文献速递重症综合管理与镇静镇痛

全球开源疾病严重程度评分(GOSSIS)

The Global Open Source Severity of Illness Score (GOSSIS).
PubMed 文献 · Crit Care Med · 2022-03-25
一句话结论GOSSIS-1是利用ICU入住首24小时数据的免费开源住院死亡预测算法,在澳大利亚、新西兰和美国三国队列中区分度与校准均优。

研究合并澳大利亚与新西兰重症监护学会成人患者数据库(ANZICS-APD,249,229例、162家医院)和美国eICU协作研究数据库(eICU-CRD,131,051例、204家医院)两个多中心队列,按70%/30%拆分训练集与测试集,开发并验证GOSSIS-1。该评分使用ICU入住首24小时的生命体征与实验室极值、入ICU诊断、格拉斯哥昏迷评分、慢性合并症及入院/人口学变量。测试集区分度AUROC 0.918(95%CI 0.915-0.921),校准优良(SMR 0.986,95%CI 0.966-1.005;Brier评分0.050),且优于APACHE-IIIj和APACHE-IVa。GOSSIS-1是跨医疗体系通用的免费开源住院死亡预测工具。

要点

  • GOSSIS-1仅用ICU入住首24小时数据(生命体征与实验室极值、入ICU诊断、格拉斯哥昏迷评分、慢性合并症、入院/人口学变量)预测住院死亡。
  • 在合并测试集中区分度AUROC 0.918(95%CI 0.915-0.921),校准SMR 0.986(95%CI 0.966-1.005)、Brier评分0.050。
  • 分库验证:ANZICS-APD AUROC 0.925、SMR 0.982、Brier评分0.047;eICU-CRD AUROC 0.904、SMR 0.992、Brier评分0.055。
  • 对照APACHE-IIIj(ANZICS-APD)AUROC 0.904、SMR 0.594、Brier评分0.059;APACHE-IVa(eICU-CRD)AUROC 0.869、SMR 0.770、Brier评分0.063。
  • GOSSIS-1为免费开源算法,三个国家数据中均表现优良,作者结论为适用于重症患者住院死亡预测。

适用人群与场景

  • 澳大利亚与新西兰ANZICS-APD及美国eICU-CRD两个多中心数据库的ICU入住患者,纳入2014—2015年出院的所有ICU入住记录。
  • 排除年龄小于16岁、ICU入住不足6小时以及既往有ICU入住史的患者。

研究设计与关键结果

  • 研究设计:合并多个重症多中心队列(注册数据与电子健康记录),按70%训练集、30%测试集拆分,分别仅用于开发与评估;数据缺失时进行插补。
  • 样本量:ANZICS-APD 249,229例(162家医院),eICU-CRD 131,051例(204家医院)。
  • GOSSIS-1在测试集的区分度AUROC 0.918(95%CI 0.915-0.921),校准SMR 0.986(95%CI 0.966-1.005),Brier评分0.050。
  • 分库性能:ANZICS-APD AUROC 0.925、SMR 0.982、Brier评分0.047;eICU-CRD AUROC 0.904、SMR 0.992、Brier评分0.055。
  • 与APACHE-IIIj(ANZICS-APD)比较:GOSSIS-1 AUROC 0.918 vs APACHE-IIIj 0.904,SMR 0.986 vs 0.594,Brier评分0.050 vs 0.059。
  • 与APACHE-IVa(eICU-CRD)比较:GOSSIS-1 AUROC 0.918 vs APACHE-IVa 0.869,SMR 0.986 vs 0.770,Brier评分0.050 vs 0.063。

证据类型、等级与局限

  • 证据类型:基于多个重症多中心队列(注册数据与电子健康记录)的预测模型开发与验证研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为GOSSIS-1是跨医疗体系通用的免费开源住院死亡预测算法,在三个国家中均达到优良的区分度与校准。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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

OBJECTIVES: To develop and demonstrate the feasibility of a Global Open Source Severity of Illness Score (GOSSIS)-1 for critical care patients, which generalizes across healthcare systems and countries.

DESIGN: A merger of several critical care multicenter cohorts derived from registry and electronic health record data. Data were split into training (70%) and test (30%) sets, using each set exclusively for development and evaluation, respectively. Missing data were imputed when not available.

SETTING/PATIENTS: Two large multicenter datasets from Australia and New Zealand (Australian and New Zealand Intensive Care Society Adult Patient Database [ANZICS-APD]) and the United States (eICU Collaborative Research Database [eICU-CRD]) representing 249,229 and 131,051 patients, respectively. ANZICS-APD and eICU-CRD contributed data from 162 and 204 hospitals, respectively. The cohort included all ICU admissions discharged in 2014-2015, excluding patients less than 16 years old, admissions less than 6 hours, and those with a previous ICU stay.

INTERVENTIONS: Not applicable.

MEASUREMENTS AND MAIN RESULTS: GOSSIS-1 uses data collected during the ICU stay's first 24 hours, including extrema values for vital signs and laboratory results, admission diagnosis, the Glasgow Coma Scale, chronic comorbidities, and admission/demographic variables. The datasets showed significant variation in admission-related variables, case-mix, and average physiologic state. Despite this heterogeneity, test set discrimination of GOSSIS-1 was high (area under the receiver operator characteristic curve [AUROC], 0.918; 95% CI, 0.915-0.921) and calibration was excellent (standardized mortality ratio [SMR], 0.986; 95% CI, 0.966-1.005; Brier score, 0.050). Performance was held within ANZICS-APD (AUROC, 0.925; SMR, 0.982; Brier score, 0.047) and eICU-CRD (AUROC, 0.904; SMR, 0.992; Brier score, 0.055). Compared with GOSSIS-1, Acute Physiology and Chronic Health Evaluation (APACHE)-IIIj (ANZICS-APD) and APACHE-IVa (eICU-CRD), had worse discrimination with AUROCs of 0.904 and 0.869, and poorer calibration with SMRs of 0.594 and 0.770, and Brier scores of 0.059 and 0.063, respectively.

CONCLUSIONS: GOSSIS-1 is a modern, free, open-source inhospital mortality prediction algorithm for critical care patients, achieving excellent discrimination and calibration across three countries.

来源:Crit Care Med,查看原文。版权归原作者所有。

参考来源

  1. Raffa JD, Johnson AEW, O'Brien Z, et al. The Global Open Source Severity of Illness Score (GOSSIS). Crit Care Med. 2022. PMID: 35354159. doi:10.1097/CCM.0000000000005518

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。