机器学习预测COVID-19机械通气患者俯卧位应答者
从荷兰25家医院多中心数据仓库纳入1142例有创机械通气COVID-19患者共3619次俯卧位,排除超过24小时的俯卧位时段。用监督机器学习算法基于常规临床特征预测俯卧位4小时后(1–7小时窗口)的成功,成功定义为PaO2/FiO2、通气比、呼吸系统顺应性或机械功至少改善10%。尽管用了多种算法和大量特征,区分应答者与非应答者的AUC仍差(PaO2/FiO2用Logistic回归、随机森林和XGBoost时AUC为0.62),各模型特征重要性不一致,既往俯卧位应答史或俯卧位前PEEP水平也无有意义的预测贡献。作者据此认为,对所有重型COVID-19 ARDS患者宽松实施俯卧位是合理的,尤其不应因既往俯卧位结果而限制。
要点
- 在1142例有创机械通气COVID-19患者的3619次俯卧位中,用常规电子病历参数预测俯卧位成功不可行,PaO2/FiO2的AUC为0.62。
- 预测目标为俯卧位4小时后(1–7小时窗口)PaO2/FiO2、通气比、呼吸系统顺应性或机械功至少改善10%,或PaO2/FiO2改善20 mmHg。
- 既往是否为俯卧位应答者、俯卧位前PEEP水平,对预测下一次俯卧位成功均无有意义的贡献。
- 各机器学习模型间特征重要性不一致,提示没有稳定可靠的预测因子。
- 作者认为,对所有重型COVID-19 ARDS患者宽松实施俯卧位是合理的,尤其不应因既往俯卧位结果而限制。
适用人群与场景
- 荷兰25家医院多中心数据仓库中,1142例有创机械通气的COVID-19 ICU患者,共3619次俯卧位。
- 排除俯卧位时长超过24小时的时段;Berlin ARDS标准未正式记录。
诊断标准与关键阈值
- 俯卧位成功定义为俯卧位后4小时(窗口1–7小时)PaO2/FiO2、通气比、呼吸系统顺应性或机械功至少改善10%。
- 另用PaO2/FiO2改善20 mmHg切点及复合结局参数建模。
- 俯卧位后4小时内重新仰卧位标记为失败。
研究设计与关键结果
- 研究类型:多中心数据仓库的机器学习建模研究;样本为25家医院的1142例有创机械通气COVID-19患者、共3619次俯卧位。
- 俯卧位中位时长为17小时(IQR 11–20,N=2632)。
- 尽管使用多种机器学习技术和大量潜在临床相关特征,区分应答者与非应答者的能力仍差:PaO2/FiO2用Logistic回归、随机森林和XGBoost建模时AUC为0.62。
- 各模型间特征重要性不一致;既往俯卧位应答史或俯卧位前PEEP水平对预测下一次俯卧位成功均无有意义的贡献。
证据类型、等级与局限
- 证据类型:基于多中心数据仓库的监督机器学习建模研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,基于现有证据,对所有重型COVID-19 ARDS患者宽松实施俯卧位是合理的,尤其不应因既往俯卧位结果而决定是否再次俯卧位。
- 用常规电子病历参数预测俯卧位是否成功目前不可行,不宜据此分配劳动力资源。
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: For mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, prone positioning is labor intensive and comes with potential adverse effects. Therefore, identifying which critically ill intubated COVID-19 patients will benefit may help allocate labor resources.
METHODS: From the multi-center Dutch Data Warehouse of COVID-19 ICU patients from 25 hospitals, we selected all 3619 episodes of prone positioning in 1142 invasively mechanically ventilated patients. We excluded episodes longer than 24 h. Berlin ARDS criteria were not formally documented. We used supervised machine learning algorithms Logistic Regression, Random Forest, Naive Bayes, K-Nearest Neighbors, Support Vector Machine and Extreme Gradient Boosting on readily available and clinically relevant features to predict success of prone positioning after 4 h (window of 1 to 7 h) based on various possible outcomes. These outcomes were defined as improvements of at least 10% in PaO2/FiO2 ratio, ventilatory ratio, respiratory system compliance, or mechanical power. Separate models were created for each of these outcomes. Re-supination within 4 h after pronation was labeled as failure. We also developed models using a 20 mmHg improvement cut-off for PaO2/FiO2 ratio and using a combined outcome parameter. For all models, we evaluated feature importance expressed as contribution to predictive performance based on their relative ranking.
RESULTS: The median duration of prone episodes was 17 h (11-20, median and IQR, N = 2632). Despite extensive modeling using a plethora of machine learning techniques and a large number of potentially clinically relevant features, discrimination between responders and non-responders remained poor with an area under the receiver operator characteristic curve of 0.62 for PaO2/FiO2 ratio using Logistic Regression, Random Forest and XGBoost. Feature importance was inconsistent between models for different outcomes. Notably, not even being a previous responder to prone positioning, or PEEP-levels before prone positioning, provided any meaningful contribution to predicting a successful next proning episode.
CONCLUSIONS: In mechanically ventilated COVID-19 patients, predicting the success of prone positioning using clinically relevant and readily available parameters from electronic health records is currently not feasible. Given the current evidence base, a liberal approach to proning in all patients with severe COVID-19 ARDS is therefore justified and in particular regardless of previous results of proning.
参考来源
- Dam TA, Roggeveen LF, van Diggelen F, et al. Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning. Ann Intensive Care. 2022. PMID: 36264358. doi:10.1186/s13613-022-01070-0
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。