预测机械通气需求的深度学习算法的开发与前瞻性验证
研究开发并外部验证了一种透明深度学习算法,利用电子病历中常见数据预测住院患者(包括COVID-19患者)未来24小时机械通气需求。数据来自两个学术医疗中心的3万余例ICU患者(含700余例COVID-19患者)。开发集与验证集24小时预测AUC分别为0.895和0.882,显著优于传统临床标准(P<.001);COVID-19患者前瞻性验证AUC为0.918~0.943。该算法可能帮助临床医生优化插管时机和资源分配。
要点
- 在3万余例ICU患者(含700余例COVID-19)中,算法提前24小时预测机械通气需求的AUC在开发集为0.895、验证集为0.882。
- 算法预测性能显著优于基于心率、氧饱和度、呼吸频率、Fio2和pH的传统临床标准(P<.001)。
- 在COVID-19患者中前瞻性验证,AUC范围为0.918至0.943。
- 算法使用电子病历中常见可用数据,为透明深度学习模型。
- 预测提前量为24小时,可能有助于优化气管插管时机和资源分配。
适用人群与场景
- 住院患者,包括ICU患者和COVID-19患者;数据来自两个学术医疗中心。
诊断标准与关键阈值
- 原文未提及
处置流程与药物剂量
- 原文未提及
红旗征与不能漏的情况
- 原文未提及
研究设计与关键结果
- 研究类型:算法开发与前瞻性验证研究;样本量:超过30,000例ICU患者(含700余例COVID-19患者),来自两个学术医疗中心。
- 干预:透明深度学习算法,使用电子病历常见数据预测未来24小时机械通气需求;对照:传统临床标准(心率、氧饱和度、呼吸频率、Fio2、pH)。
- 主要终点结果:开发集24小时预测AUC 0.895,验证集AUC 0.882,算法显著优于传统临床标准(P < .001)。
- 关键次要终点:COVID-19患者前瞻性验证AUC范围为0.918至0.943。
- 不良事件:原文未提及。
证据类型、等级与局限
- 证据类型:观察性研究(算法开发与前瞻性验证),非随机对照试验。
- 证据等级或推荐强度:原文未提及。
- 局限:原文未明确列出局限;设计上为多中心研究,但样本来源限于两个学术医疗中心,需进一步外部验证。
对床旁实践的改变
- 该算法可能辅助临床医生提前24小时识别需要机械通气的住院患者(包括COVID-19患者),从而优化气管插管时机。
- 算法预测性能优于传统临床标准,但原文未提供具体决策阈值,不能直接作为插管决策的唯一依据。
- 适用人群为住院患者(包括ICU和COVID-19患者),不适用于原文未提及的人群。
- 常见陷阱:算法需在电子病历数据可用的条件下使用,且预测提前量为24小时,不能替代临床评估。
指南或共识出处
- 原文未提及
以上提炼依据论文摘要(全文未开放获取,或许可不允许翻译转载);全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Objective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation (MV) may aid in delivering timely treatment.
RESEARCH QUESTION: Can a transparent deep learning (DL) model predict the need for MV in hospitalized patients and those with COVID-19 up to 24 h in advance?
STUDY DESIGN AND METHODS: We trained and externally validated a transparent DL algorithm to predict the future need for MV in hospitalized patients, including those with COVID-19, using commonly available data in electronic health records. Additionally, commonly used clinical criteria (heart rate, oxygen saturation, respiratory rate, Fio2, and pH) were used to assess future need for MV. Performance of the algorithm was evaluated using the area under receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value.
RESULTS: We obtained data from more than 30,000 ICU patients (including more than 700 patients with COVID-19) from two academic medical centers. The performance of the model with a 24-h prediction horizon at the development and validation sites was comparable (AUC, 0.895 vs 0.882, respectively), providing significant improvement over traditional clinical criteria (P < .001). Prospective validation of the algorithm among patients with COVID-19 yielded AUCs in the range of 0.918 to 0.943.
INTERPRETATION: A transparent deep learning algorithm improves on traditional clinical criteria to predict the need for MV in hospitalized patients, including in those with COVID-19. Such an algorithm may help clinicians to optimize timing of tracheal intubation, to allocate resources and staff better, and to improve patient care.
参考来源
- Shashikumar SP, Wardi G, Paul P, et al. Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation. Chest. 2020. PMID: 33345948. doi:10.1016/j.chest.2020.12.009
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。