Identifying Malariae Disease Through Red-blood Microscopic Image with XGBoost and Random Forest Methods

Blood cells that flow in the human body provide information to diagnose a disease. The information provided can be obtained through images of these blood cells using image processing techniques. Malaria is a very deadly disease and can affect everyone. Patients with malaria will experience anaemia because the red blood cells or erythrocytes are contaminated with plasmodium. This study offers an alternative solution to malaria disease identification through the image classification of red blood cells, by applying image processing and image classification methods with XGBoost and random forest. The research was conducted using the R programming language in RStudio and Python. The accuracy of XGBoost and random forest methods were 71.26% and 77.58%, respectively. Therefore, the random forest provided a better optimal classification model with higher accuracy. The model is used to build an application which is R web-based, RShiny. In practice, this application can be used by health workers in classifying patients based on red blood cell images such that the health centre would be easier to manage the existing patients.