Download the complete Computer science topic and material (chapter 1-5) titled A WEB-BASED CLINICAL DECISION SUPPORT SYSTEM FOR THE MANAGEMENT OF DIABETES NEUROPATHY USING NAÏVE BAYES ALGORITHM here on PROJECTS.ng. See below for the abstract, table of contents, list of figures, list of tables, list of appendices, list of abbreviations and chapter one. Click the DOWNLOAD NOW button to get the complete project work instantly.
PROJECT TOPIC AND MATERIAL ON A WEB-BASED CLINICAL DECISION SUPPORT SYSTEM FOR THE MANAGEMENT OF DIABETES NEUROPATHY USING NAÏVE BAYES ALGORITHM
The Project File Details
- Name: A WEB-BASED CLINICAL DECISION SUPPORT SYSTEM FOR THE MANAGEMENT OF DIABETES NEUROPATHY USING NAÏVE BAYES ALGORITHM
- Type: PDF and MS Word (DOC)
- Size: [7509KB]
- Length:  Pages
The use of Artificial Intelligence in medical diagnosis is becoming increasingly common and has been used widely in the diagnosis of cancers, tumors, diabetes, hepatitis, lung diseases, etc. There is a growing interest in the use of computer-based Clinical Decision Support Systems (CDSSs) to reduce medical errors and to increase health care quality and efficiency. Diabetes Neuropathy is a chronic health problem with devastating, yet preventable consequences.Due to this shortage of specialists, there is a need for a Clinical Decision Support System that will diagnose and manage diabetes neuropathy.This work therefore aimed at designing a web-based Clinical Decision Support System for the management of early diabetes neuropathy.
Four pattern classification algorithms (K-nearest neighbor, Decision Tree, Decision Stump and Rule Induction) were adopted in this study and were evaluated to choose the most precise algorithm to be employed in the developed clinical decision support system. The evaluation was carried out on appropriate dataset that was obtained from Babcock University Teaching Hospital and the University of Port Harcourt Teaching Hospital. The following benchmarks were used in comparing the generated models: performance, accuracy level, precision, confusion matrices and the models building’s speed.
From the models comparison, the study showed that Naïve Bayes outperformed all other classifiers with accuracy being 60.50%. k-nearest neighbor, Decision Tree, Decision Stump and Rule induction perform well with the lowest accuracy for x- cross validation being 36.50%. Decision Tree falls behind in accuracy, while k-nearest neighbour and Decision Stump maintain accuracy at equilibrium 41.00%. Therefore, Naïve Bayes is adopted as optimal algorithm in the domain of this study. The rules generated from the optimal algorithm (Naïve Bayes) forms the back-end engine of the Clinical Decision Support System.The web-based clinical decision support system was then designed using Adobe Creative Suite 6 as its integrated development environment in which all the web language codes was executed, Php My Admin as the server side scripting language, and MySQL as the database server.
In conclusion, the automatic diagnosis of diabetes neuropathy is an important real-world medical problem. Detection of diabetes neuropathy in its early stages is a key for controlling and managing patients early before the disabling effect present. This system can be used to assist medical programs especially ingeographically remote areas where expert human diagnosis not possible with an advantage of minimal expenses and faster results. For further studies, researchers can improve on the proposed clinical decision support system by employing more than one efficient algorithm to develop a hybrid system.
Keywords: Diabetes, Neuropathy, Precision, Classification, Algorithm, Accuracy, Clinical.
