TY - JOUR AU - Boie, Sebastian Daniel AU - Engelhardt, Lilian Jo AU - Coenen, Nicolas AU - Giesa, Niklas AU - Rubarth, Kerstin AU - Menk, Mario AU - Balzer, Felix PY - 2022 DA - 2022/10/13 TI -预测肝素治疗后活化部分凝血活蛋白时间的循环神经网络模型:回顾性研究JO - JMIR Med Inform SP - e39187 VL - 10 IS - 10kw -机器学习KW -医疗保健KW -循环神经网络KW -肝素KW -活化部分凝血活素时间(aPTT) KW -深度学习KW - ICU KW -重症监护AB -背景:肝素抗凝治疗是重症监护病房的常用治疗方法,并通过活化部分凝血活素凝血时间(aPTT)进行监测。已有研究表明,在24小时内达到既定的抗凝指标与良好的预后相关。然而,患者对肝素的反应不同,达到抗凝目标可能具有挑战性。机器学习算法可能为临床医生提供改进的剂量建议。目的:本研究评估了一系列机器学习算法预测患者对肝素治疗反应的能力。在这个分析中,我们第一次应用了一个考虑时间序列的模型。方法:从医院信息系统中提取患者人口统计数据、化验值、透析和体外膜氧合治疗及评分。我们预测了连续肝素输注24小时后aPTT实验室值的数值,并评估了7种不同的机器学习模型。将性能最好的模型与最近发布的分类任务模型进行比较。 We considered all data before and within the first 12 hours of continuous heparin infusion as features and predicted the aPTT value after 24 hours. Results: The distribution of aPTT in our cohort of 5926 hospital admissions was highly skewed. Most patients showed aPTT values below 75 s, while some outliers showed much higher aPTT values. A recurrent neural network that consumes a time series of features showed the highest performance on the test set. Conclusions: A recurrent neural network that uses time series of features instead of only static and aggregated features showed the highest performance in predicting aPTT after heparin treatment. SN - 2291-9694 UR - https://medinform.www.mybigtv.com/2022/10/e39187 UR - https://doi.org/10.2196/39187 UR - http://www.ncbi.nlm.nih.gov/pubmed/36227653 DO - 10.2196/39187 ID - info:doi/10.2196/39187 ER -
Baidu
map