机器学习模型对PICU凤凰脓毒症患儿院内死亡率的预后准确性
本研究为回顾性队列分析,纳入2010年1月1日至2022年5月10日美国亚特兰大两家PICU中63,824例疑似或确诊感染患儿,应用凤凰脓毒症评分标准(24小时内≥2分)定义脓毒症,比较多种机器学习模型预测院内死亡的准确性。18,389/63,824(29%)患儿疑似感染,其中5,355例在入PICU 24小时内符合凤凰脓毒症标准,514例(9.6%)院内死亡,2,848例(53.2%)死亡或PICU停留≥72小时;凤凰脓毒症休克患儿院内死亡386例(16.4%),1,294例(54.9%)死亡或PICU停留≥72小时。随机森林模型AUPRC为0.52-0.70,优于其他模型及凤凰脓毒症评分≥2。作者认为机器学习方法预测疑似感染患儿院内死亡的准确性优于应用凤凰脓毒症标准。
要点
- 在5,355例符合凤凰脓毒症标准的PICU患儿中,514例(9.6%)院内死亡,2,848例(53.2%)死亡或PICU停留≥72小时。
- 凤凰脓毒症休克患儿院内死亡386例(16.4%),1,294例(54.9%)死亡或PICU停留≥72小时。
- 随机森林模型预测院内死亡的AUPRC为0.52-0.70(95%CI范围0.47-0.71),在七种模型中表现最佳。
- 决策树模型AUPRC仅0.30-0.38(95%CI范围0.28-0.40),低于其他机器学习模型及凤凰脓毒症评分≥2。
- 作者认为,机器学习方法预测疑似感染患儿院内死亡的准确性优于应用凤凰脓毒症标准。
适用人群与场景
- 2010年1月1日至2022年5月10日在美国佐治亚州亚特兰大两家PICU收治的疑似或确诊感染入院诊断的患儿,共63,824例。
- 其中18,389/63,824(29%)为疑似感染,5,355例在入PICU 24小时内符合凤凰脓毒症标准。
诊断标准与关键阈值
- 凤凰脓毒症标准:疑似或确诊感染且凤凰脓毒症评分≥2分。
- 凤凰脓毒症评分标准应用于入PICU 24小时内收集的数据。
研究设计与关键结果
- 研究类型:回顾性队列分析,纳入两家PICU共63,824例疑似或确诊感染患儿,中位年龄3.9岁(IQR 1.1-10.9),女性45%。
- 5,355例符合凤凰脓毒症标准,其中514例(9.6%)院内死亡,2,848例(53.2%)死亡或PICU停留≥72小时;凤凰脓毒症休克患儿中386例(16.4%)院内死亡,1,294例(54.9%)死亡或PICU停留≥72小时。
- 预测院内死亡的AUPRC:多变量逻辑回归0.48-0.65(95%CI范围0.42-0.66),轻量梯度提升机0.50-0.70(95%CI范围0.44-0.70),随机森林0.52-0.70(95%CI范围0.47-0.71),极端梯度提升0.50-0.70(95%CI范围0.44-0.70),支持向量机0.49-0.67(95%CI范围0.43-0.68),多层感知机0.49-0.66(95%CI范围0.45-0.67),决策树0.30-0.38(95%CI范围0.28-0.40)。
- 预测院内死亡的AUROC:多变量逻辑回归0.82-0.88(95%CI范围0.82-0.90),轻量梯度提升机0.84-0.88(95%CI范围0.84-0.90),随机森林0.81-0.88(95%CI范围0.81-0.90),极端梯度提升0.84-0.88(95%CI范围0.83-0.90),支持向量机0.82-0.87(95%CI范围0.82-0.90),多层感知机0.80-0.86(95%CI范围0.79-0.89),决策树0.76-0.82(95%CI范围0.75-0.85)。
- 结论:随机森林模型AUPRC优于轻量梯度提升机、极端梯度提升、逻辑回归、多层感知机、支持向量机和决策树模型或凤凰脓毒症评分≥2。
证据类型、等级与局限
- 证据类型:回顾性队列分析。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,机器学习方法预测疑似感染患儿院内死亡的准确性优于应用凤凰脓毒症标准。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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
Objective: The Phoenix sepsis criteria define sepsis in children with suspected or confirmed infection who have ≥2 in the Phoenix Sepsis Score. The adoption of the Phoenix sepsis criteria eliminated the Systemic Inflammatory Response Syndrome criteria from the definition of pediatric sepsis. The objective of this study is to derive and validate machine learning models predicting in-hospital mortality for children with suspected or confirmed infection or who met the Phoenix sepsis criteria for sepsis and septic shock. Materials and Methods: Retrospective cohort analysis of 63,824 patients with suspected or confirmed infection admission diagnosis in two pediatric intensive care units (PICUs) in Atlanta, Georgia, from January 1, 