Cherukuri Sneha P, Bova Mark L, Mehta Shaylee P, Bautista Christian T
Armed Forces Health Surveillance Division, Integrated Biosurveillance Branch, Silver Spring, MD.
MSMR. 2025 Apr 20;32(4):29-31.
This report assesses the performance of the long short-term memory (LSTM) model, a machine-learning method with potential to improve forecasting accuracy for respiratory disease surveillance, for possible inclusion in future U.S. Department of Defense influenza forecasting analyses. LSTM is a recurrent neural network model that can be used in almost all modeling fields. The LSTM model had the lowest median log-transformed weighted interval score (WIS) for all forecasting horizons: 1 week (0.3), 2 weeks (0.4), and combined 1-2 weeks (0.4). Further research is recommended to determine the performance of the LSTM model for other respiratory infections, including COVID-19.
本报告评估了长短期记忆（LSTM）模型的性能，这是一种机器学习方法，有潜力提高呼吸道疾病监测的预测准确性，可能会被纳入美国国防部未来的流感预测分析中。LSTM是一种循环神经网络模型，几乎可用于所有建模领域。在所有预测期内，LSTM模型的中位数对数变换加权区间得分（WIS）最低：1周（0.3）、2周（0.4）以及1 - 2周综合（0.4）。建议进一步开展研究，以确定LSTM模型对包括COVID - 19在内的其他呼吸道感染的性能表现。
Zotero 插件