Recurrent neural network prediction on clinical usage of red blood cells

Journal Title: Chinese Journal of Blood Transfusion - Year 2023, Vol 36, Issue 5

Abstract

Objective To explore the prediction of clinical red blood cells (RBCs) consumption under major public health emergencies, so as to provide scientific basis for blood collection and blood inventory management. Methods The clinical consumption of different types of RBCs in Yichang from 2001 to 2017 was analyzed and modeled using the recurrent neural network (RNN) model, and the clinical RBCs consumption between January 2019 and December 2021(36 months) were scientifically predicted. Results The RNN model showed good prediction performance. The root mean square errors (RMSE) of RNN prediction values of A, B, O, AB type of RBCs were 156.7, 133.4, 204.2 and 51.3, respectively, with the average relative errors (MRE) at 6.4%, 6.6%, 8.5% and 7.1%, respectively. The model predicted the changing trend of RBCs consumption during the first round of COVID-19 outbreak (January to June, 2020) and forecasted the lowest level of consumption in February 2020 and a subsequent recovery in growth. The prediction of RBCs consumption during the second round of COVID-19 pandemic (January to June, 2021) was of high accuracy. For example, the relative errors of RNN models for A type RBCs consumption were 5.2% in Feb 2021 (the lowest level, 1 621.5 U) and 2.5% in May 2021 (the highest level, 2 397.0 U). Conclusion The artificial intelligence RNN model can predict clinical RBCs consumption well under major public health emergencies.

Authors and Affiliations

Fangyan WANG, Yurong YUAN, Min ZHANG, Kun LI, Wei LU

Keywords

Related Articles

Changes in serum immunoglobulin levels in children with thalassemia who undergo repeated blood transfusions and their correlation with delayed hemolytic transfusion reactions

Objective To study the changes in serum immunoglobulin levels in children with thalassemia who undergo repeated blood transfusions and explore their correlation with delayed hemolytic transfusion reactions(DHTR). Methods...

Comparative study of the walk-in and appointment mode of apheresis platelets donation in Guangzhou

Objective To discuss the influence of apheresis platelets donation mode transformation, from walk-in to appointment, on apheresis platelets donation, donor retention and donation service quality. Methods The comparative...

External quality assessment of laboratories in blood stations of Hebei Province in 2022: a retrospective analysis of HeBEQA project

Objective To conduct the laboratory quality assessment between 12 blood stations in Hebei province, analyze the results and explore the accuracy and comparability of testing, so as to improve the level of testing ability...

Analysis of heart rate variability during blood donation

Objective To observe the regulation of autonomic nerves in blood donors during blood donation by heart rate variability analysis and explore the possible mechanism of donation related vasovagal reaction. Methods Electroc...

Effect of IgG anti AB antibody on the correlation analysis between the titer of blood group antibodies and total bilirubin in serum of newborns with hemolytic disease

Objective To investigate the correlation between the titer of anti-A or anti-B antibodies before and after the absorption of IgG anti-AB antibodies in the serum of type O mothers with ABO hemolytic disease of fetus and n...

Download PDF file
  • EP ID EP738556
  • DOI 10.13303/j.cjbt.issn.1004-549x.2023.05.020
  • Views 6
  • Downloads 0

How To Cite

Fangyan WANG, Yurong YUAN, Min ZHANG, Kun LI, Wei LU (2023). Recurrent neural network prediction on clinical usage of red blood cells. Chinese Journal of Blood Transfusion, 36(5), -. https://europub.co.uk/articles/-A-738556