文献速递重症综合管理与镇静镇痛复苏、休克与脓毒症

机器学习早期预警评分对院内死亡率的影响:一项多中心临床干预试验

The Impact of a Machine Learning Early Warning Score on Hospital Mortality: A Multicenter Clinical Intervention Trial.
PubMed 文献 · Crit Care Med · 2022-08-15
一句话结论在4家医院医疗外科病房实施eCART评分驱动的预警流程,与院内全因死亡率显著降低相关(8.8% vs 13.9%,调整OR 0.60)。

这是一项在4家社区-学术医院系统开展的实用性前后对照研究,历时同期的10个月、连续2年,纳入所有收住医疗外科病房的成人患者,共60,261例入院患者中6,681例(11.1%)符合纳入标准(基线期n=3,191,干预期n=3,490)。基线期临床医生对eCART评分设盲,干预期向提供者展示评分:≥95百分位定为高风险,触发医生评估是否收入ICU;89–95百分位为中等风险,触发护士主导流程(每2小时测量生命体征并联系医生复核治疗方案)。干预期主要队列院内死亡率显著下降(8.8% vs 13.9%;p<0.0001;调整OR 0.60 [95%CI 0.52-0.71]),未接受干预的平均风险队列死亡率亦下降(0.49% vs 0.26%;p<0.05;调整OR 0.53 [95%CI 0.41-0.74])。亚组分析中高风险(17.9% vs 23.9%;p=0.001)与中等风险(2.0% vs 4.0%;p=0.005)患者均获益。作者认为死亡率的降低可能由更早、更频繁的ICU转入所驱动。

要点

  • 干预期主要队列院内全因死亡率8.8% vs 基线期13.9%(p<0.0001;调整OR 0.60 [95%CI 0.52-0.71])。
  • 高风险(eCART≥95百分位)患者死亡率17.9% vs 23.9%(p=0.001),中等风险(89–95百分位)2.0% vs 4.0%(p=0.005)。
  • 未接受干预的平均风险队列死亡率亦下降:0.49% vs 0.26%(p<0.05;调整OR 0.53 [95%CI 0.41-0.74])。
  • 干预期ICU转入率显著增加、转入ICU时间缩短、2小时内生命体征复评增加。
  • 作者认为死亡率下降可能由更早、更频繁的ICU转入所驱动。

适用人群与场景

  • 4家医院社区-学术卫生系统中所有收住医疗外科病房的成人患者;研究期间共60,261例入院,其中6,681例(11.1%)符合纳入标准(基线期n=3,191,干预期n=3,490)。

诊断标准与关键阈值

  • eCART评分≥95百分位定为高风险,触发医生评估是否收入ICU。
  • eCART评分在89–95百分位之间定为中等风险,触发护士主导流程:每2小时测量生命体征并联系医生复核治疗方案。

处置流程与药物剂量

  • 基线期临床医生对eCART评分设盲,不展示评分。
  • 干预期向提供者展示eCART评分:≥95百分位触发医生评估ICU收治。
  • 89–95百分位触发护士主导流程:每2小时测量生命体征并联系医生复核治疗方案。

研究设计与关键结果

  • 设计:实用性前后干预研究,同一10个月期间在连续2年进行,4家医院社区-学术卫生系统,纳入医疗外科病房成人患者。
  • 干预期主要队列院内全因死亡率8.8% vs 基线期13.9%(p<0.0001;调整OR 0.60 [95%CI 0.52-0.71])。
  • 未接受干预的平均风险队列死亡率0.49% vs 0.26%(p<0.05;调整OR 0.53 [95%CI 0.41-0.74])。
  • 高风险亚组死亡率17.9% vs 23.9%(p=0.001);中等风险亚组2.0% vs 4.0%(p=0.005)。
  • 干预期与ICU转入率显著增加、转入ICU时间缩短、2小时内生命体征复评增加相关。

证据类型、等级与局限

  • 证据类型:实用性前后干预研究(多中心临床干预试验)。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 在医疗外科病房实施eCART评分驱动的预警流程(≥95百分位触发医生评估ICU收治,89–95百分位触发护士主导的每2小时生命体征测量与医生复核治疗方案)与院内死亡率降低相关。
  • 作者认为死亡率的降低可能由更早、更频繁的ICU转入所驱动。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「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

OBJECTIVES: To determine the impact of a machine learning early warning risk score, electronic Cardiac Arrest Risk Triage (eCART), on mortality for elevated-risk adult inpatients.

DESIGN: A pragmatic pre- and post-intervention study conducted over the same 10-month period in 2 consecutive years.

SETTING: Four-hospital community-academic health system.

PATIENTS: All adult patients admitted to a medical-surgical ward.

INTERVENTIONS: During the baseline period, clinicians were blinded to eCART scores. During the intervention period, scores were presented to providers. Scores greater than or equal to 95th percentile were designated high risk prompting a physician assessment for ICU admission. Scores between the 89th and 95th percentiles were designated intermediate risk, triggering a nurse-directed workflow that included measuring vital signs every 2 hours and contacting a physician to review the treatment plan.

MEASUREMENTS AND MAIN RESULTS: The primary outcome was all-cause inhospital mortality. Secondary measures included vital sign assessment within 2 hours, ICU transfer rate, and time to ICU transfer. A total of 60,261 patients were admitted during the study period, of which 6,681 (11.1%) met inclusion criteria (baseline period n = 3,191, intervention period n = 3,490). The intervention period was associated with a significant decrease in hospital mortality for the main cohort (8.8% vs 13.9%; p < 0.0001; adjusted odds ratio [OR], 0.60 [95% CI, 0.52-0.71]). A significant decrease in mortality was also seen for the average-risk cohort not subject to the intervention (0.49% vs 0.26%; p < 0.05; adjusted OR, 0.53 [95% CI, 0.41-0.74]). In subgroup analysis, the benefit was seen in both high- (17.9% vs 23.9%; p = 0.001) and intermediate-risk (2.0% vs 4.0 %; p = 0.005) patients. The intervention period was also associated with a significant increase in ICU transfers, decrease in time to ICU transfer, and increase in vital sign reassessment within 2 hours.

CONCLUSIONS: Implementation of a machine learning early warning score-driven protocol was associated with reduced inhospital mortality, likely driven by earlier and more frequent ICU transfer.

来源:Crit Care Med,查看原文。版权归原作者所有。

参考来源

  1. Winslow CJ, Edelson DP, Churpek MM, et al. The Impact of a Machine Learning Early Warning Score on Hospital Mortality: A Multicenter Clinical Intervention Trial. Crit Care Med. 2022. PMID: 35452010. doi:10.1097/CCM.0000000000005492

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。