Case-Based Reasoning for Diagnosing Chronic Disease

1741 Words4 Pages

Background: Chronic disease is defined as disease that persists over a long condition which progress slowly and generally it can be controlled but not cure. There are types of chronic disease such as heart disease, stroke, cancer, chronic respiratory disease, liver, and diabetes mellitus. CBR is a case-based reasoning solves problems by using or adapting solutions to old problems. The systems of CBR have been used for diverse purposes likely classification, diagnostic, planning, and tutoring in the field of medical. However, the trend CBR in diagnose chronic disease need to be reviewed due to the reliable and accuracy system has to be evaluated with parameter performance. Method: In doing SLR, the review conduct from sources, such as books, journal, conference, report, etc. The publication year from 2010-2014. The population is chronic disease and the interventions are CBR, method, techniques, and tool. Result: In this review, shown that problem, dataset, method, proposed system, parameter performance and result. The 12 primary studies found that most of them using parameter performance in accuracy rate. Otherwise, the parameter include robustness and learning capacity. Conclusion: Trend CBR reviewed that most of problem found in primary studies, which is accuracy in retrieval cases, process time and missing data. In order to evaluate, parameters performance have to measure in particular CBR method. Keywords: Case-Based Reasoning, Chronic Disease, Parameter Performance, Trend, SLR 1. INTRODUCTION The lives of many people in the world have been curtailed by chronic disease. Chronic disease is defined as disease that persists over a long condition which progress slowly and generally it can be controlled but not cure. There are ... ... middle of paper ... ...mpling and contacting the authors directly. 12 primary studies were included and evaluated according to a number of research questions (Table 1). This review has shown that most of the problem found in CBR methods such as accuracy rate in retrieval cases, processing time and missing data/cases. Researchers who are new to the area can find the complete list of relevant papers in the field. They will also find the most frequently used trend CBR in diagnose chronic disease, with references to the studies in which they are used, including problem, method, dataset, parameter performance, proposed system and result (Table 2.). The parameter performance of CBR is accuracy, robustness and learning capacity. The accuracy related to sensitivity, specificity, PPV, and NPV. With this SLR, researchers have gained an overall overview of the area and an outline for future work.

Open Document