结局选择对脓毒症风险患者预测模型性能的影响
该研究回顾性分析了2014年1月至2017年9月12家医院收治的疑似感染成人住院患者,利用常规收集的临床数据构建 logistic 回归模型,分别预测住院死亡、住院死亡或ICU住院时间大于72小时的复合结局、30天死亡和90天死亡四种结局,并用受试者工作特征曲线下面积和校准图比较模型性能。在52,184例住院中,住院死亡2,030例(4%),复合结局6,659例(13%),30天死亡3,417例(7%),90天死亡5,655例(11%)。以医院内结局推导的模型预测30天和90天死亡时,曲线下面积下降,且对非推导结局的校准变差。作者认为,解读和应用疑似脓毒症患者风险模型时应考虑这些发现。
要点
- 在52,184例疑似感染住院患者中,住院死亡2,030例(4%),30天死亡3,417例(7%),90天死亡5,655例(11%),复合ICU住院时间大于72小时或住院死亡6,659例(13%)。
- 以住院死亡推导的模型预测30天死亡时,曲线下面积从0.88降至0.85(-0.03),预测90天死亡时从0.88降至0.81(-0.07),均 p < 0.01。
- 以复合ICU住院时间大于72小时或住院死亡推导的模型预测30天死亡时,曲线下面积从0.90降至0.81(-0.09),预测90天死亡时从0.90降至0.76(-0.14),均 p < 0.01。
- 模型对推导结局校准良好(均方根误差5-15),但对替代结局校准较差(均方根误差8-35)。
- 解读和应用疑似脓毒症患者风险模型时,应考虑结局选择对模型性能的影响。
适用人群与场景
- 2014年1月至2017年9月在12家医院住院的疑似感染成人患者。
- 研究为回顾性分析,使用常规收集的临床数据。
研究设计与关键结果
- 研究类型为回顾性分析,纳入12家医院52,184例疑似感染住院成人,利用常规临床数据构建 logistic 回归模型预测四种结局。
- 住院死亡2,030例(4%),复合ICU住院时间大于72小时或住院死亡6,659例(13%),30天死亡3,417例(7%),90天死亡5,655例(11%)。
- 以住院死亡推导的模型预测30天死亡时曲线下面积从0.88降至0.85(-0.03),预测90天死亡时从0.88降至0.81(-0.07),均 p < 0.01。
- 以复合ICU住院时间大于72小时或住院死亡推导的模型预测30天死亡时曲线下面积从0.90降至0.81(-0.09),预测90天死亡时从0.90降至0.76(-0.14),均 p < 0.01。
- 模型对推导结局校准良好(均方根误差5-15),对替代结局校准较差(均方根误差8-35)。
证据类型、等级与局限
- 证据类型:回顾性分析。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,解读和应用疑似脓毒症患者风险模型时,应考虑结局选择对模型性能的影响。
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
IMPORTANCE: Risk prediction models for patients with suspected sepsis have been derived on and applied to various outcomes, including readily available outcomes such as hospital mortality and ICU admission as well as longer-term mortality outcomes that may be more important to patients. It is unknown how selecting different outcomes influences model performance in patients at risk for sepsis.
OBJECTIVES: Evaluate the impact of outcome selection on risk model performance and weighting of individual predictor variables.
DESIGN SETTING AND PARTICIPANTS: We retrospectively analyzed adults hospitalized with suspected infection from January 2014 to September 2017 at 12 hospitals.
MAIN OUTCOMES AND MEASURES: We used routinely collected clinical data to derive logistic regression models for four outcomes: hospital mortality, composite ICU length of stay greater than 72 hours or hospital mortality, 30-day mortality, and 90-day mortality. We compared the performance of the models using area under the receiver operating characteristic curve and calibration plots.
RESULTS: Among 52,184 admissions, 2,030 (4%) experienced hospital mortality, 6,659 (13%) experienced the composite of hospital mortality or ICU length of stay greater than 72 hours, 3,417 (7%) experienced 30-day mortality, and 5,655 (11%) experienced 90-day mortality. Area under the receiver operating characteristic curves decreased when hospital-based models were applied to predict 30-day (hospital mortality = 0.88-0.85; -0.03, composite ICU length of stay greater than 72 hours or hospital mortality = 0.90-0.81; -0.09) and 90-day mortality (hospital mortality = 0.88-0.81; -0.07, composite ICU length of stay greater than 72 hours or hospital mortality = 0.90-0.76; -0.14; all p < 0.01). Models were well calibrated for derived (root-mean-square error = 5-15) but not alternate outcomes (root-mean-square error = 8-35).
CONCLUSIONS AND RELEVANCE: Risk models trained to predict readily available hospital-based outcomes in suspected sepsis show poorer discrimination and calibration when applied to 30- and 90-day mortality. Interpretation and application of risk models for patients at risk of sepsis should consider these findings.
参考来源
- Taylor SP, Chou SH, McWilliams AD, et al. The Effect of Outcome Selection on the Performance of Prediction Models in Patients at Risk for Sepsis. Crit Care Explor. 2020. PMID: 32166298. doi:10.1097/CCE.0000000000000078
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。