An Efficient Technique of Hemoglobin Level Screening Using Machine Learning Algorithms

Hemoglobin (Hb), a very significant parameter for the human body and deficiency of it causes anemia. During pregnancy, menstruation and ICU deficiency of it can be very risky and even caused death. So, it is important to diagnose it continuously. Usually, physicians examine it by conducting a blood test to confirm it is painful, time-consuming and costly. The major concept of this study is to screen Hb levels within a short period of time. In this study, the data of clinical blood Hb levels of a total of 104 people (54 males and 50 females) are collected along with an eye conjunctiva image. The images are taken with a Smartphone camera of constant resolution and lighting. Using MATLAB, image processing method, the percentages of the red, green and blue pixels are extracted. Taking those features, the Hb level is plotted. The 104 data have been split into two sets where the first 81 data for training purposes, the remaining 23 data have been considered for testing. To train the model of 81 data, Multivariate Linear Regression (MLR), Decision Tree (Medium), Linear Support Vector Regression (SVR) are taken and the lowest percentage of error of 11.01% has been found in the Decision Tree (Medium) while testing the 23-test data.