Search

In this research work, we have implemented an intelligent system for diagnosis of diabetic retinopathy. Diabetic retinopathy is a damage caused by diabetes to the retinal blood vessels. This causes the leak of blood and other fluid that resulted into swelling of retina tissue and cloudy vision. This can be classified into two; non-proliferative diabetic retinopathy and proliferative diabetic retinopathy. The dataset used for the implementation of this intelligent system is obtained from the freely available UCI machine learning repository. This system will aid physicians to accurately diagnose the disease. Such a system will make the diagnosis faster, accurate and easier as compared to manual diagnosis. Our novel system uses a feedforward neural network trained with backpropagation neural network. The results obtained in this work are compared with previously proposed systems using the same dataset. Experimental results indicate that our novel system outperforms the other systems in diagnosing diabetic retinopathy. [ABSTRACT FROM AUTHOR]

The orthodox system of diagnosis in medicine requires that laboratory procedures should be performed to obtain the results of diagnostic queries. While this practice is standard, the field of machine learning is now revolutionizing medical diagnoses. Data (medical histories) of different parents archived over long periods can be used to make predictions on new cases with reasonable accuracies using suitable machine learning methods. More-over, in many instances where the current situations of patients do not yet justify the cost of expensive laboratory test procedures, machine learning methods can be used to learn past medical data, with which new cases can be diagnosed. Moreover, cost is more reasonable and justifiable with this approach. In this work, we apply radial basis function neural network to the evaluation of semen quality (viability) using some attributes relating to the patients. Important parameters used to assess the performance of the considered model include precision, recall, accuracy and F1 score based on a 10-fold cross-validation scheme. [ABSTRACT FROM AUTHOR]