Anemia Detection and Classification Using Data Analysis of Blood Samples

This research explores the feasibility and impact of using data science over the blood samples to quickly and skillfully identify the fundamental health problems associated with it and construct models to further this cause and geolocate different possibilities of healthcare using effective algorithms. Once data is physically accumulated, predictions of major diseases and the people prone to or already affected by them are notified to the health officials. For the validity and effectiveness of the proposed system, real samples of blood are used. These samples are collected from the different locations within the Nagpur city of Maharashtra State, India. Data was collected during a volunteer-run hemoglobin blood test camp for women living in impoverished areas, a total of 551 samples were collected. The experimental results of the proposed technique have been evaluated based on Hb, RDW%, MCV, RBC, and M-Index.