纽约脓毒症严重程度评分:脓毒症风险调整严重程度模型的开发
为在纽约州各医院间对成人脓毒症患者医院死亡率进行准确、标准化的病例组合调整比较,纽约州卫生部利用2015年1月1日至2015年12月31日前瞻性提交至数据库的数据,回顾性评估了179家医院43204例严重脓毒症与脓毒性休克患者。采用最大似然逻辑回归估计模型系数,用90%随机样本开发模型、其余10%验证;Hosmer-Lemeshow拟合优度P值远大于0.05提示校准良好,开发集与验证集受试者工作特征曲线下面积分别为0.770(95%CI 0.765-0.775)和0.773(95%CI 0.758-0.787),提示区分度良好。死亡率随年龄、合并症和乳酸升高而增加。该脓毒症特异性模型为成人严重脓毒症与脓毒性休克患者的标准化死亡率比较提供了准确、全面的方法。
要点
- 模型基于纽约州179家医院43204例严重脓毒症与脓毒性休克患者开发,数据提交时间为2015年1月1日至2015年12月31日。
- 开发集受试者工作特征曲线下面积0.770(95%CI 0.765-0.775),验证集0.773(95%CI 0.758-0.787),区分度良好。
- Hosmer-Lemeshow拟合优度P值远大于0.05,提示模型校准良好;开发集与验证集估计死亡概率分布相似。
- 死亡率随年龄升高、合并症增多和乳酸升高而增加。
- 该脓毒症特异性模型可用于成人严重脓毒症与脓毒性休克患者医院死亡率的标准化比较。
适用人群与场景
- 纽约州179家医院的成人严重脓毒症与脓毒性休克患者,共43204例,数据于2015年1月1日至2015年12月31日前瞻性提交至数据库。
研究设计与关键结果
- 研究类型为对前瞻性收集数据的回顾性评估,纳入纽约州179家医院43204例严重脓毒症与脓毒性休克患者,无干预。
- 采用最大似然逻辑回归估计纽约州风险模型系数,以逻辑回归模型估计死亡概率;变量纳入在模型构建过程中确定,变量间交互作用在具有临床意义且P值小于0.05时纳入。
- 模型开发使用90%随机样本,其余10%用于验证;Hosmer-Lemeshow拟合优度P值远大于0.05,提示校准良好。
- 开发集受试者工作特征曲线下面积0.770(95%CI 0.765-0.775),验证集0.773(95%CI 0.758-0.787),提示区分度良好;开发集与验证集估计死亡概率分布相似。
- 死亡率随年龄升高、合并症增多和乳酸升高而增加。
证据类型、等级与局限
- 证据类型:对前瞻性收集数据的回顾性评估。
- 局限:原文未报告局限性。
对床旁实践的改变
- 该脓毒症特异性模型为成人严重脓毒症与脓毒性休克患者提供了标准化医院死亡率比较的准确、全面方法。
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: In accordance with Rory's Regulations, hospitals across New York State developed and implemented protocols for sepsis recognition and treatment to reduce variations in evidence informed care and preventable mortality. The New York Department of Health sought to develop a risk assessment model for accurate and standardized hospital mortality comparisons of adult septic patients across institutions using case-mix adjustment.
DESIGN: Retrospective evaluation of prospectively collected data.
PATIENTS: Data from 43,204 severe sepsis and septic shock patients from 179 hospitals across New York State were evaluated.
SETTINGS: Prospective data were submitted to a database from January 1, 2015, to December 31, 2015.
INTERVENTIONS: None.
MEASUREMENT AND MAIN RESULTS: Maximum likelihood logistic regression was used to estimate model coefficients used in the New York State risk model. The mortality probability was estimated using a logistic regression model. Variables to be included in the model were determined as part of the model-building process. Interactions between variables were included if they made clinical sense and if their p values were less than 0.05. Model development used a random sample of 90% of available patients and was validated using the remaining 10%. Hosmer-Lemeshow goodness of fit p values were considerably greater than 0.05, suggesting good calibration. Areas under the receiver operator curve in the developmental and validation subsets were 0.770 (95% CI, 0.765-0.775) and 0.773 (95% CI, 0.758-0.787), respectively, indicating good discrimination. Development and validation datasets had similar distributions of estimated mortality probabilities. Mortality increased with rising age, comorbidities, and lactate.
CONCLUSIONS: The New York Sepsis Severity Score accurately estimated the probability of hospital mortality in severe sepsis and septic shock patients. It performed well with respect to calibration and discrimination. This sepsis-specific model provides an accurate, comprehensive method for standardized mortality comparison of adult patients with severe sepsis and septic shock.
参考来源
- Phillips GS, Osborn TM, Terry KM, et al. The New York Sepsis Severity Score: Development of a Risk-Adjusted Severity Model for Sepsis. Crit Care Med. 2018. PMID: 29206765. doi:10.1097/CCM.0000000000002824
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。