机器学习算法预测心脏骤停除颤成功的能力:系统评价
该研究为系统评价,检索MEDLINE、Embase、CINAHL和Scopus(建库至2022年8月30日),纳入将机器学习算法用于预测院内或院外心脏骤停除颤成功(以ROSC、存活至出院或出院时神经功能状态为观察指标)的观察性研究,排除涉及创伤、未知基础心律、植入式心律转复除颤器或聚焦于心脏骤停预测或发生的研究,共纳入15项观察性研究(n=5680)。29个ECG波形特征被输入15种机器学习组合,表现最佳的模型使用4秒ECG间期,准确度为98.6(98.5-98.7)%;纳入呼气末CO2的算法准确度为83.3%(未报告CI)。因研究设计、ROSC定义和特征异质性,未进行Meta分析。作者认为机器学习算法尤其是神经网络在预测除颤成功方面具有潜力,但因异质性、报告不一致和高偏倚风险,难以确定哪种算法最优,仍需标准化报告和适当验证的进一步临床研究。
要点
- 15项观察性研究(n=5680)显示机器学习算法尤其是神经网络在预测除颤成功方面具有潜力,有较高敏感度和特异度。
- 最佳机器学习模型使用4秒ECG间期,准确度为98.6(98.5-98.7)%。
- 纳入呼气末CO2的算法准确度为83.3%(未报告CI)。
- 因研究设计、ROSC定义和特征异质性,未进行Meta分析。
- 因异质性、报告不一致和高偏倚风险,难以确定哪种算法最优,仍需进一步临床研究。
适用人群与场景
- 院内或院外心脏骤停患者,研究限定为评估除颤成功预测;排除涉及创伤、未知基础心律、植入式心律转复除颤器或聚焦于心脏骤停预测或发生的研究。
研究设计与关键结果
- 系统评价检索MEDLINE、Embase、CINAHL和Scopus(建库至2022年8月30日),初检2399项研究,全文审查107篇,最终纳入15项观察性研究(n=5680)。
- 29个ECG波形特征被输入15种不同的机器学习组合。
- 表现最佳的机器学习模型使用4秒ECG间期,准确度为98.6(98.5-98.7)%。
- 纳入呼气末CO2的算法报告准确度为83.3%(未报告置信区间)。
- 因研究设计、ROSC定义和特征异质性,未进行Meta分析。
- 使用PROBAST工具评估偏倚风险,总体偏倚风险高。
证据类型、等级与局限
- 证据类型:系统评价,纳入15项观察性研究。
- 偏倚风险使用PROBAST工具评估,总体偏倚风险高。
- 局限:因研究设计、ROSC定义和特征异质性未进行Meta分析;报告不一致;高偏倚风险;作者指出仍需标准化报告患者特征、结局和适当算法验证的进一步临床研究。
对床旁实践的改变
- 作者认为机器学习算法尤其是神经网络在预测心脏骤停除颤成功方面具有潜力,有较高敏感度和特异度。
- 作者指出因异质性、报告不一致和高偏倚风险,难以确定哪种算法最优,仍需进一步临床研究。
指南或共识出处
- PROSPERO 2020 CRD42020148912。
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」,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
OBJECTIVE: To evaluate the existing knowledge on the effectiveness of machine learning (ML) algorithms inpredicting defibrillation success during in- and out-of-hospital cardiac arrest.
METHODS: MEDLINE, Embase, CINAHL and Scopus were searched from inception to August 30, 2022. Studies were included that utilized ML algorithms for prediction of successful defibrillation, observed as return of spontaneous circulation (ROSC), survival to hospital or discharge, or neurological status at discharge.Studies were excluded if involving a trauma, an unknown underlying rhythm, an implanted cardiac defibrillator or if focused on the prediction or onset of cardiac arrest. Risk of bias was assessed using the PROBAST tool.
RESULTS: There were 2399 studies identified, of which 107 full text articles were reviewed and 15 observational studies (n = 5680) were included for final analysis. 29 ECG waveform features were fed into 15 different ML combinations. The best performing ML model had an accuracy of 98.6 (98.5 - 98.7)%, with 4 second ECG intervals. An algorithm incorporating end-tidal CO2 reported an accuracy of 83.3% (no CI reported). Meta-analysis was not performed due to heterogeneity in study design, ROSC definitions, and characteristics.
CONCLUSION: Machine learning algorithms, specifically Neural Networks, have been shown to have potential to predict defibrillation success for cardiac arrest with high sensitivity and specificity.Due to heterogeneity, inconsistent reporting, and high risk of bias, it is difficult to conclude which, if any, algorithm is optimal. Further clinical studies with standardized reporting of patient characteristics, outcomes, and appropriate algorithm validation are still required to elucidate this. PROSPERO 2020 CRD42020148912.
参考来源
- Sem M, Mastrangelo E, Lightfoot D, et al. The ability of machine learning algorithms to predict defibrillation success during cardiac arrest: A systematic review. Resuscitation. 2023. PMID: 36842672. doi:10.1016/j.resuscitation.2023.109755
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。