Admissions Open
Admissions Open
Skin diseases are becoming increasingly prevalent all over the world due to a multitude of factors including disparity in income groups, lack of access to primary health care, poor levels of hygiene, varied climate, and different cultural factors. The ratio of dermatologists to the number of people affected is very low, and hence, there is a need for expedited and accurate diagnosis of skin diseases. Prurigo Nodularis can be a bothersome-to-enervating disease and its treatment requires a multifaceted approach depending on the severity and underlying etiology of the disease. Often, once patients are diagnosed with Prurigo Nodularis, they are also advised a complete work-up to rule out any underlying systemic disease. Knowing the advantages of early detection of the disease to facilitate quick and suitable treatment, this paper proposes the use of deep learning for accurate and early detection of Prurigo Nodularis. Different architectures of convolutional neural networks were used on the dataset of diseased skin images and the results were compared to ascertain the best method. Thus, with a combination of transfer learning on the image dataset and applying the extra tree classifier on the symptoms dataset, we were able to correctly predict the occurrence of Prurigo Nodularis with an accuracy of around 96%.