2010, through May 10, 2022. The Phoenix Sepsis Score criteria were applied to data collected within 24 h of PICU admission. The primary outcome was in-hospital mortality. The composite secondary outcome was in-hospital mortality or PICU length of stay (LOS) ≥ 72 h. Model-based score performance measures were the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC). Results: Among 18,389/63,824 (29%) children with suspected infection (median age [25th - 75th interquartile range [IQR]): 3.9 [1.1,10.9]; female, 45%, a total of 5,355 met Phoenix sepsis criteria within 24 h of PICU admission. Of the children with Phoenix sepsis, a total of 514 (9.6%) died in the hospital, and 2,848 (53.2%) died or had a PICU stay of ≥72 h. Children with Phoenix septic shock had an in-hospital mortality of 386 (16.4%) and 1,294 (54.9%) had in-hospital mortality or PICU stay of ≥72 h. For children with Phoenix sepsis and Phoenix septic shock, the multivariable logistic regression, light gradient boosting machine, random forest, eXtreme Gradient Boosting, support vector machine, multilayer perceptron, and decision tree models predicting in-hospital mortality had AUPRCs of 0.48-0.65 (95% CI range: 0.42-0.66), 0.50-0.70 (95% CI range: 0.44-0.70), 0.52-0.70 (95% CI range: 0.47-0.71), 0.50-0.70 (95% CI range: 0.44-0.70), 0.49-0.67 (95% CI range: 0.43-0.68), 0.49-0.66 (95% CI range: 0.45-0.67), and 0.30-0.38 (95% CI range: 0.28-0.40) and AUROCs of 0.82-0.88 (95% CI range: 0.82-0.90), 0.84-0.88 (95% CI range: 0.84-0.90), 0.81-0.88 (95% CI range: 0.81-0.90), 0.84-0.88 (95% CI range: 0.83-0.90), 0.82-0.87 (95% CI range: 0.82-0.90), 0.80-0.86 (95% CI range: 0.79-0.89), and 0.76-0.82 (95% CI range: 0.75-0.85), respectively. Conclusion: Among children with Phoenix sepsis admitted to a PICU, the random forest model had the best AUPRC for in-hospital mortality compared to the light gradient boosting machine, eXtreme Gradient Boosting, logistic regression, multilayer perceptron, support vector machine, and decision tree models or a Phoenix Sepsis Score ≥ 2. These findings suggest that machine learning methods to predict in-hospital mortality in children with suspected infection predict mortality in a PICU setting with more accuracy than application of the Phoenix sepsis criteria.
参考来源
- Moore R, Chanci D, Brown S, et al. PROGNOSTIC ACCURACY OF MACHINE LEARNING MODELS FOR IN-HOSPITAL MORTALITY AMONG CHILDREN WITH PHOENIX SEPSIS ADMITTED TO THE PEDIATRIC INTENSIVE CARE UNIT. Shock. 2025. PMID: 39671551. doi:10.1097/SHK.0000000000002501
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。