以降钙素原为锚点的机器学习模型在儿童革兰阴性脓毒症培养前识别中的应用:四中心研究
该研究为四中心回顾性分析,纳入431例同时开具血培养和降钙素原的儿科就诊,主要结局为革兰阴性血流感染合并Phoenix-8器官功能障碍(除外免疫域),共20例(4.6%)达到。单用降钙素原AUROC为0.762,四特征成人脓毒症对齐模型AUROC为0.862,系统筛选出的三特征模型(降钙素原、血小板计数、肌酐)AUROC为0.884(BCa 95%CI 0.871-0.982),随机森林与LASSO结果一致(0.874)。三特征模型较单用降钙素原AUROC提高0.122(p<0.001),阳性似然比12.56,需评估人数2.6。作者认为儿童预测依赖肾功能(肌酐)而非血流动力学,结论为假设生成性,需前瞻性验证。
要点
- 在431例同时开具血培养和降钙素原的儿科就诊中,仅20例(4.6%)达到革兰阴性血流感染合并Phoenix-8器官功能障碍的主要结局。
- 单用降钙素原识别主要结局的AUROC为0.762,四特征成人脓毒症对齐模型AUROC为0.862,其中呼吸频率和收缩压贡献可忽略。
- 三特征模型(降钙素原、血小板计数、肌酐)AUROC为0.884(BCa 95%CI 0.871-0.982),随机森林与LASSO一致为0.874,较单用降钙素原提高0.122(p<0.001)。
- 三特征模型Brier评分0.038低于零模型0.044,阳性似然比12.56,需评估人数2.6。
- 作者指出儿童预测依赖肾功能(肌酐)而非血流动力学,与成人模型不同,结论为假设生成性,需前瞻性验证后方可临床实施。
适用人群与场景
- 四中心回顾性分析的431例儿科就诊,均同时开具血培养和降钙素原检测。
诊断标准与关键阈值
- 主要结局为革兰阴性血流感染合并Phoenix-8器官功能障碍,采用排除免疫域的Phoenix-8标准判定。
- 血培养结果通过基于优先级的自然语言处理算法分为革兰阴性血流感染、革兰阳性血流感染、污染或阴性。
研究设计与关键结果
- 研究类型为四中心回顾性分析,样本量431例儿科就诊,主要结局为革兰阴性血流感染合并Phoenix-8器官功能障碍(除外免疫域),共20例(4.6%)达到。
- 单用降钙素原AUROC为0.762;四特征成人脓毒症对齐模型AUROC为0.862,呼吸频率和收缩压贡献可忽略。
- 系统单变量筛选确定血小板计数和肌酐为最佳共特征,三特征模型(降钙素原、血小板计数、肌酐)AUROC为0.884(BCa 95%CI 0.871-0.982),随机森林与LASSO一致为0.874,Brier评分0.038低于零模型0.044,阳性似然比12.56,需评估人数2.6。
- 三特征模型较单用降钙素原AUROC提高0.122(p<0.001),采用配对折层AUROC检验比较判别能力,校准通过Platt缩放评估。
证据类型、等级与局限
- 证据类型为四中心回顾性分析,采用嵌套重复分层交叉验证和置换重要性分析,随机森林与LASSO为共同主要算法。
- 局限:作者指出这些发现为假设生成性,需在足够效能的队列中进行前瞻性验证后方可临床实施。
对床旁实践的改变
- 作者认为将降钙素原嵌入三特征机器学习模型(降钙素原、血小板计数、肌酐)较单用降钙素原可改善对儿童革兰阴性血流感染合并器官功能障碍的培养前识别,但该发现为假设生成性,需前瞻性验证后方可临床实施。
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: Procalcitonin (PCT) has moderate accuracy for bacteremia detection but is infrequently used in pediatric emergency departments, partly due to poor sensitivity when applied as a standalone threshold and guideline recommendations against its isolated use. We evaluated whether a machine learning (ML) approach that contextualizes PCT with additional clinical features has the potential to improve detection of gram-negative bacteremic organ dysfunction in children prior to culture results.
METHODS: We conducted a retrospective analysis of 431 pediatric encounters across four sites where blood culture and PCT were co-ordered. Blood culture results were classified as gram-negative bloodstream infection (BSI), gram-positive BSI, contaminant, or negative using a priority-based NLP algorithm applied to free-text result strings. The primary outcome was gram-negative BSI with concurrent organ dysfunction ascertained by Phoenix-8 criteria excluding the immunologic domain. We evaluated PCT alone, a four-feature adult sepsis-aligned benchmarking model, and candidate multi-feature combinations identified through systematic univariate screening, using Random Forest (RF) and penalized logistic regression (LASSO) as co-primary algorithms with nested repeated stratified cross-validation and permutation importance analysis. Model discrimination was compared using paired fold-level AUROC testing and calibration was assessed using Platt scaling.
RESULTS: Among 431 encounters with a numeric PCT result, 20 (4.6%) met the primary outcome of gram-negative BSI with Phoenix-8 organ dysfunction. PCT alone achieved AUROC 0.762. A four-feature adult sepsis-aligned model achieved AUROC 0.862; respiratory rate and systolic blood pressure contributed negligibly. Systematic screening identified platelet count and creatinine as optimal co-features; the three-feature model (PCT, platelet count, creatinine) achieved AUROC 0.884 (BCa 95% CI 0.871-0.982), consistent across RF and LASSO (0.874), with Brier score 0.038 below the null model (0.044), and positive likelihood ratio 12.56 (number needed to assess of 2.6).
CONCLUSIONS: PCT alone showed limited performance. Embedding PCT within a 3-feature ML model improved discrimination over PCT alone (delta AUROC 0.122, p<0.001), with consistent performance across RF and LASSO. Unlike adult models, pediatric prediction relied on renal dysfunction (creatinine) rather than hemodynamics. These findings are hypothesis-generating and require prospective validation in adequately powered cohorts before clinical implementation.
参考来源
- Velez T, Dewan M, Badaki-Makun O, et al. PCT-Anchored Machine Learning for Pre-Culture Identification of Gram-Negative Sepsis in Children: A Four-Site Study. Shock. 2026. PMID: 42320014. doi:10.1097/SHK.0000000000002895
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。