantage of the knowledge of more than one specialist. Such KBS uses
Artificial Intelligence techniques for efficient and effective decision making in
unstructured domain and apply reasoning and explanation facility for the domain
problem to achieve high level of performance [11].
4.2. Structure of Knowledge-Based System
The model of the system is given in Figure 1 representing the overall process structure
of KBS for medical diagnosis. The basic components of the system are the knowledge
base, inference engine, and a workspace. The knowledge base of the system plays a
key role in the procedure of decision-making by efficiently storing the domain
knowledge and patients history. Temporary results can be stored in workspace. The
inference engine is a program, which infers the knowledge available in the knowledge
base.
FIGURE 1 STRUCTURE OF KBS
4.3. Types of Knowledge Based Systems
4.3.1. Fuzzy Logic Rule Based
According to [9] it is a form of knowledge base and has achieved several important
techniques and mechanisms to diagnose the disease and pain in patient. For example
RVM Learning Technique is used for pain management in patient who cannot
communicate verbally. The pattern recognition technique can assist medical staff in
measuring the pain which is an extension of Vector machine algorithm. The Fuzzy
Logic Rule based classifier is very effective in high degree of positive predictive
value and diagnostic accuracy. For example in diseases like appendicitis, the results
predicted by fuzzy logic rule based classifier have an accuracy rate of 95% on
http://www.iaeme.com/IJCET/index.asp
50
[email protected]
Application of Rule Based Reasoning System For Council HIV/AIDS Patients
average. For improving the effectiveness of fuzzy set theory, Rough set theory can be
proposed to complement fuzzy set and to deal with vagueness and uncertainty. Its
main advantage is that it does not need data such as probability distribution in
statistics, basic probability assignment, and grade of membership of value of
possibility in fuzzy set theory. Clinical guidelines provide benefits to health outcomes
and are economical but they have certain characteristics that are difficult to handle
such as vagueness and ambiguity. Fuzzy logic facilitates us for treatment of
vagueness in decision support system. Fuzzy logic approach can be a very useful
approach for describing vagueness and imprecision in precise mathematical language,
explicitly representing clinical vagueness.
4.4. Rule- Based Systems and Evidence Based Systems
They tend to capture the knowledge of domain experts into expressions that can be
evaluated as rules. When a large number of rules have been compiled into a rule base,
the working knowledge will be evaluated against rule base by combining rules until a
conclusion is obtained. It is helpful for storing a large amount of data and information.
However it is difficult for an expert to transfer their knowledge into distinct rules.
For closing the gap between the physicians and CDSSs, evidence based appeared
to be a perfect technique. It proves to be a very powerful tool for improving clinical
care and also patient outcomes. It has the potential to improve quality and safety as
well as reducing the cost.
The human immunodeficiency virus, or HIV, is the virus that causes HIV
infection. During HIV infection, the virus attacks and destroys the infection-fighting
CD4 cells of the body’s immune system. Loss of CD4 cells makes it difficult for the
immune system to fight infections. Human immunodeficiency virus (HIV)/Acquired
immune deficiency syndrome (AIDS) is a major global health problem. Advances in
Information and Communication Technology (ICT) have facilitated development of
medical expert systems. [1] They have proved their usefulness by providing precise,
quick and inexpensive consultation. Advisory expert system is seen as an
enhancement tool in providing home-base care to people living with HIV/AIDS.
Acquired immunodeficiency syndrome, or AIDS, is the most advanced stage of HIV
infection.
In 2011, the prevalence rate for HIV was estimated to be 10.6 percent and the total
number of people living with HIV/AIDS rising from 4.2 million in 2001 to an
estimate of 5.4 million in 2011 [2]. It has been estimated that up to 90 percent of
nursing care is provided at home by the untrained family and associates [3]. Up to 80
percent of HIV/AIDS related deaths occur at home [3]. The patients and their care
givers do not always have contact with professional help, thus support is inadequate.
