Document Type: Research Paper
Department of Electrical and Computer Engineering, Hakim Sabzevari University, Sabzevar, Iran
Department of Neurobiology, Care Sciences and Society (NVS), Karolinska Institute, Stockholm, Sweden
Background and Objectives: Accurate detection of type and severity of Hepatitis is crucial for effective treatment of the disease. While several computational algorithms for detection of Hepatitis have been proposed to date, their limited performance leaves room for further improvement. This paper proposes a novel computational method for the diagnosis of Hepatitis B using pattern detection techniques. Methods: Clinical data of healthy individuals and those suspected of Hepatitis B were collected from the laboratories of Vasei Hospital in Sabzevar (Iran). Using the algorithm, first, data were normalized, then SVM classifier was used for detection of Hepatitis B, and finally, adaptive FCM was applied for measuring the severity of the disease. Findings: Application of the algorithm to plenary database yielded 98.36%, detection accuracy, 98.44% sensitivity, and 94.06% specificity. Conclusions: Low PPV and high NPV of the proposed method indicate its high reliability for use in practical diagnosis of Hepatitis B and its severity.