Klasifikasi Penyakit Anemia Menggunakan Machine Learning

Abstract

Anemia is a blood disorder in which the level of hemoglobin, or red blood cells in the blood is reduced and the body's iron stores are insufficient due to diet, lifestyle, and various attitudes and behaviors towards iron health. Protein is responsible for the formation of new hemoglobin molecules by transporting iron to the bone marrow where the body requires adequate use of iron and protein. These non-communicable diseases are commonly found in lower middle-income countries. Anemia greatly affects work performance by limiting muscle tone, so that people with anemia experience a decrease in their ability to perform physical tasks. Red blood cell indicators are often used to assess the classification of anemic patients HGB, RBC, PCV, MCV, MCH, MCHC, RDW, TLC, PLT. This study aims to classify anemia by comparing three machine learning algorithms Decision Tree, Random Forest and K Nearest Neighbors (KNN) and the method with the highest accuracy will be used as a suggestion in the proposed and used decision making. The model was tested using kaggle and hospital data collection with a total of 1536 data with 11 attributes and 1 class label. This model uses four different data sets of feature selection. The data set is classified using three different machine learning algorithms. The model will be evaluated by applying a confusion matrix consisting of accuracy, precision, recall, and f1-score. The highest accuracy obtained in this study was 99% with the random forest model, then followed by a decision tree of 98% and Knn of 95%.