An automated diagnosis & classification of dengue using advance artificial neural network

In this research, an advanced artificial neural network (ANN)-based approach for prognosis and classification of dengue disease is presented. Dengue diagnosis usually relies on clinical assessment; subsequently, there might be a high probability of misdiagnoses due to the complex hodgepodge of symptoms of dengue with other vector-borne diseases. It is needed to develop a system that can help doctors to identify dengue disease much faster than the manual system, which takes longer time and more cost to detect the diseases. Such a system may help users to take an early action before it becomes serious. The study involved three phases: pre-processing, neural network processing, and post-processing. In the pre-processing phase, data were gathered from three high-severity dengue outbreak sites in Pakistan (Benazir Bhutto Hospital, CITI Lab Rawalpindi, and Meo Hospital Lahore) where the dengue outbreak severity was high during the year of 2011. After cleaning and normalizing, 768 samples were obtained, split into 560 for training and 208 for testing. Nineteen critical parameters were selected with input from physicians, medical staff, and prior research. This study presents a supervised feed-forward neural network (FFNN) with two hidden layers, trained using backpropagation and optimized with the Levenberg-Marquardt algorithm, achieving nearly 100% accuracy, minimal runtime, and a very low MSE (0.00000000000032521). The model reached 100% sensitivity, 99.8% precision, and 98.7% specificity, surpassing prior results in dengue diagnosis. The findings support improved diagnostic accuracy and confidence, providing a framework for physicians. Key factors in achieving optimal results include careful selection of architecture, data normalization, parameter selection, and critical evaluation.