Counselors (trained health workers linked to the hospitals) have been enrolled to
help the patients. Counselors’ role is to maintain regular contact with the patients,
train existing primary family on how to safely perform day-to-day task, provide
clinical task such as administering pain relief or medication to patients and providing
with nutritional care and support information. The counselors toil on many fronts to
meet the enormous demand for the HIV/AIDS services [13].
http://www.iaeme.com/IJCET/index.asp
51
[email protected]
Yirga Yayeh Munaye and Getaneh Berie Tarekegn
4.5. HIV-Positive without Symptoms
According to [4] many people who are HIV-positive do not have symptoms of HIV
infection. Often people only begin to feel sick when they progress toward AIDS
(Acquired Immunodeficiency Syndrome). Sometimes people living with HIV go
through periods of being sick and then feel fine.
While the virus itself can sometimes cause people to feel sick, most of the severe
symptoms and illnesses of HIV disease come from the opportunistic infections that
attack a damaged immune system. It is important to remember that some symptoms of
HIV infection are similar to symptoms of many other common illnesses, such as the
flu, or respiratory or gastrointestinal infections.
4.6. Early Stages of HIV: Signs and Symptoms
As early as 2-4 weeks after exposure to HIV (but up to 3 months later), people can
experience an acute illness, often described as “the worst flu ever.” This is called
acute retroviral syndrome (ARS), or primary HIV infection, and it’s the body’s
natural response to HIV infection. During primary HIV infection, there are higher
levels of virus circulating in the blood, which means that people can more easily
transmit the virus to others. It is important to remember, however, that not everyone
gets ARS when they become infected with HIV.
4.7. How is HIV transmitted?
According to [10] HIV is transmitted (spread) through the blood, semen, genital
fluids, or breast milk of a person infected with HIV. Having unprotected sex or
sharing drug injection equipment (such as needles and syringes) with a person
infected with HIV are the most common ways HIV is transmitted.
We can’t get HIV by shaking hands, hugging, or closed-mouth kissing with a
person who is infected with HIV. And you can’t get HIV from contact with objects
such as toilet seats, doorknobs, dishes, or drinking glasses used by a person infected
with HIV.
Even though it takes many years for symptoms of HIV to develop, a person
infected with HIV can spread the virus at any stage of HIV infection. Detecting HIV
early after infection and starting treatment with anti-HIV medications before
symptoms of HIV develop can help people with HIV live longer, healthier lives.
Treatment can also reduce the risk of transmission of HIV.
4.8. What is the treatment for HIV?
Antiretroviral therapy (ART) is the recommended treatment for HIV infection. ART
involves taking a combination (regimen) of three or more anti-HIV medications daily.
ART prevents HIV from multiplying and destroying infection-fighting CD4 cells.
This helps the body fight off life-threatening infections and cancer. ART can’t cure
HIV, but anti-HIV medications help people infected with HIV live longer, healthier
lives [5].
5. METHODOLOGIES
5.1. Methods of data collection
Data for this project have been collected by reviewing the relevant literature about
medical diagnosis in general and healthcare diagnosis and advisory in particular in an
http://www.iaeme.com/IJCET/index.asp
52
[email protected]
Application of Rule Based Reasoning System For Council HIV/AIDS Patients
attempt to understand the issues leading to the design and development of the
healthcare expert system.
5.2. Method of system development
A prototyping approach is followed to develop the system using the technique of
Certainty Factor. Prototyping is preferred from other methods, because it is a common
way of developing an expert system and it enables better management of the system
in times of implementation. The rule-based knowledge representation method is
employed. Because;
1. It makes decision based on the knowledge base stored.
2. It is easy to understand and also communicable because its communication is using
natural language processing.
5.3. Project Development Tool
SWI –prolog is used for developing the expert system. SWI-prolog has debugging
tool that used to code the facts and rules that is necessary for our project. Moreover,
the code is readable and easier to update and maintain.
6. KNOWLEDGE ACQUISITION METHOD
Acquiring expert knowledge is a crucial component of knowledge engineering. This
phase is difficult and time consuming. It is the process of gathering the relevant
information about a domain, usually from an expert. A number of knowledge
acquisition techniques have been developed [11]. Knowledge acquisition involves the
acquisition of knowledge from human experts, books, documents, sensors or
computer files. The knowledge may be specific to the problem domain and the
problem solving procedures, or it may be general knowledge (e.g., knowledge about
business), or it may be Meta knowledge (knowledge about knowledge). By the later,
we mean information about how experts use their knowledge to solve problems. The
process of seeking out the knowledge required by an expert system is referred to as
knowledge acquisition. Therefore, In order to develop the HIV counseling expert
system knowledge acquisition process of this project work is based on domain expert
interviewing of and reviewing of related documents.
