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

Diagnostic analysis and clinical treatment strategies for patients with hyperhemolytic syndrome: a case report

Objective To analyze a case of hyperhemolytic syndrome(HHS) and explore the laboratory diagnostic method and clinical treatment strategy. Methods Serological tests such as blood typing, direct antiglobulin test(DAT), ant...

A laboratory model for evaluating the risk of thrombosis in patients with chronic venous insufficiency

Objective To explore the predictive value of combined thromboelastography(TEG), coagulation index and platelet parameters in evaluating the risk of thrombosis in patients with chronic venous insufficiency(CVI). Methods A...

Study on the confirmation of treponema pallidum antibody reactivity in blood donors

Objective To evaluate the feasibility of confirming syphilis reactive blood donors. Methods The serum of donors with anti-TP reaction by ELISA were confirmed by treponema pallidum particle agglutination (TPPA) and Wester...

Study on the hepatitis B virus infection in blood donors reactive to jointed NAT but non-reactive to primary discriminatory test

Objective To analyze the status of HBV infection in blood donors reactive to jointed NAT but non-reactive to primary discriminatory tests (NRR), so as to provide suggestions and data support for subsequent studies on NRR...

Correlation between type Ⅱ CD36 deficiency and intron polymorphism

Objective To study the correlation between type ⅡCD36 deficiency and the polymorphism of intron sequence. Methods A total of 516 random healthy platelet donors from Liaoning Blood Center were involved: 241 of them were t...

Download PDF file
  • EP ID EP738556
  • DOI 10.13303/j.cjbt.issn.1004-549x.2023.05.020
  • Views 44
  • 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