指南与共识重症综合管理与镇静镇痛消化、代谢与肾脏急症

跨算法机器学习与共识特征用于脓毒症诱导凝血病早期弥散性血管内凝血风险预测

Cross-algorithm machine learning and consensus features for early disseminated intravascular coagulation risk prediction in sepsis-induced coagulopathy.
指南 / 共识 · J Transl Med · 2026-03-31
一句话结论基于7项常规指标构建的GB模型在SIC患者中预测DIC进展,内部验证AUC 0.75、外部验证AUC 0.74,作者认为可作为决策支持工具。

本研究为回顾性多中心研究,整合MIMIC-IV v3.1数据库与温州医科大学附属第一医院独立队列,共纳入4874例SIC患者(本地队列1629例,MIMIC-IV 3245例)。利用ICU入住48小时内采集的61项常规临床变量,设计两阶段机器学习框架:第一阶段16种算法结合11种特征重要性排序方法及后向消除筛选各自最优特征子集;第二阶段跨算法共识策略提取全局稳定特征并构建简约可解释预测模型。共识分析识别7个高度稳定预测因子:ICU住院时长、血管加压药、白蛋白水平、MDRD估算值、LODS评分、SOFA评分、CRRT。最终GB模型内部验证F1-score 0.71、AUC 0.75;外部验证F1-score 0.92、AUC 0.74、ACC 0.92。可解释性分析显示疾病严重程度、器官功能障碍和治疗强度是DIC进展的主要驱动因素。作者结论认为该模型为脓毒症相关凝血病的精准风险分层和靶向干预提供实用决策支持工具,但需前瞻性多中心研究纳入动态时间序列数据进一步验证和扩展实时临床适用性。

要点

  • 在4874例SIC患者中,跨算法共识识别出7个稳定预测因子:ICU住院时长、血管加压药、白蛋白水平、MDRD估算值、LODS评分、SOFA评分、CRRT。
  • 最终GB模型内部验证F1-score 0.71、AUC 0.75;外部验证(MIMIC-IV队列)F1-score 0.92、AUC 0.74、ACC 0.92。
  • 可解释性分析确认疾病严重程度、器官功能障碍和治疗强度是DIC进展的主要驱动因素。
  • 列线图校准良好,在DCA广泛风险阈值范围内提供一致的净临床获益。
  • 作者认为该模型可作为脓毒症相关凝血病精准风险分层和靶向干预的实用决策支持工具,但需前瞻性多中心研究纳入动态时间序列数据进一步验证。

适用人群与场景

  • 脓毒症诱导凝血病(SIC)患者,共4874例,包括温州医科大学附属第一医院本地队列1629例和MIMIC-IV v3.1数据库队列3245例。
  • 研究场景为ICU,使用ICU入住48小时内采集的61项常规临床变量进行预测。

研究设计与关键结果

  • 研究类型为回顾性多中心研究,整合MIMIC-IV v3.1数据库与温州医科大学附属第一医院独立队列,共纳入4874例SIC患者(本地队列1629例,MIMIC-IV 3245例)。
  • 采用两阶段机器学习框架:第一阶段16种机器学习算法结合11种特征重要性排序方法和后向消除识别算法特异性最优特征子集;第二阶段跨算法共识策略提取全局稳定特征并构建简约可解释预测模型。
  • 单算法优化中,梯度提升分类器(GB)模型在性能和稳健性之间达到最佳平衡。
  • 跨算法共识分析识别7个高度稳定预测因子:ICU住院时长、血管加压药、白蛋白水平、MDRD估算值、LODS评分、SOFA评分、CRRT。
  • 最终GB模型(含7个特征)内部验证队列F1-score 0.71、AUC 0.75;外部验证队列(MIMIC-IV)F1-score 0.92、AUC 0.74、ACC 0.92。
  • 可解释性分析(置换特征重要性、SHAP、列线图)确认疾病严重程度、器官功能障碍和治疗强度是DIC进展的主要驱动因素。
  • 列线图校准良好,决策曲线分析显示在广泛风险阈值范围内提供一致的净临床获益。