Word Count: 422
TABLE OF CONTENTS
Title Page i
Table of Contents vi
List of Tables vii
List of Figures viii
CHAPTER ONE: INTRODUCTION
1.1. Background to the Study 1
1.2. Statement of the Problem ` 3
1.3. Objective of the Study 4
1.4. Methodology 4
1.5. Scope of the Study 5
1.6. Significance of Study 5
1.7. Organization of the Subsequent Chapters 5
CHAPTER TWO: REVIEW OF LITERATURE
2.0. Introduction 6
2.1. Clinical Decision-Making 7
2.1.1. Clinical Decision Analysis (Problem Solving) 7
2.1.2. Structure of Clinical Decision Support Systems 10
2.1.3. Elements of CDSS Design and Function 10
2.1.4. CDSS Knowledge Axes 12
2.1.5. CDSS Decision support Axes 13
2.1.6. CDSS Information Delivery Axes 14
2.1.7. CDSS Model 14
2.1.8. CDSS Knowledge Representation 15
2.1.9. Knowledge Engineer 16
2.1.10. CDSS Knowledge Acquisition 16
2.1.11. CDSS User Interface 17
2.2. Overview of Diabetes Neuropathy 18
2.2.1. Causes of Diabetes Neuropathy 18
2.2.2. Symptoms of Diabetes Neuropathy 18
2.2.3. Classification of Diabetes Neuropathy 19
2.2.4. Diagnosis of Diabetes Neuropathy 19
2.2.5. Early Detection of Diabetes Neuropathy 20
2.3. Review of Closely Related Works 21
2.3.1. A Novel Analysis of Diabetes Mellitus by Using Expert System
Based on Brain Derived Neurotropic Factor (BDNF) Levels 21
2.3.2. Web Based Intelligent Decision Support System for Type 2
Diabetes Patients 21
2.3.3. An Expert System for Diabetes Diagnosis using VP_Expert Shell 21
2.3.4. Web Based Medical Diagnosis System Using ANN-ARM
For Diabetes Mellitus 22
2.3.5. Expert System for Diagnosis and treatment of Diabetes 22
2.3.6. Design of a Diabetic Diagnosis Expert System Using Rough Sets 22
2.3.7. Mycin 23
2.3.8. Gideion 23
2.3.9. An Expert System for Diagnosing Diseases and Prescribing
Medication Using Visual Basic.Net (Autodoc) 24
2.3.10. Computerized clinical decision support systems for chronic disease
management: A decision-maker-researcher partnership systematic review 24
2.3.11. Clinical Decision Support System for Diabetes Disease Diagnosis using
fuzzy logic 24
2.4. The limitations of related works reviewed 25
2.5. Pattern Classification 25
2.5.1. Approach to Pattern Classification 25
2.6. Classification Algorithms 27
2.6.1 Types of Classification Algorithms 28
2.7. K-nearest Neighbors (KNN) 28
2.8. Decision Tree Algorithm (DTA) 30
2.9. Decision Stump (DS) 31
2.10. Rule Induction (RI) 31
CHAPTER THREE: METHODOLOGY
3.0. Introduction 33
3.1. Design a Web-based Clinical Decision Support System to Diagnose
and Manage Diabetes Neuropathy 33
3.2. Research Tools 34
3.2.1. Wamp Package 34
3.2.2. Adobe Dreamweaver Creative Suite 6 34
3.2.3. Software Development Life Cycle 35
3.2.4. Spiral Model 35
3.2.5. History of Spiral Model 36
3.3. Clinical Decision Support System (CDSS) Modules 38
3.3.1. User Interface 38
3.3.2. Medical Knowledge Base 38
3.3.3. Classification Algorithm Module 39
3.3.4. Inference Engine 39
3.3.5. Database Design 40
3.3.6. Tables 40
3.3.7. Use Case Diagram for the System 44
3.3.8. Sequence Diagram 46
3.3.9. Activity Diagram 47
3.4. Data Acquisition 48
3.4.1. Preparation of Acquired Dataset 48
3.4.2. Rapid Miner Software Version 6.2 48
3.5. Classification of Dataset using the Naïve Bayes Theorem 49
3.6. Naïve Bayes 49
3.6.1. How Naïve Bayes Theorem Works 49
3.7. Post Research Benefits 51
CHAPTER FOUR: DATA ANALYSIS, RESULTS AND
DISCUSSION OF FINDINGS
4.0. Introduction 52
4.1. Dataset 52
4.1.1. Dataset Acquisition 52
4.1.2. Dataset Pre-processing 53
4.2. Performance of the Classification Models 55
4.2.1. Performance of Naïve Bayes Model 55
4.3. Performance Evaluation with other Classification Algorithm 57
4.3.1. Performance of K-nearest neighbor (K-NN) 57
4.3.2. Performance of Decision Tree 58
4.3.3. Performance of Decision Stump 60
4.3.4. Performance of Rule Induction 61
4.3.5. Comparison Summary Based on Classification Performance 62
4.4. Implementation of the Clinical Decision Support System for the
Management of Diabetes Neuropathy 63
4.4.1. Medical Administrator 63
220.127.116.11. Login Page 63
18.104.22.168. Administrator Dashboard Page 64
22.214.171.124. Add Specialist Page 65
126.96.36.199. Add Symptoms Page 65
188.8.131.52. Add Medicare Page 66
184.108.40.206. Change Password Page 66
4.4.2. Medical User 67
220.127.116.11. User Login Page 67
18.104.22.168. User Home Page 68
22.214.171.124. Personal Details 69
126.96.36.199. Change Password 70
4.5. System Testing 71
4.5.1. Software Component Testing 71
CHAPTER FIVE: SUMMARY, CONCLUSION
5.1. Summary 72
5.2. Conclusion 72
5.3. Recommendations 72
LIST OF TABLES
3.1. Use Case description 45
4.1. Dataset in MS Excel Format 53
