Abstract
Blood is a substance that moves waste materials from the cell and carries nutrition and oxygen to it. Blood is made up of platelets, which serve to halt hemorrhaging, red blood cells, which transport oxygen, and white blood cells, which act as the body's first line of defense against infectious diseases. The most prevalent blood condition, anemia, is brought on by a deficiency in red blood cells, which prevents the body from receiving enough oxygen. Chronic anemia results from a gradual decrease in red blood cells and is frequently associated with inflammatory diseases. Acute anemia is caused by a sudden drop in RBCs. In order to identify and categories anemia, this study applies machine learning techniques such as K-nearest neighbors (KNN), Naive Bayes, and decision trees. States/UTs, Area, and other monitoring data were used as input for evaluation. Infants aged 6 to 59 months (about 5 years) with anemia (11.0 g/dl), Non-pregnant women aged 15 to 49 with anemia (12.0 g/dl), Pregnant women aged 15 to 49 with anemia (11.0 g/dl), All women aged 15 to 49 with anemia (11.0 g/dl) All ladies between the ages of 15 and 19 who are anemic : 22 (%) Males aged 15 to 49 who are anemic (13.0 g/dl) make up 22 (%), as do men aged 15 to 19 who are anemic (13.0 g/dl). The study's findings point to a wide range of potential uses for this technology in the area of medical diagnosis.
Keyword
Machine Learning, Anemia, Extraction, Identification
PDF Download (click here)
|