WhatsApp or SMS: 07087083227
Click here to Get The Complete Research Project Chapter 1-5

Full Project – Decision support system for depression management

Click here to Get this Complete Project Chapter 1-5

CHAPTER ONE

INTRODUCTION

1.1 Background of the Study

Decision support systems are organized collections of procedures, software, databases, and devices that are in place to support managerial decision-making and problem-solving activities. DSSs are generally structured for use at all levels within an organization, although upper managers are more likely to find a need for these systems. DSSs are used to bring structure to the unstructured problems that are found within a firm. Quite often, DSSs are used to assist in routine problems since many contain programmable parameters.

Depression is a common mental disorder in primary health care, but its diagnosis and effective treatment is controversial because of variations in clinical practice, lack of evidence on the best treatments and access to them, and because of its multifaceted nature and contested meaning of symptoms (Dowrick, 2004). Depressive symptoms range along a continuum from every day sadness, loss of interest to suicidal depression. Although many other symptoms occur in varying combinations, the illness is a causal factor in many chronic conditions such as diabetes, cardiovascular diseases, HIV/AIDS resulting in higher costs to the healthcare system (Maja, Meifania, & Tharam, 2008; World Health Organization (WHO), 2009; Kessler, 2002). The recognition and treatment of depression is a challenging area of clinical practice, especially in primary care where there are many patients with various presentations and a multitude of causes for distress (Lester & Howe, 2008).

Figure 1: Depression Questions

In depression diagnosis, physicians utilize a number of cognitive behavioural therapy (CBT) assessment tools such as Becks depression inventory (BDI) and Hamilton’s Rating Scale for Depression (HRSD) or the Montgomery-Asberg Depression Rating Scale (MADRS) to establish severity levels of the disease in order to determine therapy (Ariyanti, Kusumadewi, & Paputungan, 2010; Nameroff, 2006). Classification of the disease is therefore based on the patients’ subjective description of symptoms and the physician’s judgment as to whether they meet the criteria of the diagnostic and statistical manual of mental disorders, version 4 (DSM-IV) (American Psychiatric Association (APA), 1994). Diagnosis of the disorder by primary care physicians is difficult due to the complexity and confusing nature of the disease (Mondimore, 2006; Mila, Kielan, & Michalak, 2009).

Medical diagnosis has undergone different phases of research from mathematical and statistical approaches which are mostly engaged to enhance the quality of medical data estimations, to Artificial Intelligent (AI) approaches. The inadequacy of statistical estimation techniques is that quality cannot be guaranteed when dealing with incomplete, noisy and non-linear data (Antoni, Jorge, & Paulo, 2008). AI approaches provides reasoning capability, which consists of inference from facts and rules using heuristics, pattern matching or other search approaches. Recent developments in medical diagnostics has embraced the AI approaches such as genetic algorithms (GA), neural networks (NN), Fuzzy logic (FL), rule based systems (RBS) and Case Based Reasoning (CBR) to develop tools for diagnosis and for predicting treatment responses (Wan, Wan, & Fadzilah, 2006).

In this work, AI techniques of neural networks, fuzzy logic and CBR are combined to model a DSS for the diagnosis of depression disorders. NNs are constructed to imitate the intelligent human biological processes of learning, self-modification and adaptation. Although NN is good at handling non-linear, noisy or incomplete data it has very weak explanation mechanism which is highly desirable in medical decision support systems (MDSS) (Uzoka, Obot, & Baker, 2009).

Fuzzy logic provides a means for dealing with imprecision, vagueness and uncertainties in medical data (Zadeh, 1965). Neuro-fuzzy inference systems provide self-learning intelligent systems that are capable of handling uncertainties in a diagnosis process (Jang, Sun, & Mitzutani, 1997). CBR entails the use of a set of concrete past situations, called cases, stored in a knowledge base referred to as a case base to solve a new problem (Aamodt, 1994). Combinations of CBR with other intelligent methods have been explored for more effective knowledge representation and problem solving.