4.3. Comparison of Classification models based on Accuracy 63
LIST OF FIGURES
2.1. General Model for CDSS 15
2.2. The Statistical and Structural Approaches to Pattern Classification
Applied to a Common Identification Problem 27
2.3. A Decision Tree Algorithm 30
3.1. The Spiral Model Diagram 37
3.2. Architecture of the Design CDSS for Diabetes Neuropathy 38
3.3. Database of the Proposed CDSS for Diabetes Neuropathy 41
3.4a. A Flow Diagram for the Proposed CDSS for Diabetes Neuropathy
from the User Point of View 42
3.4b. A Flow Diagram for the Proposed CDSS for Diabetes Neuropathy
from the Administrative Point of View 43
3.5. Use Case Diagram for the CDSS for Diabetes Neuropathy 44
3.6. Sequence Diagram of CDSS for the Proposed System 46
3.7. Activity Diagram of CDSS for Diabetes Neuropathy 47
4.1. Architecture for the Data Mining Process 54
4.2.1. Classification Process for Naïve Bayes Algorithm using the Rapidminer
6.2 Software 56
4.2.2. Classification Process for K-nearest neighbor Algorithm using the
Rapidminer 6.2 Software 57
4.2.3. Classification Process for Decision Tree Algorithm using the Rapidminer
6.2 Software 59
4.2.4. Classification Process for Decision Stump Algorithm using the Rapidminer
6.2 Software 60
4.2.5. Classification Process for Rule Induction Algorithm using the Rapidminer
6.2 Software 62
188.8.131.52. Administrator Login Page 64
184.108.40.206. Administrator Dashboard Page 64
220.127.116.11. Add Specialist Page 65
18.104.22.168. Add Symptoms Page 65
22.214.171.124. Add Medicare Page 66
126.96.36.199. Change Password Page 67
188.8.131.52a. User Login Page 68
184.108.40.206b. New User Registration Page 68
220.127.116.11. User Home Page 69
18.104.22.168a. Personal Detail Page 69
22.214.171.124b. Edit Personal Detail Page 70
126.96.36.199. Change Password Page 70
1.1.Background to the Study
The world is fast evolving and in order to cope with the insatiable demand of the human race for the kind of living that can be described as top-notch in which people have all they need at their beck and call, there is the need to develop intelligent decision making applications that will drive systems or devices to carry out tasks that require human intelligence. This concept is known as Artificial Intelligence (AI).In science and technology, the desire for improvement is a constant subject which triggersadvancements.Technology has changed civilization in many different ways. Humans have always been on a path of progression through the help of technology, the twentieth and twenty-first centuries have seen a number of advancements that revolutionized the way people work, live and play.
Artificial Intelligence (AI) is the area of Computer Science focusing on creating expert machines that can engage on behaviours that humans consider intelligent. Artificial Intelligence is the branch of Computer Science that is concerned with the design and development of the intelligent systems. Recent advances in the field of Artificial Intelligence have led to the emergence of expert systems and computational tools; designed to capture and make available the knowledge of experts in a field.Expert system is an area of Artificial Intelligence that emulates the decision-making ability of a human expert (Jackson, 1998). Expert systems are designed to solve complex problems by reasoning about knowledge, represented primarily as if–then rules rather than through conventional procedural code.The use of computer technology in areas of diagnosis, treatment of illnesses and patient pursuit has highly increased. Though, the fields in which computers are being used have very high complexity and uncertainty; the uses of intelligent systems such as fuzzy logic, artificial neural network and genetic algorithm have been developed (Jimoh et al, 2014).
A Clinical Decision Support System (CDSS) is an active knowledge system, where two or more items of patient data are used to generate case-specific recommendation(s) (Chen et al, 2002). This implies that a CDSS is a Decision Support System (DSS) that uses knowledge management to achieve clinical advice for patient care based on some number of items of patient data. This helps to ease the job of healthcare practitioners, especially in areas where the number of patients is overwhelming. Clinical decision support system (CDSS) provides clinicians, staff, patients or other individuals with knowledge and person-specific information, intelligently filtered or presented at appropriate times, to enhance health and health care. A CDSS can also be seen as an application that analyses data to help healthcare providers make clinical decisions (Rouse, 2014).
