Non-invasive prediction of hemoglobin level using machine learning techniques with the PPG signals characteristics features

Abstract : Hemoglobin can be measured normally after the analysis of the blood sample taken from the body and this measurement is named as invasive. Hemoglobin must continuously be measured to control the disease and its progression in people who go through hemodialysis and have diseases such as oligocythemia and anemia. This gives a perpetual feeling of pain to the people. This paper proposes a non-invasive method for the prediction of the hemoglobin using the characteristic features of the PPG signals and different machine learning algorithms. In this work, PPG signals from 33 people were included in 10 periods and 40 characteristic features were extracted from them. In addition to these features, gender information (male or female), height (as cm), weight (as kg) and age of each subjects were also considered as the features. Blood count and hemoglobin level were measured simultaneously by using the “Hemocue Hb-201TM” device. Using the different machine learning regression techniques (classification and regression trees – CART, least squares regression – LSR, generalized linear regression – GLR, multivariate linear regression – MVLR, partial least squares regression – PLSR, generalized regression neural network – GRNN, MLP – multilayer perceptron, and support vector regression – SVR). RELIEFF feature selection (RFS) and correlation-based feature selection (CFS) were used to select the best features. Original features and selected features using RFS (10 features) and CFS (11 features) were used to predict the hemoglobin level using the different machine learning techniques. To evaluate the performance of the machine learning techniques, different performance measures such as mean absolute error – MAE, mean square error – MSE, R2 (coefficient of determination), root mean square error – RMSE, Mean Absolute Percentage Error (MAPE) and Index of Agreement – IA were used. The promising results were obtained (MSE-0.0027) using the selected features by RFS and SVR. Hence, the proposed method may clinically be used to predict the hemoglobin level of human being clinically without taking and analyzing blood samples.
 EXISTING SYSTEM :
 ? Existing clinical approaches to measure blood haemoglobin levels require specialized equipment. It has accuracy but is expensive and needs a lot of infrastructure requirements, all of which are especially problematic in rural and low-resources settings, where anaemia is more prevalent. Here, the blood sample of the person is taken, and then certain tests are conducted using chemicals like Ethylenediaminetetraacetic acid (EDTA). ? It is not only time consuming but causes a lot of unnecessary pain to the person. Aside from being cost-prohibitive in resource-poor settings, the necessary invasive blood sampling to measure haemoglobin levels causes discomfort in younger pediatric patients. It also produces a lot of waste which is non-biodegradable. Therefore, it is not eco- friendly.
 DISADVANTAGE :
 ? The least squares method divides the problems into two categories: linear or ordinary least squares and nonlinear least squares, depending on whether each unknown value of the redundancies is linear. ? The linear least squares problem occurs in statistical regression analysis; there is a closed-form solution available. ? PPG is a photoelectrical method, which is used for measuring the tissue blood volume based on the change in the blood volume at every heartbeat.
 PROPOSED SYSTEM :
 • In this method, an area of skin on the fingertip is transilluminated by light which is emitted by a red LED and a green LED.This light passes through the tissues and is reflected back. • The wavelength of the light reflected back from the tissue is recorded. The difference in wavelength is used to calculate the hemoglobin count. • The software is an application named detectIR which contain a database for storing the optimal hemoglobin level, providing tips and articles based on the hemoglobin count, predicting the chance of heart attack using SVM algorithm in Machine Learning and providing additional information based on the symptoms entered by the person using Web Crawling.
 ADVANTAGE :
 ? In this work, non-invasive hemoglobin concentration level prediction system has been proposed based on combining regression methods and feature selection with time domain features extracted from PPG signal. ? The feature selection algorithms are often used for the purpose of selecting the relevant features associated with the output label and minimizing the computational time during classification process of classification.
Download DOC Download PPT

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com