Estimation of HbA1c value using artificial neural networks
Article Sidebar
Main Article Content
Abstract
Diabetes is a life-long disease that occurs because of ineffectiveness or lack of the insulin hormone. Although the blood sugar, fructose and haemoglobin A1c (HbA1c) values are commonly used for diagnosis, the latter give more accurate results. The HbA1c value gives information about the blood sugar levels over the past 2 to 3 months, which is required for treating diabetes. Follow-up data of diabetic patients have been used in this study. In the classification phase, a feed-forward artificial neural network (ANN) was used to estimate the factors affecting HbA1c. The designed ANN has 26 features used as input parameters. The output layer comprises two outputs: normal (HbA1c < 6.5) and high (HbA1c ≥ 6.5). An accuracy rate of 90.33% was obtained with the proposed method. The results, which show accurate estimation of the HbA1c level parameters, will be used in future studies to investigate which parameter affects the HbA1c levels, and in what way.
Keywords: Neural network, haemoglobin A1c, diagnosis of diabetes disease
Downloads
Article Details
Global Journal of Computer Sciences: Theory and Research is an Open Access Journal. All articles can be downloaded free of charge. Articles published in the Journal are Open-Access articles distributed under CC-BY license [Attribution 4.0 International (CC BY 4.0)]
Birlesik Dunya Yenilik Arastirma ve Yayincilik Merkezi (BD-Center) is a gold open access publisher. At the point of publication, all articles from our portfolio of journals are immediately and permanently accessible online free of charge. BD-Center articles are published under the CC-BY license [Attribution 4.0 International (CC BY 4.0)], which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and the source are credited.