开发用于急诊科心脏骤停早期检测的神经网络模型
本研究为单中心基于电子健康记录的研究,旨在开发并测试人工神经网络分类器,用于急诊科早期识别有心脏骤停风险的患者。主要结局为预测后24小时内发生心脏骤停。研究训练了多层感知机、长短期记忆和混合三种神经网络模型,并与改良早期预警评分、逻辑回归和随机森林进行比较,采用AUROC、敏感度、特异度、阳性预测值和阴性预测值评价。结果显示三种神经网络模型AUROC分别为0.929、0.933和0.936,均高于非神经网络模型,其中混合模型表现最佳;在固定阈值使阳性结果与MEWS评分≥3、≥4、≥5三个阈值相同时,神经网络分类器在多数测试特征上表现更优。结论认为神经网络在急诊科心脏骤停预测方面优于MEWS和传统机器学习算法。
要点
- 混合神经网络模型预测急诊科24小时内心脏骤停的AUROC为0.936(95%CI 0.933-0.939),为三种神经网络模型中最佳。
- 多层感知机模型AUROC为0.929(95%CI 0.926-0.932),长短期记忆模型AUROC为0.933(95%CI 0.930-0.936)。
- 三种神经网络模型AUROC均高于非神经网络模型(MEWS、逻辑回归、随机森林)。
- 当阈值固定使阳性结果与MEWS评分≥3、≥4、≥5三个阈值相同时,神经网络分类器在多数测试特征上表现更高。
- 研究期间共纳入374,605次急诊就诊和2,910,321次患者状态更新。
适用人群与场景
- 急诊科就诊患者,研究期间共374,605次急诊就诊。
诊断标准与关键阈值
- 主要结局为预测后24小时内发生心脏骤停。
- 比较时采用MEWS评分≥3、≥4、≥5三个阈值作为参照。
研究设计与关键结果
- 单中心基于电子健康记录的研究,训练多层感知机、长短期记忆和混合三种人工神经网络模型,并与MEWS、逻辑回归和随机森林比较。
- 多层感知机AUROC为0.929(95%CI 0.926-0.932),长短期记忆AUROC为0.933(95%CI 0.930-0.936),混合模型AUROC为0.936(95%CI 0.933-0.939)。
- 三种神经网络模型AUROC均高于非神经网络模型,混合模型表现最佳。
- 当阈值固定使阳性结果与MEWS评分≥3、≥4、≥5三个阈值相同时,神经网络分类器在多数测试特征上表现更高。
- 研究期间共374,605次急诊就诊和2,910,321次患者状态更新。
证据类型、等级与局限
- 证据类型:单中心基于电子健康记录的研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,神经网络在急诊科心脏骤停预测方面优于MEWS和传统机器学习算法,混合神经网络模型利用基线和序列信息取得最佳表现。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Automated surveillance for cardiac arrests would be useful in overcrowded emergency departments. The purpose of this study is to develop and test artificial neural network (ANN) classifiers for early detection of patients at risk of cardiac arrest in emergency departments.
METHODS: This is a single-center electronic health record (EHR)-based study. The primary outcome was the development of cardiac arrest within 24 h after prediction. Three ANN models were trained: multilayer perceptron (MLP), long-short-term memory (LSTM), and hybrid. These were compared to other classifiers including the modified early warning score (MEWS), logistic regression, and random forest. We used AUROC, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for the comparison.
RESULTS: During the study period, there were a total of 374,605 ED visits and 2,910,321 patient status updates. The ANN models (MLP, LSTM, and hybrid) achieved higher AUROC (AUROC: 0.929, 0.933, and 0.936; 95% confidential interval: 0.926-0.932, 0.930-0.936, and 0.933-0.939, respectively) compared to the non-ANN models, and the hybrid model exhibited the best performance. The ANN classifiers displayed higher performance in most of the test characteristics when the threshold levels of the classifiers were fixed to display the same positive result as those at the three MEWS thresholds (score ≥ 3, ≥4, and ≥5), and when compared with each other.
CONCLUSIONS: The ANN improves upon MEWS and conventional machine learning algorithms for the prediction of cardiac arrests in emergency departments. The hybrid ANN model utilizing both baseline and sequence information achieved the best performance.
参考来源
- Jang DH, Kim J, Jo YH, et al. Developing neural network models for early detection of cardiac arrest in emergency department. Am J Emerg Med. 2019. PMID: 30982559. doi:10.1016/j.ajem.2019.04.006
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。