7. KNOWLEDGE MODELING
In order to model the knowledge of the domain area decision tree is used. Decision
tree is structure that can be used to divide up a large collection of records into
successively smaller sets of records by applying a sequence of simple decision rules.
A decision tree model consists of a set of rules for dividing a large heterogeneous
population into smaller, more homogeneous groups with respect to a particular target
variable.
http://www.iaeme.com/IJCET/index.asp
53
[email protected]
Yirga Yayeh Munaye and Getaneh Berie Tarekegn
Reaso
n
Cd count
Weight
Loss
<350
HIV
positive
<10%
Take
Abacavir
tablet
Figure 2 Decision tree for level I case
8. KNOWLEDGE REPRESENTATION
Knowledge representation is the systematic means of encoding knowledge of human
expert in an appropriate medium. Knowledge can be represented as: Logic is part of
mathematics and can be used in various forms to reason about the correctness of
computational representation and inference. The forms of logic include:Propositional logic or calculus that consist of building blocks such as atomic
sentences, joined by ‘and’, ‘or’, and ‘not’. Predicate logic with its basic building
block objects and relations such as “is-a” and “has-a” between them to build
statements.
Hence, in order to represent the knowledge of HIV counseling expert system first
order predicate logic is used, and rule-based approach to represent the knowledge is
followed. The rules are extracted from the domain experts of health centers and the
corresponding first order logic representation is given under each rule. Facts which
have a paramount importance for the knowledge based are stated here in bellow.
Facts:
Less than(C, 350)
Greater than (C, 350)
Less than (W, 10%)
Equal to (W, 10%)
Greater than (W, 10%)
Positive(x)
•
Negative(x)
Level 1(C, W)
Level 2(C, W)
Level 3(C, W)
Level 0(C, W)
Where C for CD4 count, W for weight loss of the patent
Rule 1:
If a patient has cd-4 count less than 350 and weight loss is less than 10 percent
then s/he is in level one.
∀c, w less than (C, 350) ˄ less than (W, 10) => level1 (C, W)
http://www.iaeme.com/IJCET/index.asp
54
[email protected]
Application of Rule Based Reasoning System For Council HIV/AIDS Patients
Rule 2:
If a patient has cd-4 count less than 350 and weight loss is equal to 10 percent
then s/he is in level two.
∀c, w less than (C, 350) ˄ equal to (W, 10) => level2 (C, W)
Rule 3:
If a patient has cd-4 count less than 350 and weight loss is greater than 10 percent
then s/he is in level three.
∀c, w less than (C, 350) ˄ greater than (W, 10) => level3 (C, W)
Rule 4:
If a patient has cd-4 count greater than 350 and weight loss is greater than or equal
to or less than or equal to 10 percent then s/he is in level zero.
∀c, w greater than(C, 350) ˄ greater than or equal to or less than or equal to (W,
10) => level3 (C, W)
Rule 5:
If the patient is level one or level two or level three then s/he should take
Abacabari, dedanosine, lumivudine and read advice as well as side effect respectively.
∀ Level (C, W)=> take (abacabari) ˄ read(x) ˄ x==1 => advice 1(x) ˄ x==2
=>side-effect1(x)
∀ leve2 (C, W)=> take (dedanosine) ˄ read(y) ˄ y==1 => advice 2(y) ˄ y==2
=>side-effect2(y)
∀ leve3 (C, W)=> take (lumivudine) ˄ read(z) ˄ z==1 => advice 3(z) ˄ z==2
=>side-effect3(z)
9. FINDINGS AND IMPLEMENTATION
When the user runs the system initially it looks like:
http://www.iaeme.com/IJCET/index.asp
55
[email protected]
Yirga Yayeh Munaye and Getaneh Berie Tarekegn
If the user is yes for sick and HIV positive he/she can interact with the system like:
If the user is HIV negative the system interact continuously up to the user need to exit
from our system
http://www.iaeme.com/IJCET/index.asp
56
[email protected]
Application of Rule Based Reasoning System For Council HIV/AIDS Patients
10. CONCLUSION
The need for health education to bring about behavioral changes and further study to
identify the prevalence and role of exposure to HIV infection in the community is
recommended. In doing so, the major challenge for such counseling services becomes
satisfactory are shortage of skilled health professionals, the number of HIV/ADIS
patients and health professionals are disproportionate too. The other challenge is most
of the time patients need high security when they counseled by human beings. As a
result they become mentally affected. Mental health issue is the basic concern for the
better life of everybody. Mental health problems touch every aspects of human life
such as humans’ general health condition, work, family life, social relations, etc.
counseling expert systems, other Knowledge based systems that can serve as a
counselor of HIV/ADIS patients have great role in saving the patients and others to
treat the patients safely and to prevent others.
Generally, in this study, the applicability of knowledge based system is proved as
useful approach for preventing mental disorder and treating HIV patients properly,
and preventing others by giving essential information about HIV.
11. RECOMMENDATION
The study achieves its objectives by demonstrating the applicability of rule based
system by developing a knowledge based system that can advise and assist
HIV/ADIS. This study is the promising study for further research works to fully
implement the knowledge based system in the domain area. As a result, the following
recommendations are given based on the observed opportunities and uncover areas by
this study.
•
Counseling HIV patients is somewhat complex when compared to other disease. It
involves both physical examination and mental status examination. Therefore, further
investigation should be done to integrate an intelligent agent that has the capability to
perform mental status examination and observation of facial expressions of a patient.
•
In rule based systems; the acquired examples are used to construct decision rules.
These rules are further used to make decisions regarding new, unknown cases.
However, rule based systems are not able to learn from experience and do not operate
with cases which have not matching facts in the rule base of the systems.
•
To enhance the performance of the prototype knowledge based systems, the hybrid
strategy approaches should be investigated which combines case-based reasoning.
The Inclusion of case based reasoning helps the system to learn from documented
experiences.
REFERENCE
[1]
[2]
[3]
[4]
[5]
Horton, M. HIV/AIDS in South Africa. Spectrum, July (2004), 113-129.
ASSA. National planning commission: National Development Plan. 2011.
HIV and AIDS home based care. 2011. http://www.avert.org/aids-homecare.htm.
Session 5 Nutritional Management of HIV / AIDS-Related Symptoms Learning
objectives Prerequisite knowledge. Management, 97-116, http://www.
fantaproject.org/downloads/preservice/training_5.pdf.
How to deliver care for people with HIV/AIDS and their families.2012.
http://www.etu.org.za/toolbox/docs/aids/family-care.html.
http://www.iaeme.com/IJCET/index.asp
57
[email protected]
Yirga Yayeh Munaye and Getaneh Berie Tarekegn
[6]
[7]
[8]
[9]
[10]
[11]
Expert system notes. 2011. http://www.scribd.com/doc/35213874/Expert-SystemNotes
Vijayalakshmi, K; Sreedevi, E. and Kumar Naveen, R and Padmavathamma, M.
Design and Development of Secured Diagnostic Expert System for HIV and
AIDS. Architecture, (2011), 2–5.
A.N. Masizana-Katongo, T.K. Leburu-Dingalo, D. Mpoeleng an Expert System
for HIV and AIDS Information
ichael J. Pazzani, tDarry1 See, j-Edison Schroeder, and I Jeremiah Tilles
Application of an Expert System in the Management HIV-Infected Patients.
Retrieved on 2016, http://aidsinfo.nih.gov.
Salwa Hamada, Mahmoud Elsayess and Ahmed Hamam, A Proposed Model
Based On Audio-Visual Aids For Learning The Accurate Arabic Pronunciation.
International Journal of Computer Engineering and Technology, 4(5),
2014, pp. 300–311.
[12]
[13]
[14]
Getaneh Berie Tarekegn and Yirga Yayeh Munaye, Application of Digital Cloud
Libraries For Ethiopian Public Higher Learning Institutions (Ephlis),
International Journal of Computer Engineering and Technology, 7(3), 2016, pp.
187–197.
Getaneh Berie Tarekegn and Yirga Yayeh Munaye, Big Data: Security Issues,
Challenges and Future Scope, International Journal of Computer Engineering and
Technology, 7(4), 2016, pp. 12–24.
Tagel Aboneh Knowledge based system for pre-medical triage treatment at
Adama University Asella hospital Master’s Thesis at Addis Ababa University
Journal of Public Health. Apr 2013, 21(2) pp. 155–16.
http://www.iaeme.com/IJCET/index.asp
58
[email protected]