Sickle Cell Anemia is a hereditary disorder caused due to abnormal red blood cells which affect more than 300k newborn babies globally every year. The present-day treatments for this health problem require adept medical professional, gives fallible results, and are costly and time-consuming. These are major impediments to the timely diagnosis of this blood disorder. Modern techniques like artificial intelligence and machine learning are used to elucidate medical data and support medical decisions. Here we have reviewed the advancement in machine learning models like Plain Convolution Neural Networks (PCNN), data augmentation of Plain Convolution Networks (DAPN-48), Very Deep Convolutional Networks (VGG19), and Multi-Layer Perceptron (MLP) models that can aid in the estimation of clinical complications and development of effective therapies for sickle cell anemia.

Sickle Cell Anemia, Machine Learning, Multi-Layer Perceptron, Data Mining Techniques, Neural Networks, Diagnosis, Convolution Neural Networks (PCNN), data augmentation of Plain Convolution Networks (DAPN-48), Very Deep Convolutional Networks (VGG19), Residual Networks (RESNET-50)