急诊科人工智能心电图推荐系统的开发与验证
研究使用机器学习开发并验证临床决策支持工具,预测急诊分诊患者是否需要心电图检查。数据来自一家三级医院2017年8月至2020年11月的301,658次急诊就诊,分为开发队列、验证队列及两个测试队列(包含COVID-19大流行前及期间就诊)。比较逻辑回归、决策树、随机森林和XGBoost模型的AUC、PPV和NPV,XGBoost模型被选中用于后续应用。验证队列中XGBoost模型AUC为0.887;测试队列1 AUC为0.891,敏感度0.812,特异度0.814,PPV 0.708,NPV 0.886;测试队列2 AUC为0.885,敏感度0.816,特异度0.812,PPV 0.659,NPV 0.908。累积发病率分析显示,未接受心电图但被模型阳性预测的患者在48小时内接受检查的概率显著高于模型阴性预测者。
要点
- 基于分诊数据的XGBoost模型在验证队列预测急诊患者需心电图的AUC为0.887。
- 测试队列1中模型AUC为0.891,敏感度0.812,特异度0.814,PPV 0.708,NPV 0.886。
- 测试队列2(含COVID-19大流行期间就诊)中模型AUC为0.885,敏感度0.816,特异度0.812,PPV 0.659,NPV 0.908。
- 未接受心电图但模型阳性预测的患者48小时内接受检查的概率显著高于模型阴性预测者。
- 该心电图推荐系统可预测急诊分诊患者是否需要心电图,辅助后续分析与决策。
适用人群与场景
- 一家三级医院2017年8月至2020年11月的301,658次急诊就诊患者,用于模型开发与验证。
- 测试队列包括COVID-19大流行前及大流行期间就诊的急诊分诊患者。
研究设计与关键结果
- 研究类型为使用机器学习开发并验证临床决策支持工具的建模研究,数据来自一家三级医院301,658次急诊就诊。
- 验证队列中AUC:XGBoost模型0.887,逻辑回归模型0.885,随机森林模型0.878,决策树模型0.845;XGBoost模型被选中用于后续应用。
- 测试队列1:AUC 0.891,敏感度0.812,特异度0.814,PPV 0.708,NPV 0.886。
- 测试队列2:AUC 0.885,敏感度0.816,特异度0.812,PPV 0.659,NPV 0.908。
- 累积发病率分析显示,未接受心电图但被模型阳性预测的患者在48小时内接受检查的概率显著高于模型阴性预测者。
证据类型、等级与局限
- 证据类型:基于急诊分诊数据集的机器学习模型开发与验证研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 基于分诊数据的机器学习模型可预测急诊分诊患者是否需要心电图检查,辅助急诊后续分析与决策。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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
The machine learning-assisted electrocardiogram (ECG) is increasingly recognized for its unprecedented capabilities in diagnosing and predicting cardiovascular diseases. Identifying the need for ECG examination early in emergency department (ED) triage is key to timely artificial intelligence-assisted analysis. We used machine learning to develop and validate a clinical decision support tool to predict ED triage patients' need for ECG. Data from 301,658 ED visits from August 2017 to November 2020 in a tertiary hospital were divided into a development cohort, validation cohort, and two test cohorts that included admissions before and during the COVID-19 pandemic. Models were developed using logistic regression, decision tree, random forest, and XGBoost methods. Their areas under the receiver operating characteristic curves (AUCs), positive predictive values (PPVs), and negative predictive values (NPVs) were compared and validated. In the validation cohort, the AUCs were 0.887 for the XGBoost model, 0.885 for the logistic regression model, 0.878 for the random forest model, and 0.845 for the decision tree model. The XGBoost model was selected for subsequent application. In test cohort 1, the AUC was 0.891, with sensitivity of 0.812, specificity of 0.814, PPV of 0.708 and NPV of 0.886. In test cohort 2, the AUC was 0.885, with sensitivity of 0.816, specificity of 0.812, PPV of 0.659, and NPV of 0.908. In the cumulative incidence analysis, patients not receiving an ECG yet positively predicted by the model had significantly higher probability of receiving the examination within 48 h compared with those negatively predicted by the model. A machine learning model based on triage datasets was developed to predict ECG acquisition with high accuracy. The ECG recommendation can effectively predict whether patients presenting at ED triage will require an ECG, prompting subsequent analysis and decision-making in the ED.
参考来源
- Tsai DJ, Tsai SH, Chiang HH, et al. Development and Validation of an Artificial Intelligence Electrocardiogram Recommendation System in the Emergency Department. J Pers Med. 2022. PMID: 35629122. doi:10.3390/jpm12050700
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。