Abstract: Hematology is the study of blood, blood-forming organs, and blood diseases. Hematological tests such as Full Blood Count (FBC) can be used to diagnose a wide range of infections and diseases by comparing their results with the standard hematology reference (SHR) ranges. These ranges were established many years ago by considering the Caucasian population and all countries have used them until recent times to measure the healthiness of the people. But these reference ranges can be varied according to various reasons such as dietary habits, geographical location, climate, environmental factors, etc., and the use of them by all countries may not be correct. Many researchers have started research in finding Local Hematology Reference (LHR) ranges. Most of them used statistical analyses which have their limitations. Machine learning is a solution to overcome those limitations. Finding an approach to determine the LHR range based on machine learning techniques is the goal of this research. The dataset was generated using FBC test reports in Sri Lanka. The LHR range of WBC count of healthy adults in Sri Lanka is only addressed in this research. A difference between the SHR range of WBC and the LHR range of WBC is observed.

K. A. Hasara Semini and H.A.Caldera, “Determining Local Hematology Reference Ranges: A Data-driven Approach” International Journal of Advanced Computer Science and Applications(IJACSA), 12(8), 2021. http://dx.doi.org/10.14569/IJACSA.2021.0120810

@article{Semini2021,
title = {Determining Local Hematology Reference Ranges: A Data-driven Approach},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2021.0120810},
url = {http://dx.doi.org/10.14569/IJACSA.2021.0120810},
year = {2021},
publisher = {The Science and Information Organization},
volume = {12},
number = {8},
author = {K. A. Hasara Semini and H.A.Caldera}
}