Hybrid CBR systems are reported in (Obot, Akinyokun, & Udoh, 2008; Prentzas, & Harzilygeroudis, 2009; Lopez-Fernandez, FdezRiverola, Rboiro-Jato, Glez-Pena, & Mendez, 2011; Begum & Mema, 2011). Among the hybrid CBR systems, a neuro-fuzzy CBR is not widely reported; the closest are combinations of FL with CBR or NN with CBR in the implementation of medical diagnosis systems. Hence, the contribution to knowledge of this work stems not only from the hybridization of NN, FL and CBR but also the fusion of neuro-fuzzy inference system and fuzzy similarity matching in the implementation of a MDSS.

Decision Support Systems (DSS) is developed based on the dominant technology component or driver of decision support, the targeted users, the specific purpose of the system and the primary deployment technology. Five generic categories based on the dominant technology component are proposed, including Communications-Driven, Data-Driven, Document-Driven, Knowledge-Driven, and Model-Driven Decision Support Systems. Each generic DSS can be targeted to internal or external stakeholders. DSS can have specific or very general purposes. Finally, the DSS deployment technology may be a mainframe computer, a client/server LAN, or a Web-Based architecture. The goal in proposing this expanded DSS framework is to help people understand how to integrate, evaluate and select appropriate means for supporting and informing decision-makers.

The limitations of hardware and software, early DSS systems provided executives only limited help. With the increased power of computer hardware, and the sophisticated software available today, DSS can crunch lots more data, in less time, in greater detail, with easy to use interfaces. The more detailed data and information executives have to work with, the better their decisions can be.

Decision Support Systems should be defined as a broad category of information systems for informing and supporting decision-makers. DSS are intended to improve and speed-up the processes by which people make and communicate decisions. We need to improve how we define Decision Support Systems on both a conceptual level and on a concrete, technical level. Both managers and DSS designers need to understand categories of decision support so they can better communicate about what needs to be accomplished in informing and supporting decision makers.

The DSS literature includes a number of frameworks for categorizing systems. Steven Alter (1980) developed the broadest and most comprehensive one more than 20 years ago. A new, broader typology or framework than Alter’s (1980) is needed because Decision Support Systems are much more common and more diverse than when he conducted his research and proposed his framework.

Decision Support Systems do vary in many ways. Some DSS focus on data, some on models and some on communications. DSS also differ in scope, some DSS are intended for one “primary” user and used “stand-alone” for analysis and others are intended for many users in an organization. A Decision Support System could be categorized in terms of the generic operations it performs, independent of type of problem, functional area or decision perspective. His seven types included: file drawer systems, data analysis systems, analysis information systems, accounting and financial models, representational models, optimization models, and suggestion models.

The following expanded DSS framework is still evolving. The author and others have used the framework to classify a large number of software packages and systems. Anecdotal reports indicate that people who have tried to use it in describing a proposed or existing DSS have found it comprehensive, useful and parsimonious. It seems to help one categorize the most common Decision Support Systems currently in use. The framework focuses on one major dimension with 5 generic types of DSS and 3 secondary dimensions. The primary dimension is the dominant technology component or driver of the decision support system; the secondary dimensions are the targeted users, the specific purpose of the system and the primary deployment technology. Some DSS are best classified as hybrid systems driven by more than one major DSS component.

1.2 Statement of the Problem

There is a growing incidence of suicide in Nigeria which has become worrisome to the extent that psychiatrists and other physicians have called for high index of suspicion for signs and symptoms of depression among their patients. Within developing countries such as Nigeria, the mindset about the spiritual causes of ailment has formed a wall in our thought that we dismiss depression as an ailment thereby giving wrong forms of treatment to its patients. According to the World Health Organization(WHO), there are 322 million people living with depression in the world and in its suicide ranking, Nigeria has 15.1 suicides per 100,000 populations per year ranking it the 30th most suicide-prone out of 183 nations in the world.

