Title:	A HYBRID METHODOLOGY FOR DIFFERENTIAL DIAGNOSIS OF CONFUSABLE DISEASES
Author(s):	Okure U. Obot, Udoinyang G. Inyang, Joseph Osuji, Faith-Michael E. Uzoka3
ISBN:	978-989-8704-11-5
Editors:	Piet Kommers, Pedro Isaías, Claire Gauzente, Miguel Baptista Nunes, Guo Chao Peng and Mário Macedo
Year:	2014
Edition:	Single
Keywords:	Tropical diseases; viral hepatitis; malaria; typhoid fever; urinary tract infection; fuzzy logic.
Type:	Short Paper
First Page:	362
Last Page:	366
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	Some tropical diseases are no longer localized in tropical regions of the world and are increasingly seen in the emergency units of major medical centers in the developed world. Some of these diseases present with overlapping and ‘confusable’ symptoms. The combination of non-specific clinical manifestations that characterize these conditions and the probable lack of expertise and experience among primary care and emergency physicians exponentially increases the potential for mis-diagnosis and subsequent increased morbidity and mortality rates resulting from these diseases. This paper proposes an intelligent system based on fuzzy Logic and fuzzy clustering to assist physicians in investigating, diagnosing, and managing confusing symptoms for accurate and timely diagnosis of confusable diseases. Data on patients diagnosed and confirmed by laboratory tests of viral hepatitis, malaria, typhoid fever and urinary tract infection were collected from general hospitals in Nigeria. The data were used in training, testing and validation of the system. The validity of the clusters were also carried out. The results show that the system compares favorably with diagnosis arrived at by experienced physicians and in addition provides patient’s level of severity in each confusable disease.
	Go Back