HLH风险计算器:基于机器学习预测继发性噬血细胞性淋巴组织细胞增多症的病程与死亡率
该研究纳入来自3个欧洲国家6个中心的167例成人继发性噬血细胞性淋巴组织细胞增多症(sHLH)患者,回顾性分析临床与实验室特征。利用随机森林模型,以两组各8个临床和实验室特征分别预测初始疾病严重程度(IDS,定义为入住ICU或90天内未入住ICU死亡)及30、60、90、180、365天死亡率。模型在包含32例(IDS)或43例(死亡率)sHLH患者的留出测试集上测试,显示出较强的判别能力、整体性能和准确的風險预测。血清可溶性白介素-2受体(sIL-2R)和 albumin(用于IDS)或sIL-2R和血小板计数(用于死亡率预测)对模型预测贡献最大。结论认为该计算器为探索性工具,需外部验证评估其有效性、适用性和稳健性,目前仅限研究用途(www.hlh-risk-calculator.com),不用于临床决策。
要点
- HLH风险计算器基于机器学习,可预测sHLH患者IDS(入住ICU或90天内未入住ICU死亡)及30至365天死亡率。
- 模型在留出测试集(IDS n=32;死亡率 n=43)中表现出较强的判别能力和整体性能。
- sIL-2R和 albumin 对IDS预测贡献最强;sIL-2R和血小板计数对死亡率预测贡献最强。
- 该工具目前仅限研究用途,不用于临床决策,需外部验证评估其有效性、适用性和稳健性。
适用人群与场景
- 成人继发性噬血细胞性淋巴组织细胞增多症(sHLH)患者,来自3个欧洲国家的6个研究中心的回顾性队列。
诊断标准与关键阈值
- 初始疾病严重程度(IDS)定义为入住ICU或90天内未入住ICU死亡。
研究设计与关键结果
- 研究类型:回顾性多中心队列研究,纳入167例成人sHLH患者,来自6个中心、3个欧洲国家。
- 干预/方法:使用随机森林模型,以两组各8个临床和实验室特征分别预测IDS和30、60、90、180、365天死亡率;校准后在留出测试集(IDS n=32;死亡率 n=43)中测试。
- 主要终点结果:模型总体表现出较强的判别能力、整体性能和准确的風險预测。
- 关键次要终点:sIL-2R和 albumin 对IDS预测贡献最强;sIL-2R和血小板计数对死亡率预测贡献最强。
证据类型、等级与局限
- 证据类型:回顾性多中心队列研究(机器学习模型开发与验证)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 该计算器为探索性工具,仅限研究用途,目前不用于临床决策。
- 作者认为需外部验证评估其有效性、适用性和稳健性,之后方可用于真实世界。
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
PURPOSE: Secondary hemophagocytic lymphohistiocytosis (sHLH) is a life-threatening hyperinflammatory condition. While few diagnostic scores are established, none exist to predict both clinical course and time-point specific outcome of sHLH patients so far. We present a machine learning (ML)-based tool to predict Initial Disease Severity (IDS; defined as admission to intensive care units (ICU) OR death < 90 days without ICU admission) and mortality across different time points in sHLH patients.
METHODS: 167 adult sHLH patients from six study centers across three European countries were included retrospectively. Clinical and demographic features, course, survival, and laboratory data were assessed. Random forest models were trained with two sets of eight clinical and laboratory features: one to predict IDS, and five to predict mortality at distinct time points (30, 60, 90, 180 or 365 days). After calibration, the models were tested against hold-out test sets containing n = 32 (IDS) or n = 43 (mortality) sHLH patients.
RESULTS: Overall, the models demonstrated strong discriminatory ability, overall performance, and accurate prediction of risk. Serum levels of the soluble interleukin-2 receptor (sIL-2R) and albumin (for IDS) or sIL-2R and platelet counts (for mortality prediction) showed the strongest contributions to the models' predictions.
CONCLUSION: The HLH-Risk-Calculator is an exploratory tool predicting the clinical course of sHLH. External validation is critical to assess its validity, applicability, and robustness for real-world use. To this end, the calculator is available at www.hlh-risk-calculator.com for research use only, and is currently not intended for clinical decision-making.
参考来源
- Ruzicka M, Stubbe HC, Fauser J, et al. The HLH-Risk-Calculator is a machine learning-based tool to predict course & mortality of secondary hemophagocytic lymphohistiocytosis. Intensive Care Med. 2026. PMID: 42377458. doi:10.1007/s00134-026-08515-1
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。