Diabetes mellitus is a group of metabolic diseases characterized by elevated blood glucose levels (Hyperglycemia) resulting from defects in insulin secretion, insulin action or both. Insulin is a hormone manufactured by the beta cells of the pancreas, which is required to utilize glucose from digested food as an energy source. It is a hormone made by the pancreas that allowsthe body to use sugar (glucose) from carbohydrates in the food that you eat for energy or to store glucose for future use. Insulin helps keeps blood sugar level from getting too high (hyperglycemia) or too low (hypoglycemia) (Hess, 2014). Chronic hyperglycemia is associated with microvascular and macro vascular complications that can lead to visual impairment, blindness, kidney disease, nerve damage, amputations, heart disease, and stroke (Harris, 2007). Symptoms of diabetes include polydipsia (increased thirst), polyuria (increased urine volume), blurring of vision, recurrent infections, and unexplained weight loss. In severe cases, drowsiness, coma and high levels of glycosuria are usually present.
There are three major types of diabetes: type 1 diabetes, type 2 diabetes, and gestational diabetes. All types of diabetes mellitus have something in common. Normally, the body breaks down sugars and carbohydrates into a special sugar called glucose. Glucose fuels the cells in the body, but the cells need insulin, a hormone in the bloodstream in order to take in the glucose and use it for energy. With diabetes mellitus, either the body doesn’t make enough insulin or cannot use the insulin it does produce, or a combination of both. Since the cells can’t take in the glucose, it builds up in the blood. High levels of blood glucose can damage the tiny blood vessels in the kidneys, heart, eyes, or nervous system. Diabetes if left untreated, can eventually cause heart disease, stroke, kidney disease, blindness, and nerve damage (Diabetic Neuropathy) a type of nerve damaging disorders associated with diabetes mellitus (Papadakis, et al, 2014).
Diabetic neuropathy is the most common complication of diabetes mellitus, affecting as many as 50 percent of patients with type 1 and type 2 diabetes mellitus.(Khardori, 2014). About half of all people with diabetes have some form of nerve damage and up to 26 percent of people with type 2 diabetes have evidence of nerve damage at the time that diabetes is diagnosed(Davies et al, 2006). It is more common in those who have had the disease for a number of years and this can lead to different kinds of problems like sensory loss and damage to the limbs. It can also cause impotence in diabetic men. Major risk factors of this condition are the level and duration of elevated blood glucose.Getting diabetes under better control also may help limit the amount of damage caused by neuropathy once it’s developed. The best way to prevent or stop the progression of diabetic neuropathy is to keep diabetes under control. Nerve damage or diabetic neuropathy resulting from chronically high blood glucose can be one of the most frustrating and debilitating complications of diabetes because of the pain, discomfort and disability it can cause, and because available treatments are not uniformly successful. Although physicians have found some medications and other treatments that help ease these symptoms in some people, prevention continues to be the key. (Joslin, 2015). Poorly managed diabetes can lead to a host of long-term complications among these are heart attacks, strokes, blindness, kidney failure, and blood vessel disease that may require an amputation, nerve damage, and impotence in men. If the blood glucose is kept close to normal as possible, it can help in reducing the risk of developing some of these complications by 50 percent or more.
Computer based methods are increasingly used to improve the quality of medical services. The use of computer technology in areas of diagnosis, treatment of illnesses and patient pursuit has highly increased. Though, the fields in which computers are being used have very high complexity and uncertainty; the uses of intelligent systems such as fuzzy logic, artificial neural network and genetic algorithm have been developed (Jimoh et al, 2014). Artificial Intelligence (AI) is the area of Computer Science focusing on creating expert machines that can engage on behaviours that humans consider intelligent. Artificial Intelligence is concerned with the design and development of the intelligent systems. Recent advances in the field of Artificial Intelligence have led to the emergence of expert systems and computational tools; designed to capture and make available the knowledge of experts in a field. Hence, this work focuses on the design and implementation of a web-based clinical decision support system for the management of early diabetes neuropathy.
1.2. Statement of the Problem
Diabetes Neuropathy is a chronic health problem with devastating, yet preventable consequences. Over 135 million people worldwide suffer from diabetes, with 25% developing podiatric problems related to the disease, such as diabetic neuropathy. This neuropathy often causes severe pain and can be incapacitating.Globally, rates of diabetes neuropathy were 15.1 million in 2000 (Skaff et al, 2003). According to Nau et al (2007), 7.8% of 23.6 million people of USA population were recorded for having type 2 diabetes that resulted to diabetes neuropathy. (Nau et al, 2007).The World Health Organization (WHO) estimates the number of diabetes patients will reach 300 million by 2025(medoc, 2014). Four to five percent of health budgets are spent on diabetes-related illnesses, such as the management of diabetic neuropathy and its consequences.
