现代信息科技2025，Vol.9Issue(22)：17-22,29,7.DOI:10.19850/j.cnki.2096-4706.2025.22.004
基于LSTM时间序列模型的医疗资源配给预测方案
Medical Resource Allocation Prediction Scheme Based on LSTM Time Series Model
摘要
Abstract
Accurate prediction and efficient deployment of medical supplies are the core to improve the effectiveness of epidemic prevention and control.The traditional model is difficult to effectively deal with the nonlinear characteristics and dynamic interference of time series data,and it is easy to introduce prediction bias.Based on the Long Short-Term Memory(LSTM)network,this study uses its gating mechanism and long-term dependence modeling ability to optimize the complex temporal correlation in epidemic data.Combined with Adam optimizer,an efficient medical supply demand forecasting model is constructed.Experiments based on the real data of the new coronavirus epidemic in multiple cities show that the LSTM model in this paper has advantages in prediction performance and efficiency compared with benchmarks such as regression model,recurrent neural network and Transformer.The ablation experiment further shows that when the length of the historical window is set to 4,the model can best balance the long-term rule capture and noise suppression,thereby achieving optimal performance.关键词
医疗物资需求预测/LSTM/时间序列预测/门控机制Key words
medical supply demand forecasting/LSTM/time series prediction/gating mechanism分类
信息技术与安全科学引用本文复制引用
郭瑛,张莉莉,李月梅,余良超..基于LSTM时间序列模型的医疗资源配给预测方案[J].现代信息科技,2025,9(22):17-22,29,7.基金项目
广西壮族自治区卫生健康委员会自筹经费科研课题(Z20211433) （Z20211433）
桂林医科大学护理科研基础能力提升项目(202504014) （202504014）
