دانلود رایگان مقاله انگلیسی تشخیص بیماری با استفاده از روش منطق فازی: بررسی سیستماتیک و متاآنالیز - الزویر 2018

Abstract

Background and Objective: Diagnosis as the initial step of medical practice, is one of the most important parts of complicated clinical decision making which is usually accompanied with the degree of ambiguity and uncertainty. Since uncertainty is the inseparable nature of medicine, fuzzy logic methods have been used as one of the best methods to decrease this ambiguity. Recently, several kinds of literature have been published related to fuzzy logic methods in a wide range of medical aspects in terms of diagnosis. However, in this context there are a few review articles that have been published which belong to almost ten years ago. Hence, we conducted a systematic review to determine the contribution of utilizing fuzzy logic methods in disease diagnosis in different medical practices. Methods: Eight scientific databases are selected as an appropriate database and Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method was employed as the basis method for conducting this systematic and meta-analysis review. Regarding the main objective of this research, some inclusion and exclusion criteria were considered to limit our investigation. To achieve a structured meta-analysis, all eligible articles were classified based on authors, publication year, journals or conferences, applied fuzzy methods, main objectives of the research, problems and research gaps, tools utilized to model the fuzzy system, medical disciplines, sample sizes, the inputs and outputs of the system, findings, results and finally the impact of applied fuzzy methods to improve diagnosis. Then, we analyzed the results obtained from these classifications to indicate the effect of fuzzy methods in decreasing the complexity of diagnosis. Results: Consequently, the result of this study approved the effectiveness of applying different fuzzy methods in diseases diagnosis process, presenting new insights for researchers about what kind of diseases which have been more focused. This will help to determine the diagnostic aspects of medical disciplines that are being neglected. Conclusions: Overall, this systematic review provides an appropriate platform for further research by identifying the research needs in the domain of disease diagnosis.

6. Conclusion

This review has argued about prior studies that were conducted about applying fuzzy methods in disease diagnosis. In this investigation, the main goal was to assess the effect of fuzzy methods and their frequency on improving diagnosis to decrease errors in misdiagnosis, with meta-analysis systematic review. Therefore, we designed search strategy based on our main goal. In this regard, eight scientific databases include PubMed, Google Scholar, IEEE, Science Direct, Web of Science, Taylor & Francis, Wiley Online Library, and Emerald were selected to retrieve the published scientific papers in a period of 2005 to 2017. In order to meet the goals of this study, all found papers were classified by authors, the publication year, journals or conferences type, the fuzzy methods, main objectives of the research, problems and research gaps, tools utilized to model fuzzy system, medical disciplines, sample size, the inputs and outputs of the system, findings, results and finally the impact of applied fuzzy method to improve diagnosis. Additionally, we classified our results based on their publishers and the databases with reviewing relevant articles which have been retrieved by the search strategy. The results showed that the rate of publishing articles in this domain has been increased. In this study, more favorable journals and conferences related to our issue were determined with their frequency and percentage. Another goal in this review was to determining the most utilized fuzzy methods among researchers. Returning to the question posed at the beginning of this study, it is now possible to state that the use of fuzzy logic is a beneficial way to improve the accurate diagnosis of diseases, because most of the studies declared positive impact of fuzzy methods in diagnosing various diseases. The most obvious finding to emerge from this study is that applying the fuzzy method, in addition to improve the diagnosis of diseases, can provide an early detection of the disease in order to prevent the progression of complex diseases. Another key point to remember is that we identified 13 fuzzy methods which are the most used in recent studies and we represented our results based on this classification. In addition, the impact of each fuzzy method based on the degree of effects reported by articles, was investigated. Hence, we hope that this review will serve as a base for future studies; a summary of the articles reviewed based on the impact of the applied fuzzy method along with their classification are also provided in the Appendix B in order to be used by researchers in future research.