CHAPTER ONE
INTRODUCTION
1.1 BACKGROUND TO THE STUDY
The major challenge facing the healthcare industry is the provision for quality services at affordable costs. A quality service implies diagnosing patients correctly and treating them effectively (John, 2009). Poor clinical decisions can lead to disastrous results which is unacceptable. Even the most technologically advanced hospitals in Nigeria have no such software that predicts and treat a disease. There is a huge amount of untapped data that can be turned into useful information (Quinlan, 2006). Medical diagnosis is known to be subjective; it depends on the physician making the diagnosis. Secondly, and most importantly, the amount of data that should be analyzed to make a good prediction is usually huge and at times unmanageable (Quinlan, 2006). In this context, machine learning can be used to automatically infer diagnostic rules from descriptions of past, successfully treated patients, and help specialists make the diagnostic process more objective and more reliable (Quinlan, 2006).
The decision support systems that have been developed to assist physicians in the diagnostic and treatment process often are based on static data which may be out of date (Stephen, 2005). A decision support system which can learn the relationships between patient history, diseases in the population, symptoms, pathology of a disease, family history and test results, would be useful to physicians and hospitals (Stephen, 2005). The concept of Decision Support System is very broad because of many diverse approaches and a wide range of domains in which decisions are made (Sim et al, 2001). Decision support system terminology refers to a class of computer-based information systems including knowledge based systems that support decision making activities. In general, it can say that a decision support system is a computerized system for helping make decisions (Rao&Turoff, 2000). A decision support system application can be composed of the subsystems. However, the development of such system presents a daunting and yet to be explored task. Many factors have been attributed but inadequate information has been identified as a major challenge. To reduce the diagnosis time and improve the diagnosis accuracy, it has become more of a demanding issue to develop reliable and powerful decision support systems to support the yet and still increasingly complicated diagnosis decision process (John, 2009). The medical diagnosis by nature is a complex and fuzzy cognitive process, hence soft computing methods, such as decision tree classifiers have shown great potential to be applied in the development of decision support system of Ebola and Lassa fever.
Ebola Virus Disease (EVD) also known as the Ebola hemorrhagic fever is a very deadly infectious disease to humankind. Therefore, a safer and complementary method of diagnosis is to employ the use of an expert system in order to initiate a platform for pre-clinical treatments, thus acting as a precursor to comprehensive medical diagnosis and treatments (WHO, 2014). The deadly, scary spate and debilitating effects of the Ebola Virus Disease (EVD) in the West African sub-region, especially in 2014, left terrifying, untold hardships and discrimination mostly among the affected West African countries. Many are yet to fully recover from the Ebola scare and the psychological trauma it generated. It is a known fact that the Ebola Virus Disease, is a very contagious and deadly disease. Presently, there is no globally recognized or known cure for the disease. Other problems associated with the disease are lack of proper knowledge in diagnosing and managing the disease especially among countries in Sub-Sahara Africa. In some cases, lack of proper training for medical experts to effectively and efficiently manage the disease constitutes a problem.
Also, Lassa fever is a viral hemorrhagic fever that was first described in 1969 in the town of Lassa in the North-East of Nigeria. It is endemic in the West African countries of Sierra Leone, Guinea, Liberia, and Nigeria. Cases imported to Europe indicate that Lassa fever also occurs in Côte d'Ivoire and Mali (WHO, 2014). The causative agent is Lassa virus, an RNA virus of the family Arenaviridae. Its natural host is the rodent Mastomysnatalensis, which lives in close contact to humans. Mastomys shed the virus in urine and contamination of human food is a likely mode of transmission. The virus may be further transmitted from human to human, giving rise to mainly nosocomial epidemics with case fatality rates (CFR) of up to 65%. However, most of the Lassa virus infections in the communities are probably mild.
In the hospital, Lassa fever is extremely difficult to distinguish from other febrile illnesses seen in West African hospitals, at least in the initial phase. Gastrointestinal symptoms, pharyngitis, and cough are frequent signs. Late complications include pleural and pericardial effusions, facial edema, bleeding, convulsion, and coma. In the terminal stage patients often go into shock, although bleeding itself is usually not of a magnitude to produce shock. The only drug with a proven therapeutic effect in humans is the nucleoside analogue ribavirin. Drug efficacy decreases if treatment is commenced at day 7 or later, making early diagnostics critical for survival.
Lassa virus can be detected in blood at an early stage of illness. Death occurs about two weeks after onset of illness with fatal cases showing higher levels of viremia than those who survive. In survivors, virus is cleared from circulation about three weeks after onset of symptoms. IgM and IgG antibodies are detectable only in a fraction of patients during the first days of illness, and patients with fatal Lassa fever may not develop antibodies at all making early diagnostics critical for survival.
With these in views, there is need for a practical implementation of a complementary system that can diagnose and provide excellent recommendations to individuals in order to curb the spread of Ebola and Lassa fever diseases. Such system will also act as a supporting tool for medical experts and resident doctors in training.
This work presents a design and implementation of decision support system for the diagnosis, and provision of recommendations on the appropriate type of recommended treatment to the Ebola Virus Disease and Lassa Fever disease.
1.2 STATEMENT OF THE PROBLEM
Samore, Kim & Stephen (2005) measured the added value of Decision Support Systems when coupled with a community intervention to reduce inappropriate diagnosis and treatment of highly contagious diseases. Sim et al. (2001) described the research and policy challenges for capturing research and practice-based evidence in machine-interpretable repositories and made recommendations for accelerating the development and adoption of decision support system for evidence based medical practice. Jeste et al. (2008) reviewed studies that compared the effects of multimedia (video or computer based) educational aids with those of routine procedures to inform healthcare consumers about medical evaluations or management and concluded that multimedia educational aids hold promise for improving the provision of complex medical information to patients and caregivers. Hence this study seeks to develop and implement a decision support system for the diagnosis and treatment of Ebola and Lassa fever.
1.3 AIM AND OBJECTIVES OF THE STUDY
The aim of this study is to assess the feasibility of developing a decision support system for the diagnosis and treatment of Ebola and Lassa fever while the following are the specific objectives:
1. To design and implement a decision support system for the diagnosis and treatment of Ebola and Lassa fever.
2. To identify the requirements for this application in terms of clinical data and validate it with mock patient data that addressed Ebola and Lassa fever scenario to ensure that it could deliver the expected results.
1.5 SIGNIFICANCE OF THE STUDY
The outcome of this study will be useful for the doctors and other healthcare providers, patients and the general public given that it will facilitate the accurate management of Ebola and Lassa fever. This research will be a contribution to the body of literature in the area of design of decision support system for diagnosing and treating Ebola and Lassa fever, thereby constituting the empirical literature for future research in the subject area.
================================================================
Item Type: Project Material | Size: 117 pages | Chapters: 1-5
Format: MS Word | Delivery: Within 30Mins.
================================================================
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.