CHAPTER II

REVIEW OF RELATED LITERATURES

This chapter presents related literatures which are relevant to the study.

Decision Support System

Decision support systems are used by professionals in a wide range of industries to assist them in

making daily decisions. These tools enable users to make informed judgments by providing sample

scenarios and building models based on data compilation. Understanding how decision support systems

support particular processes will help you install a system more successfully if you're interested in

employing one (Indeed, 2023).

Furthermore, similar study shows that decision support system (DSS) is crucial since it is

considered a tool that assist workers in making thoughtful and well-informed business decisions. Also,

depending on the sectors and the professionals using them, DDSs can serve a variety of purposes and

have different focal points.

According to Elsevier (2023), in order to guarantee the quality of the services rendered, clinical

decision support systems, or CDSS, are a means to support the decisions made by individual patients in

the healthcare setting. The two categories of these systems are classified as knowledge-based systems

and non-knowledge-based systems. There are benefits to using CDSS in health information systems.

lowering clinical errors and averting patient-related issues. Rule-based systems are a subset of knowledge-

based systems that use data extraction and manipulation to gain contextual knowledge from other systems.

Currently, the healthcare industry is dealing with serious organizational and financial difficulties as

the Chronic illness sufferers are becoming more prevalent. In fact, achieving therapeutic goals for chronic

patients calls for continued care that is not intended to promote healing but rather to improve their clinical

state. This has a big effect. on health spending, with almost 80% of the country's health care budget going

toward treating chronic illnesses. Diabetes is a big concern in this competition. One of the main causes of
death is diabetes, however it also constitutes a considerable amount of national health spending, especially

in light of the urgent need for patient observation (Colella, et al., 2021).

Based on the symptoms and patient data entered into the system, a Decision Support System

(DSS) uses the frame-based expert system algorithm to assess the possible diseases that a patient may

have. The system entails capturing information, keeping health data, diagnosing patients, issuing electronic

prescriptions, and creating statistical reports. The methodology employed in the system is extreme

programming since the development process is continuous and the phases allow the system to be created

and adjusted as mistakes are discovered during the testing phase. The system is then released once the

study is complete and all modules tested have passed (Palomar, 2021).

Significance of DSS in Medical Field

Healthcare practitioners deal with hundreds of patients on a daily basis in their work. All of this

interaction must, of course, be converted into records—clinical or administrative—which are then converted

into data, information, and, ideally, knowledge. These records are still maintained in physical format despite

technological advancements, which causes a delay in work completion when compared to their digital

counterparts. Hence, decision support (DS) efficiently and reliably composes models and approaches via a

knowledge representation architecture, converting this activity into a system-based format. Also, a DSS is a

framework intended to assist a professional in learning about and making decisions in a particular field,

thereby reducing uncertainty during the decision-making process (Hak, Guimarães, & Santos, 2022).

Patil (2023) states that a clinical decision support system (also known as a decision support

system for healthcare) functions similarly to an assistant for physicians. It belongs to a certain class of clinic

administration systems. Also, since it offers pertinent information and recommendations based on medical

data, it assists them in making informed decisions regarding a patient's care. This clever technology

evaluates clinical knowledge and research pertaining to patients and then provides recommendations for

diagnosis to medical professionals.

 In addition, to put it briefly, it's similar to having an informed companion to help with medical

decision-making. When a physician must choose the best course of action for a patient, the DSS will

suggest possibilities based on patient characteristics and cases that are similar to each other.

However, the goal of this technology is to improve human judgment rather than replace it. It was

created as a result to enable healthcare professionals to more quickly obtain pertinent health information so

they may make well-informed decisions. This suggests that it uses technology to improve patient care and

help doctors navigate through a sea of medical data (Patil, 2023).

Rule-Based System

A rule-based system makes use of specific information and offers a degree of adaptability in terms

of changing the knowledge acquired. It was formerly employed in studies on ship design and was capable

of formulating machine layout architecture principles by addressing the connection between equipment and

shipowner requirements, wisdom, style, etc. Also, a rule-based system that has been created has grown

increasingly widespread and suitable for a larger range of products (Nugraha, 2018).

Moreover, according to Nugraha in 2018, some knowledge or information that was not known

before can be discovered from the data. The information could be used as corroborating data to highlight

some significant trends by applying modeling strategies. The model can be automatically updated since the

database updated instantly when modeling approaches are applied. A rule can be used to represent data.

Fundamental guidelines can be utilized to properly and effectively manage regulations by taking note of

retrieval and storage. The most widely utilized the rule-based approach represents rules in a methodical

manner.

Unlike traditional procedural or object-oriented programs, rule-based systems don't have a

predetermined sequence in which code runs. In this case, the expert's information is incorporated into a

collection of rules, each of which encodes a small portion of the expert's knowledge. There are left and right

sides to every rule. Certain facts and things are covered in the information on the left. A rule is selected
from the agenda, carried out according to its rights, and then the rule is struck. Intelligent decisions may be

made, and the decision-making process can be traced with rule-based systems (Giridhar, 2015).

In addition, as previously stated, a rule-based system is made up of a set of facts, a series of if-

then rules, and an interpreter who decides how the rules should be applied in light of the facts. The

conditional statements that make up the whole knowledge base are created using these if-then rule

statements. The format of a single if-then rule is 'if x is A then y is B.' The if portion of the rule, "x is A," is

referred to as the antecedent or premise, while the then section, "y is B," is referred to as the consequent or

conclusion. Rule-based systems use two main types of inference engines: forward chaining and backward

chaining systems. In a forward chaining system, the initial facts are processed first, and the rules are then

applied to generate new conclusions based on those facts.

Mulongo and Pihlqvist explains in 2018 that a system designed around rules includes a working

memory or knowledge base, a rule base, an inference engine, and an execution engine. The knowledge

base, also known as working memory, describes the facts and conditions. The rule base describes the

relationship between premises and conclusions. The inference engine contains a pattern matcher that

applies rules based on an agenda that includes all relevant rules. The execution engine determines which

rules to apply based on the input.

In addition, forward and backward chaining are the two basic techniques used to infer a rule-based

system. Forward chaining takes a top-down approach, starting with the facts and applying the rules to

deduce conclusions or trigger actions based on the facts. Backward chaining takes a bottom-up strategy,

beginning with a hypothesis or goal and searching the rule space for rules that verify it. As the process

progresses, new sub-goals are defined to prove the hypothesis.

Rule-based Analysis

The rule-based approach is considered an independent solution to the short. There is an answer-

scoring problem. It has not used any training data. It is accurate. calculated for the entire dataset. The
accuracy is 45 percent. It is lower than. The machine learning method is still fairly good, given that

no training data is used. The rule-based strategy is utilized for benchmarking. purpose and assisting the

machine learning system in labeling new examples (Mulongo & Pihlqvist, 2018).

Additionally, the rule-based system has the same difficulty as when developing a machine learning

system for short response scoring: the difficulty of writing ahead of time a collection of appropriate

references, answers, or patterns that the student's replies can be corrected against. In our dataset, the

collection of all eligible reference responses is not a closed set. A comprehensive examination of the

various possible responses was plausible, and if the set had been more closed, it would have been easier

to write rules and patterns in a rule-based system.

Bibliography

Colella, Y., De Lauri, C., Improta, G., Rossano, L., Vecchione, D., Spinosa, T., . . . Santini, S. (2021). A
Clinical Decision Support System based on fuzzy rules and classification algorithms for monitoring
the physiological parameters of type-2 diabetic patients. Mathematical Biosciences and
Engineering.

Elsevier. (2023). Rule-based System for Effective Clinical Decision Support.

Giridhar, A. V. (2015). Rule-Based Systems for Medical Diagnosis. Retrieved from Google: https://www.igi-
global.com/chapter/rule-based-systems-for-medical-diagnosis/124441

Hak, F., Guimarães, T., & Santos, M. (2022, August 15). National Library of Medicine. Retrieved from
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9377614/

Indeed. (2023). Retrieved from Google:

https://www.indeed.com/career-advice/career-development/decision-support-system

Mulongo, B., & Pihlqvist, F. (2018). USING RULE-BASED METHODS.

Nugraha, J. A. (2018). Rule Based System for Medicine Inventory Control Using.

Palomar, C. A. (2021). FRAME-BASED EXPERT DECISION SUPPORT SYSTEM FOR.

Patil, N. (2023). Decision Support Systems Healthcare: Meaning, Functions, Benefits, And Types.