A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit.
A transformer-based diffusion probabilistic model for heart rate and blood pressure forecasting in Intensive Care Unit.
复制标题
基于变压器的扩散概率模型，用于重症监护病房的心率和血压预测。
DOI：
10.1016/j.cmpb.2024.108060
复制
发表时间：
2024
影响因子：
6.1
通讯作者：
Li,Ao
中科院分区：
文献类型：
--
作者：
Chang,Ping;Li,Huayu;Quan,StuartF;Lu,Shuyang;Wung,Shu-Fen;Roveda,Janet;Li,Ao
背景与目的重症监护室（ICU）生命体征监测是及时干预的关键。这就需要一个准确的预测系统。因此，这项研究提出了一种新的深度学习方法，用于预测ICU中的心率（HR），收缩压（SBP）和舒张压（DBP）。方法从MIMIC-III数据库中抽取24886例ICU住院患者，对模型进行训练和测试。在这项研究中提出的模型，基于变压器的扩散概率模型稀疏时间序列预测（TDSTF），合并Transformer和扩散模型来预测生命体征。TDSTF模型在预测ICU中的生命体征方面表现出最先进的性能，优于其他模型预测生命体征分布的能力，并且计算效率更高。该代码可在https：//github上获得。com/PingChang818/TDSTF.结果TDSTF模型的标准化平均连续排序概率得分（SACRPS）为0.4438，均方误差（MSE）为0.4168，比最佳基线模型分别提高了18.9%和34.3%。TDSTF的推理速度比最佳基线模型快17倍以上。结论TDSTF是一种有效的ICU生命体征预测方法，与其他模型相比有显著的提高。
Abstract Background and Objective Vital sign monitoring in the Intensive Care Unit (ICU) is crucial for enabling prompt interventions for patients. This underscores the need for an accurate predictive system. Therefore, this study proposes a novel deep learning approach for forecasting Heart Rate (HR), Systolic Blood Pressure (SBP), and Diastolic Blood Pressure (DBP) in the ICU. Methods We extracted 24, 886 ICU stays from the MIMIC-III database which contains data from over 46 thousand patients, to train and test the model. The model proposed in this study, Transformer-based Diffusion Probabilistic Model for Sparse Time Series Forecasting (TDSTF), merges Transformer and diffusion models to forecast vital signs. The TDSTF model showed state-of-the-art performance in predicting vital signs in the ICU, outperforming other models' ability to predict distributions of vital signs and being more computationally efficient. The code is available at https://github. com/PingChang818/TDSTF. Results The results of the study showed that TDSTF achieved a Standardized Average Continuous Ranked Probability Score (SACRPS) of 0.4438 and a Mean Squared Error (MSE) of 0.4168, an improvement of 18.9% and 34.3% over the best baseline model, respectively. The inference speed of TDSTF is more than 17 times faster than the best baseline model. Conclusion TDSTF is an effective and efficient solution for forecasting vital signs in the ICU, and it shows a significant improvement compared to other models in the field.