Electroencephalography and Blood Cells Analysis for Cerebral Malaria Detection Using Deep Learning and Neural Networks

Abstract

Cerebral malaria is a clinical syndrome that is marked by the asexual parasitic form, 'plasmodium falciparum.' Early diagnosis can help in avoiding fatal and long-lasting neurological outcomes, such as severe psychosis, metabolic acidosis, and hypoglycemia. Therefore, the developed model aims to detect the same for narrowed down symptoms associated with the same. The design is divided into the following functions: the recognition of potential seizures in the patient and the identification of parasitic blood cells. In the first half, the deep-learning algorithm consists of a Neural Network Sequential model to grasp the exclusive electroencephalogram (EEG) features of epileptic seizures and also reveal the correlation between data samples that are successive to each other. The latter work focuses on inspecting the decompressed blood cells images that are fed into a deep convolutional neural network to distinguish parasitized cells from healthy cells. With this, the transfer of medical findings is also made effortless since compression of images is done without loss of valuable information.