Virtual Hue: A Web Application for Anemia Prognosis

Anemia is a state of bad health condition where there is the presence of a low amount of red blood cells in the blood. We aim to build a simple Anemia prediction Web Application, that predicts whether a patient is anemic or not by which doctor can make a better decision in the diagnosis of the disease. The purpose of this study is to create a model that uses red blood cell indicators to predict anemia in adults. There are 1422 data records in the collection of data from Kaggle. After that, they undergo preprocessing, normalization, balancing, and the application of certain machine learning algorithms. It is followed by outcome analysis, validation, and verification. With an accuracy of 98.7%, the Ada Boost and Random Forest Classifier ensemble model exhibits the best performance. For the prediction of anemia, choosing the top-performing algorithm, stacking it with other algorithms, and using a voting classifier are all essential to increase accuracy regardless of any time constraints.