1.3 Objective of the Study

The project is aimed at implementing a decision making web application for depression. The platform will actually have to prescribe solution to depression by presenting question to the victims. The other objectives of the system are as follows;

Implement a decision support system using the python flask
Develop a system where a patient login after creating account.
Depression symptoms questions are presented to patients
Decision made by the system is presented by the patients

1.4 Significance of the Study

The research work is a web based application where all users or patients have access to dashboard after a proper login. The system will diagnose the patient by presenting questions the make decisions and the results are presented to patients. The platform will present an expert system to be used by the patients. It will provide solution to faster means of been diagnosed and presented with drugs.

1.5 Scope of the Study

The platform will be implemented using the python flask and the system will store information in sqlite3 database for easy access. It will involve the use of vital information given by the patient (who is mature enough to communicate their symptoms adequately) in response to the System’s interrogative process.

1.6 Limitation of the Study

The study is limited by the sample size of patients. The platform is a Web Based Application and runs on Web Browsers. The limitation to the System is the age bracket of the User (must have attained some level of maturity). This is to make sure that the User is able to register, login and also to ensure that the input given to the system is not invalid and hence resulting to invalid output.

1.7 Definition of Terms

Decision Support System: is an information system that supports business or organizational decision-making activities. DSSs serve the management, operations and planning levels of an organization (usually mid and higher management) and help people make decisions about problems that may be rapidly changing and not easily specified in advance i.e. unstructured and semi-structured decision problems. Decision support systems can be either fully computerized or human-powered, or a combination of both.

Depression Management: May involve a number of different therapies: medications, behavior therapy, and medical devices. Major depressive disorder, often referred to simply as “depression”, is diagnosed more frequently in developed countries, where up to 20% of the population is affected at some stage of their lives. According to WHO (World Health Organization), depression is currently fourth among the top 10 leading causes of the global burden of disease; it is predicted that by the year 2020, depression will be ranked second.

Artificial Intelligence: is intelligence demonstrated by machines, in contrast to the natural intelligence (NI) displayed by humans and other animals. In computer science AI research is defined as the study of “intelligent agents”: any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals. Colloquially, the term “artificial intelligence” is applied when a machine mimics “cognitive” functions that humans associate with other human minds, such as “learning” and “problem solving”. See glossary of artificial intelligence.

Knowledge Based Systems: (KB) is a computer program that reasons and uses a knowledge base to solve complex problems. A more specific definition of the domain restricts it to expert systems (ES) (frequently called knowledge-based systems). Although the terms sound very general, actually they have acquired a very technical, restricted meaning of referring to narrow set of computer systems fulfilling quite rigid conditions. Such definition is not representative of cornucopia of knowledge intensive applications and technologies flooding the digital world. A more general view regards KBS as an area of engineering dealing with digitizing knowledge and building knowledge intensive systems in general, beyond more conservative ES. The more general view extends and generalizes the definition of knowledge-based systems.

Web Based System: information displays many benefits of multimedia technology. Using today’s fast broadband connection, it’s possible to stream sophisticated content to a computer anywhere in the world. This is an advantage for many people as the information can be received and read wherever and whenever it is convenient for them, which can be a crucial factor for a busy executive. A significant amount of interactive multimedia content is now delivered via the internet.

Database:is an organized collection of data, stored and accessed electronically. Database designers typically organize the data to model aspects of reality in a way that supports processes requiring information, such as (for example) modeling the availability of rooms in hotels in a way that supports finding a hotel with vacancies.

Get the Complete Project

This is a premium project material and the complete research project plus questionnaires and references can be gotten at an affordable rate of N3,000 for Nigerian clients and $8 for international clients.

Click here to Get this Complete Project Chapter 1-5

You can also check other Research Project here: