基于机器学习的静脉外体膜氧化的第一天死亡率预测:新的RESCUE-24得分
Jung-Chi Hsu1,2, Chen-Hsu Pai3,4, Lian-Yu Lin2,3,5
1From the Department of Internal Medicine, National Taiwan University Hospital, Jinshan Branch, New Taipei City, Taiwan.
ASAIO journal (American Society for Artificial Internal Organs : 1992)
|February 20, 2025
概括
机器学习准确地预测了静脉外体膜氧化 (VA-ECMO) 患者的死亡率. 基于乳酸清除的新RESCUE-24评分,改善了风险分层,并指导了为更好的生存结果量身定制的患者管理.
科学领域:
- 心脏病学 心脏病学
- 关键护理医学 关键护理医学
- 生物医学工程 生物医学工程
背景情况:
- 体外膜氧化 (ECMO) 对于心脏支持至关重要,但预测患者的结果仍然具有挑战性.
- 准确的预后对于优化治疗策略和在重症监护机构的资源配置至关重要.
研究的目的:
- 开发和验证一种机器学习模型,用于预测成人静脉动脉 (VA) -ECMO患者的住院死亡率.
- 创建一个新的,临床上适用的风险评分 (RESCUE-24评分) 来分层VA-ECMO患者死亡风险.
主要方法:
- 在国家台湾大学医院对1,748名VA-ECMO成年患者 (2010-2021) 的回顾性分析.
- 机器学习,特别是随机生存森林 (RSF) 模型,用于预测建模.
- 将RSF模型的性能与已建立的评分系统进行比较:SOFA,APACHE II,SAVE,ENCOURAGE和SAPS III.
主要成果:
- 该RSF模型实现了在医院死亡率 (AUC:0.953) 的优异预测,显著超过现有得分.
- 在8小时内未能达到25%的乳酸清除或在16小时内未能达到50%的乳酸清除,与死亡风险增加有关.
- 开发的RESCUE-24评分有效地将患者分为低风险,中风险和高风险组,具有不同的生存概率.
- 卡普兰-梅尔分析证实了改善乳酸清除的改善生存率,并验证了RESCUE-24评分的预后值.
结论:
- 机器学习,特别是RSF模型,为预测VA-ECMO患者的死亡率提供了一个强大的工具.
- RESCUE-24评分为患者管理提供了经过验证的,风险分层的方法,强调了乳酸清除的重要性.
- 在24小时内优化乳酸清除是改善VA-ECMO患者生存结果的关键可修改因素.
相关概念视频
01:29Acute Respiratory Failure-V
113
The treatment for acute respiratory failure varies based on factors like the underlying cause, overall health, and severity. A collaborative healthcare team is essential for early detection, often through arterial blood gas analysis. Identifying the cause is the primary goal, with treatment strategies adjusted for ventilation/perfusion (V/Q) mismatch, shunting, or diffusion impairment.
Ensure that patients are monitored continuously for their response to therapy, including changes in...
Ensure that patients are monitored continuously for their response to therapy, including changes in...
113
01:20Assessment of Ventilation I: Respiratory Rate
987
Assessment of Ventilation
A Ventilation assessment is critical for monitoring a patient's health status. Respiration, one of the most accessible vital signs, provides insights into the function of numerous body systems and can indicate serious health issues, such as brainstem injuries from head trauma.
Critical Guidelines for Assessing Ventilation:
A Ventilation assessment is critical for monitoring a patient's health status. Respiration, one of the most accessible vital signs, provides insights into the function of numerous body systems and can indicate serious health issues, such as brainstem injuries from head trauma.
Critical Guidelines for Assessing Ventilation:
987