【摘要】 为实现对脓毒症的提前预测，本研究设计了一种基于时间序列数据的预测模型KA-Transformer。通过在KA-Transformer中引入核注意力机制，以改善训练样本有限、参数众多及样本分布不均等问题。将连续的时间序列数据输入模型，结果显示：在脓毒症发生前1、6和12 h的3个预测时间点，模型预测脓毒症的受试者工作特征曲线下面积分别为0.962、0.944和0.984,准确率分别为92.3%、93.9%和96.1%。实验结果表明，KA-Transformer在脓毒症预测的准确性和泛化能力方面优于现有方法，在提升脓毒症预测实时性与可靠性方面具备一定潜力。更多还原

【Abstract】 To achieve early prediction of sepsis, we designed a prediction model KA-Transformer based on time series data. A kernel attention mechanism was introduced in the KA-Transformer to improve issues such as limited training samples, numerous parameters, 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.更多还原