院外心脏骤停后良好神经功能恢复的预测:机器学习分析
本研究旨在训练、验证并比较使用机器学习分析预测院外心脏骤停(OHCA)患者良好神经功能恢复的模型。分析对象为2013年至2016年间成人OHCA患者,推测为心源性病因且自主循环恢复持续;80%个体用于训练,20%用于验证。使用六种机器学习算法:逻辑回归(LR)、极端梯度提升(XGB)、支持向量机、随机森林、弹性净(EN)和神经网络;变量为急诊就诊24小时内可获得的数据。共纳入19,860例OHCA患者;训练组15,888例中2,228例(14.0%)良好神经功能恢复;验证组3,972例中577例(14.5%)良好神经功能恢复。LR、XGB和EN模型判别力最高(AUROC(95%CI)均为0.949(0.941-0.957)),且三者校准良好(Hosmer-Lemeshow检验:p>0.05)。XGB模型按真实风险重新分类患者优于LR模型(NRI:0.110),但EN模型重新分类劣于LR模型(NRI:-1.239)。结论:表现最佳的机器学习算法是XGB和LR算法。
要点
- 在19,860例成人OHCA且自主循环恢复患者中,LR、XGB和EN模型的判别力最高,AUROC(95%CI)均为0.949(0.941-0.957)。
- 训练组15,888例中2,228例(14.0%)良好神经功能恢复;验证组3,972例中577例(14.5%)良好神经功能恢复。
- LR、XGB和EN模型均校准良好(Hosmer-Lemeshow检验:p>0.05)。
- XGB模型按真实风险重新分类患者优于LR模型(NRI:0.110),EN模型重新分类劣于LR模型(NRI:-1.239)。
- 作者结论认为表现最佳的机器学习算法是XGB和LR算法。
适用人群与场景
- 成人OHCA患者,推测为心源性病因,且自主循环恢复持续,数据来自2013年至2016年。
研究设计与关键结果
- 研究类型为机器学习模型训练、验证与比较分析;共纳入19,860例OHCA患者,80%用于训练(15,888例),20%用于验证(3,972例)。
- 训练组15,888例中2,228例(14.0%)良好神经功能恢复;验证组3,972例中577例(14.5%)良好神经功能恢复。
- 使用六种机器学习算法:逻辑回归(LR)、极端梯度提升(XGB)、支持向量机、随机森林、弹性净(EN)和神经网络;变量为急诊就诊24小时内可获得的数据。
- LR、XGB和EN模型判别力最高,AUROC(95%CI)均为0.949(0.941-0.957),且三者校准良好(Hosmer-Lemeshow检验:p>0.05)。
- XGB模型按真实风险重新分类患者优于LR模型(NRI:0.110),EN模型重新分类劣于LR模型(NRI:-1.239)。
证据类型、等级与局限
- 证据类型:机器学习模型开发与验证研究;原文未报告证据等级。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为表现最佳的机器学习算法是XGB和LR算法,可用于预测OHCA患者良好神经功能恢复。
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
BACKGROUND: This study aimed to train, validate and compare predictive models that use machine learning analysis for good neurological recovery in OHCA patients.
METHODS: Adult OHCA patients who had a presumed cardiac etiology and a sustained return of spontaneous circulation between 2013 and 2016 were analyzed; 80% of the individuals were analyzed for training and 20% were analyzed for validation. We developed using six machine learning algorithms: logistic regression (LR), extreme gradient boosting (XGB), support vector machine, random forest, elastic net (EN), and neural network. Variables that could be obtained within 24 hours of the emergency department visit were used. The area under the receiver operation curve (AUROC) was calculated to assess the discrimination. Calibration was assessed by the Hosmer-Lemeshow test. Reclassification was assessed by using the continuous net reclassification index (NRI).
RESULTS: A total of 19,860 OHCA patients were included in the analysis. Of the 15,888 patients in the training group, 2228 (14.0%) had a good neurological recovery; of the 3972 patients in the validation group, 577 (14.5%) had a good neurological recovery. The LR, XGB, and EN models showed the highest discrimination powers (AUROC (95% CI)) of 0.949 (0.941-0.957) for all), and all three models were well calibrated (Hosmer-Lemeshow test: p >0.05). The XGB model reclassified patients according to their true risk better than the LR model (NRI: 0.110), but the EN model reclassified patients worse than the LR model (NRI: -1.239).
CONCLUSION: The best performing machine learning algorithm was the XGB and LR algorithm.
参考来源
- Park JH, Shin SD, Song KJ, et al. Prediction of good neurological recovery after out-of-hospital cardiac arrest: A machine learning analysis. Resuscitation. 2019. PMID: 31362082. doi:10.1016/j.resuscitation.2019.07.020
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。