Haemoglobin Levels Analysis Using Robust Partial Least Square Regression Models

The Robust Partial Least Square Regression method is used to handle outliers and increase the explanation proportion, but it does not reduce the average of the mean square error. In this article, three methods are proposed to handle the problem of outliers, reduce the average of the mean square error, and increase the explanation proportion of the predictor and dependent variables. The first proposed method (Iteration) depends on identifying outliers by estimating the initial Partial Least Square Regression and then estimating outliers based on the residuals of those values to obtain the lowest mean square error, while the second and third proposed methods depend on a hybrid process between iteration and robust Partial Least Square Regression. The proposed and conventional methods were applied to estimate PLSR models on data Datasets for various ordinary patients in Iraq. The Dataset provides the patients Cell Blood Count test information that can be used to create a Hematology diagnosis/prediction system. Also, this Data was collected in 2022 from Al-Zahraa Al-Ahly Hospital. The proposed iterative method with higher efficiency provided 5 variables' importance in the projection score that explain the changes in HGB levels.