文献速递复苏、休克与脓毒症重症综合管理与镇静镇痛

机器学习算法预测院内心搏骤停复苏期间短期不良结局的价值:一项回顾性研究

The value of a machine learning algorithm to predict adverse short-term outcome during resuscitation of patients with in-hospital cardiac arrest: a retrospective study.
PubMed 文献 · Eur J Emerg Med · 2023-04-28
一句话结论仅用急救团队到达时可获得的数据,机器学习模型预测未获自主循环恢复的AUC为0.9,但阳性预测值不足以支持早期终止复苏。

这项回顾性队列研究纳入630例成人院内心搏骤停患者,使用急救团队到达时即可获得的人口学和临床数据,通过随机森林模型预测未能获得自主循环恢复和出院时不良神经功能结局(CPC 3-5)。预测未获自主循环恢复的模型AUC为0.9(95%CI 0.89-0.9),阳性预测值0.88,阴性预测值0.61;预测不良功能结局的模型AUC为0.93(95%CI 0.92-0.93),阳性预测值0.91,阴性预测值0.57。作者结论认为两个模型的阳性预测值均不足以支持早期终止复苏。

要点

  • 630例成人院内心搏骤停患者中,390例(61.9%)未能获得自主循环恢复,559例(88.7%)出院时神经功能结局不良(CPC 3-5)。
  • 预测未获自主循环恢复的随机森林模型AUC为0.9(95%CI 0.89-0.9),阳性预测值0.88(0.86-0.91),阴性预测值0.61(0.6-0.63),灵敏度0.69(0.66-0.72),特异度0.84(0.8-0.88)。
  • 预测出院时不良功能结局的模型AUC为0.93(95%CI 0.92-0.93),阳性预测值0.91(0.9-0.91),阴性预测值0.57(0.48-0.66),灵敏度0.98(0.97-0.99),特异度0.2(0.16-0.24)。
  • 作者结论指出,两个模型的阳性预测值均不够高,不足以支持在复苏早期终止复苏努力。
  • 指南推荐医院急救团队应本地验证院内心搏骤停终止心肺复苏的标准。

适用人群与场景

  • 成人院内心搏骤停患者,由急救团队到场处理。

诊断标准与关键阈值

  • 出院时神经功能结局采用脑功能分类(CPC)评分,CPC 3-5定义为不良功能结局。

研究设计与关键结果

  • 研究类型为回顾性队列研究,纳入630例成人院内心搏骤停患者,其中390例(61.9%)未能获得自主循环恢复,559例(88.7%)出院时神经功能结局不良(CPC 3-5)。
  • 预测未获自主循环恢复的最终分类模型:AUC 0.9(95%CI 0.89-0.9),平衡准确度0.77(95%CI 0.75-0.79),F1分数0.78(95%CI 0.76-0.79),阳性预测值0.88(0.86-0.91),阴性预测值0.61(0.6-0.63),灵敏度0.69(0.66-0.72),特异度0.84(0.8-0.88)。
  • 预测出院时不良功能结局的最终分类模型:AUC 0.93(95%CI 0.92-0.93),平衡准确度0.59(95%CI 0.57-0.61),F1分数0.94(95%CI 0.94-0.95),阳性预测值0.91(0.9-0.91),阴性预测值0.57(0.48-0.66),灵敏度0.98(0.97-0.99),特异度0.2(0.16-0.24)。
  • 作者结论:使用急救团队到达时即可获得的数据,机器学习算法在复苏进行期间对预测未能获得自主循环恢复和不良功能结局具有高预测能力,但两个模型的阳性预测值均不够高,不足以支持早期终止复苏努力。

证据类型、等级与局限

  • 证据类型:回顾性队列研究。
  • 指南推荐医院急救团队应本地验证院内心搏骤停终止心肺复苏的标准。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,虽然机器学习模型预测能力高,但阳性预测值不够高,不足以支持早期终止复苏努力。
  • 指南推荐医院急救团队应本地验证院内心搏骤停终止心肺复苏的标准。

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 and importance Guidelines recommend that hospital emergency teams locally validate criteria for termination of cardiopulmonary resuscitation in patients with in-hospital cardiac arrest (IHCA). Objective To determine the value of a machine learning algorithm to predict failure to achieve return of spontaneous circulation (ROSC) and unfavourable functional outcome from IHCA using only data readily available at emergency team arrival. Design Retrospective cohort study. Setting and participants Adults who experienced an IHCA were attended to by the emergency team. Outcome measures and analysis Demographic and clinical data typically available at the arrival of the emergency team were extracted from the institutional IHCA database. In addition, outcome data including the Cerebral Performance Category (CPC) score count at hospital discharge were collected. A model selection procedure for random forests with a hyperparameter search was employed to develop two classification algorithms to predict failure to achieve ROSC and unfavourable (CPC 3-5) functional outcomes. Main results Six hundred thirty patients were included, of which 390 failed to achieve ROSC (61.9%). The final classification model to predict failure to achieve ROSC had an area under the receiver operating characteristic curve of 0.9 [95% confidence interval (CI), 0.89-0.9], a balanced accuracy of 0.77 (95% CI, 0.75-0.79), an F1-score of 0.78 (95% CI, 0.76-0.79), a positive predictive value of 0.88 (0.86-0.91), a negative predictive value of 0.61 (0.6-0.63), a sensitivity of 0.69 (0.66-0.72), and a specificity of 0.84 (0.8-0.88). Five hundred fifty-nine subjects experienced an unfavourable outcome (88.7%). The final classification model to predict unfavourable functional outcomes from IHCA at hospital discharge had an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.93), a balanced accuracy of 0.59 (95% CI, 0.57-0.61), an F1-score of 0.94 (95% CI, 0.94-0.95), a positive predictive value of 0.91 (0.9-0.91), a negative predictive value of 0.57 (0.48-0.66), a sensitivity of 0.98 (0.97-0.99), and a specificity of 0.2 (0.16-0.24). Conclusion Using data readily available at emergency team arrival, machine learning algorithms had a high predictive power to forecast failure to achieve ROSC and unfavourable functional outcomes from IHCA while cardiopulmonary resuscitation was still ongoing; however, the positive predictive value of both models was not high enough to allow for early termination of resuscitation efforts.

来源:Eur J Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Dünser MW, Hirschl D, Weh B, et al. The value of a machine learning algorithm to predict adverse short-term outcome during resuscitation of patients with in-hospital cardiac arrest: a retrospective study. Eur J Emerg Med. 2023. PMID: 37115946. doi:10.1097/MEJ.0000000000001031

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。