生物医学工程研究2025，Vol.44Issue(2)：90-96,7.DOI:10.19529/j.cnki.1672-6278.2025.02.04
基于时间序列和KA-Transformer模型的早期脓毒症预测
Early sepsis prediction based on time series and KA-Transformer models
朱宇 1张天逸 2张立 3程云章2
作者信息
- 1. 上海理工大学健康科学与工程学院,上海 200093||上海介入医疗器械工程技术研究中心,上海 200093||海军军医大学第二附属医院胸心外科,上海 200003
- 2. 上海理工大学健康科学与工程学院,上海 200093||上海介入医疗器械工程技术研究中心,上海 200093
- 3. 同济大学医学院,上海 200092
- 折叠
摘要
Abstract
To achieve early prediction of sepsis,we designed a prediction model KA-Transformer based on time series data.A ker-nel attention mechanism was introduced in the KA-Transformer to improve issues such as limited training samples,numerous parame-ters,and uneven sample distribution.With the input of continuous time series data,at three prediction time points 1,6,and 12 h before sepsis onset,the area under the receiver operating characteristic curve of the model for predicting sepsis were 0.962,0.944 and 0.984,respectively,the accuracy rates were 92.3％,93.9％and 96.1％,respectively.The experimental results show that the KA-Transformer significantly outperforms existing methods in terms of accuracy and generalization ability for sepsis prediction,and has the potential to enhance the timeliness and reliability of prediction for sepsis prediction.关键词
脓毒症/时间序列/深度学习/核注意力/TransformerKey words
Sepsis/Time series/Deep learning/Kernel attention/Transformer分类
基础医学引用本文复制引用
朱宇,张天逸,张立,程云章..基于时间序列和KA-Transformer模型的早期脓毒症预测[J].生物医学工程研究,2025,44(2):90-96,7.