According to the World Health Organization, there is one diabetes specialist available for 10,000 Nigerians (WHO, 2012). Methods are needed to quantitatively evaluate the integrity of both small and large-caliber sensory nerve fibers in order to detect and manage this condition early in its progression. Since diabetic neuropathy is an irreversible condition, early detection is a key factor for controlling and managing patients early before the disabling effects present.Due to this shortage of specialists, there is a need for a Clinical Decision Support System that willdiagnose and manage diabetes neuropathy. Existing Clinical Decision Support Systems make use of patients symptoms, medical history, physical exam and the blood sugar level to diagnose patients and come up with a valid result as regards whether such person(s) have diabetes neuropathy or not. However, very little research have been carried out using the genetic predisposition, loss of nerve function and plasma insulin level of the individual in question to predict his or her susceptibility to diabetes, thus making this aspect presently pose itself as a gray area. This research consequently proposes a web-based adaptive clinical decision support system to diagnose and manage diabetes neuropathy based on the genetic predisposition, loss of nerve function and plasma insulin level of the person(s) in question.
1.3. Objective of the Study
The main objective is to develop a Web-based Clinical Decision Support System to diagnose and manage Diabetes Neuropathy using Naïve Bayes Algorithm.
The specific objectives are to:
- design a web-based clinical decision support system to diagnose and manage diabetes neuropathy;
- classify diabetes neuropathy using Naïve Bayes Theorem and
- carryout performance evaluation between Naïve Bayes theorem and four well known classification algorithms (K-nearest neighbor (KNN), Decision Tree (DT), Decision Stump (DS), and Rule Induction (RI) based on appropriate dataset using the Rapidminer 6.2 software.
To achieve the set objective, the following procedures was adopted.
- Design and implement a web-based clinical decision support system to diagnose and manage diabetes neuropathy.
The web-based CDSS interface was developed using:
- Apache serves as the server used to execute the web code created with HTML and PHP.
- MySQL as its database management system
- PHP Programming Language as its server side scripting language and was used to connect to the database.
- Cascading Style Sheet (CSS) was used to make all the designs of the CDSS
- Adobe Dreamweaver CS6 was the Integrated Development Environment (IDE) used in coding.
- Critical review on existing works was carried out and then dataset was acquired from the University of Port Harcourt Teaching Hospital (UPTH) and Babcock University Teaching Hospital (BUTH). The pre-processed dataset was classified using Naïve Bayes Theorem.
- Performance evaluation was carried out between Naïve Bayes theorem and four well known classification algorithms (k-nearest neighbor (KNN), Decision Tree (DT), Decision Stump (DS) and Rule Induction (RI) based on the acquired dataset using the Rapidminer 6.2 software to pick the optimal algorithm that will serve as the back-end engine to the CDSS.
1.5. Scope of the Study
This dissertation intends to make contributions in terms of generating patient-specific Clinical Pathways (CPs) for diabetes that targets the knowledge needs and clinical duties of General Practitioners (GPs), especially those working in Nigeria and sub-Saharan Africa as a whole. The Clinical Pathways was based on existing Clinical Practice Guidelines (CPGs),it was made to incorporate expert medical knowledge of specialists that treat diabetes who are domicile in Nigeria.
1.6. Significance of the Study
This research serves as the platform upon which an intelligent Clinical Decision Support Systemwas built and operationalized for the diagnosis and management of early stages of diabetes neuropathy. It makes it possible for Medical Practitioners (GPs) who have little idea in the area of diabetes to have insights into the diagnosis and management including patient-specific care plans for patients with diabetes neuropathy.This study could support academic development and also contribute to the improvement of education in architecture not only in this faculty but also in other discipline.It could also help improve the degree of awareness to Nigerians and also rendering useful preventive measures to anyone who seek for it. The uniqueness of the this work is that, it does not only limit itself to diagnosis of the disease, but also renders useful management solutions, prescriptions and preventive measures to the user.
1.7.Organization of the Subsequent Chapters
Chapter One: gives the introduction or background to the study which includes the pertinent details and statistics about diabetes.
Chapter Two: deals with the literature review which includes the basic terms and concepts upon which this research work is hinged also the related literature that were thoroughly perused while doing this work.
Chapter Three: handles the research methodology which specifies how precisely we intend to successfully achieve the objectives of this study including the design tools that will be employed.
Chapter Four:deals with the analysis of the proposed work and its juxtaposition with other existing works as well as the results obtained from running the needed experiments.
Chapter Five: deals with the conclusion, recommendation and the suggestion for further research.