文献速递重症综合管理与镇静镇痛复苏、休克与脓毒症

医院内识别恶化患者:新型评分系统的开发与验证

Detecting Deteriorating Patients in the Hospital: Development and Validation of a Novel Scoring System.
PubMed 文献 · Am J Respir Crit Care Med · 2021-01-01
一句话结论HAVEN机器学习模型在识别院内24小时内发生心脏骤停或非计划ICU入住方面,区分度(c-statistic 0.901)显著优于现有评分系统。

该回顾性队列研究纳入英国四家医院16岁及以上住院患者,利用单中心230,415例次数据训练基于生命体征、实验室检查、合并症和衰弱的梯度提升树模型(HAVEN),并在四家医院266,295例次中内外部验证。主要终点为心脏骤停或非计划ICU入住,HAVEN在每次测量后24小时内的c-statistic为0.901(95%CI 0.898-0.903),优于其他已发表评分系统(范围0.700-0.863)。在精确度10%时,HAVEN可提前最多48小时识别42%的事件,而次优系统仅22%。结论提示该机器学习算法显著优于国家早期预警评分等现有工具。

要点

  • HAVEN模型在每次测量后24小时内预测心脏骤停或非计划ICU入住的c-statistic为0.901(95%CI 0.898-0.903)。
  • 对比其他已发表评分系统(包括国家早期预警评分、基于实验室的急性生理评分、电子心脏骤停风险分诊评分),其c-statistic范围为0.700-0.863。
  • 在精确度10%条件下,HAVEN可提前最多48小时识别42%的心脏骤停或非计划ICU入住事件。
  • 次优系统在相同条件下仅能提前识别22%的事件。
  • 模型训练使用单家医院230,415例次入院数据,外部验证使用四家医院266,295例次入院数据。

适用人群与场景

  • 英国四家医院中年龄16岁及以上的住院患者。
  • 研究为回顾性队列,纳入患者数据包含生命体征、实验室检查、合并症和衰弱信息。

诊断标准与关键阈值

  • 主要结局定义为心脏骤停或非计划入住ICU。
  • 模型预测时间窗为每次测量后24小时内。
  • 精确度设定为10%时评估模型识别事件的比例和提前时间(最多48小时)。

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

  • 研究类型为回顾性队列研究,数据来自英国四家医院,训练集230,415例次入院,验证集266,295例次入院。
  • HAVEN模型(梯度提升树)在主要结局(每次测量后24小时内的心脏骤停或非计划ICU入住)的c-statistic为0.901(95%CI 0.898-0.903)。
  • 其他已发表评分系统的c-statistic范围为0.700(95%CI 0.696-0.704)至0.863(95%CI 0.860-0.865)。
  • 在精确度10%时,HAVEN可提前最多48小时识别42%的心脏骤停或非计划ICU入住事件,次优系统为22%。

证据类型、等级与局限

  • 证据类型为回顾性队列研究,使用单中心数据训练模型并在四家医院进行外部验证。
  • 局限性:原文未明确列出,但研究设计为回顾性,模型基于电子健康记录数据,可能受数据质量和中心差异影响。

对床旁实践的改变

  • 原文未提及

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

Rationale: Late recognition of patient deterioration in hospital is associated with worse outcomes, including higher mortality. Despite the widespread introduction of early warning score (EWS) systems and electronic health records, deterioration still goes unrecognized. Objectives: To develop and externally validate a Hospital- wide Alerting via Electronic Noticeboard (HAVEN) system to identify hospitalized patients at risk of reversible deterioration. Methods: This was a retrospective cohort study of patients 16 years of age or above admitted to four UK hospitals. The primary outcome was cardiac arrest or unplanned admission to the ICU. We used patient data (vital signs, laboratory tests, comorbidities, and frailty) from one hospital to train a machine-learning model (gradient boosting trees). We internally and externally validated the model and compared its performance with existing scoring systems (including the National EWS, laboratory-based acute physiology score, and electronic cardiac arrest risk triage score). Measurements and Main Results: We developed the HAVEN model using 230,415 patient admissions to a single hospital. We validated HAVEN on 266,295 admissions to four hospitals. HAVEN showed substantially higher discrimination (c-statistic, 0.901 [95% confidence interval, 0.898-0.903]) for the primary outcome within 24 hours of each measurement than other published scoring systems (which range from 0.700 [0.696-0.704] to 0.863 [0.860-0.865]). With a precision of 10%, HAVEN was able to identify 42% of cardiac arrests or unplanned ICU admissions with a lead time of up to 48 hours in advance, compared with 22% by the next best system. Conclusions: The HAVEN machine-learning algorithm for early identification of in-hospital deterioration significantly outperforms other published scores such as the National EWS.

来源:Am J Respir Crit Care Med,查看原文。版权归原作者所有。

参考来源

  1. Pimentel MAF, Redfern OC, Malycha J, et al. Detecting Deteriorating Patients in the Hospital: Development and Validation of a Novel Scoring System. Am J Respir Crit Care Med. 2021. PMID: 33525997. doi:10.1164/rccm.202007-2700OC

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。