证据类型、等级与局限

  • 证据类型:回顾性多中心研究(整合数据库与独立队列),无原文给出的证据等级或推荐强度。
  • 局限:原文报告需前瞻性多中心研究纳入动态时间序列数据以进一步验证和扩展模型的实时临床适用性。

对床旁实践的改变

  • 作者认为该模型可基于7项常规临床指标(ICU住院时长、血管加压药、白蛋白水平、MDRD估算值、LODS评分、SOFA评分、CRRT)为SIC患者进展为DIC的风险分层提供决策支持工具。
  • 作者认为该模型可用于脓毒症相关凝血病的精准风险分层和靶向干预。
  • 原文指出该模型需前瞻性多中心研究纳入动态时间序列数据进一步验证和扩展实时临床适用性。

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

BACKGROUND: Sepsis-induced coagulopathy (SIC) represents an early and potentially reversible stage of coagulation dysfunction in sepsis, whereas progression to disseminated intravascular coagulation (DIC) is associated with multi-organ failure and markedly increased mortality. Although existing diagnostic criteria and machine learning (ML) models have demonstrated utility in broad sepsis populations, they lack specificity for identifying high-risk subgroups within SIC patients who are most likely to deteriorate into DIC. Timely and precise risk stratification at this critical transition point remains an unmet clinical need. METHODS: We conduct a retrospective, multicenter study integrating data from MIMIC-IV v3.1 database and an independent cohort from the First Affiliated Hospital of Wenzhou Medical University. A total of 4,874 SIC patients are included, comprising 1,629 patients from the local cohort and 3,245 patients from MIMIC-IV. Using 61 routinely available clinical variables collected within 48 h of ICU admission, we design a two-stage ML framework. In phase I, 16 ML algorithms are combined with 11 feature importance ranking methods and backward elimination to identify algorithm-specific optimal feature subsets. In phase II, a cross-algorithm consensus strategy is applied to extract globally stable features and construct a minimalist, interpretable predictive model. Model performance is evaluated using accuracy (ACC), area under the receiver operating characteristic curve (AUC), and F1-score. External validation was performed using the MIMIC-IV cohort. Model interpretability was assessed through permutation feature importance, SHapley Additive exPlanations (SHAP), and a clinically deployable nomogram, with calibration curves and decision curve analysis (DCA) used to assess clinical utility. RESULTS: Across single-algorithm optimization, the Gradient Boosting Classifier (GB) model achieved the best balance between performance and robustness. Cross-algorithm consensus analysis identified seven highly stable predictors: intensive care unit (ICU) length of stay (LOS), vasopressor, albumin (ALB) level, Modification of Diet in Renal Disease (MDRD) estimate, Logistic Organ Dysfunction System (LODS) score, Sequential Organ Failure Assessment (SOFA) score, Continuous Renal Replacement Therapy (CRRT). The final GB model incorporating these seven features achieved an F1-score of 0.71 and an AUC of 0.75 in the internal validation cohort, while demonstrating excellent generalization in the external validation cohort (F1-score 0.92, AUC 0.74, ACC 0.92). Interpretability analyses confirmed that disease severity, organ dysfunction, and treatment intensity were the primary drivers of DIC progression. The nomogram exhibited good calibration and provided consistent net clinical benefit across a wide range of risk thresholds in DCA. CONCLUSIONS: We propose a robust and interpretable ML framework for early identification of SIC patients at high risk of progression to DIC, based on only seven routinely available clinical indicators. By transitioning from algorithm-specific optimization to cross-algorithm consensus feature selection, this study achieves a favorable balance between predictive performance, generalizability, and clinical usability. This model offers a practical decision-support tool for precision risk stratification and targeted intervention in sepsis-associated coagulopathy. Prospective multicenter studies incorporating dynamic time-series data are warranted to further validate and extend its real-time clinical applicability.

来源:J Transl Med,查看原文。版权归原作者所有。

参考来源

  1. Chen F, Mei X, Yang D, et al. Cross-algorithm machine learning and consensus features for early disseminated intravascular coagulation risk prediction in sepsis-induced coagulopathy. J Transl Med. 2026. PMID: 41918111. doi:10.1186/s12967-026-08067-4

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。