文献速递MDS 与骨髓增殖性肿瘤白血病

基于外周血的可解释机器学习模型无创检测JAK2 V617F阳性MPN中中度至重度骨髓纤维化:多中心初步概念验证研究

Interpretable machine learning model using peripheral blood for non-invasive detection of moderate-to-severe myelofibrosis in JAK2 V617F-positive MPNs: A multicentre pilot proof-of-concept study.
PubMed 文献 · Br J Haematol · 2026-05-27

Progression to moderate-to-severe myelofibrosis (MF) in JAK2 V617F-positive myeloproliferative neoplasms (MPNs) is often clinically silent, and bone marrow biopsy is invasive and unsuitable for regular monitoring.…

要点

  • 支持向量机模型基于外周血参数检测中度至重度MF的AUC达0.916(95%CI 0.83-0.99)。
  • 血红蛋白、IL-1β和年龄是模型中最具影响力的特征。
  • IL-1β随纤维化进展上调,芦可替尼或聚乙二醇干扰素α可逆转而羟基脲不能。

核心结论

  • 基于外周血的可解释机器学习工具对识别中度至重度MF显示出初步准确性,并提示IL-1β作为机制性生物标志物。
  • 数据支持其作为补充方法的潜在用途,但骨髓活检仍是参考标准。

研究设计与样本

  • 多中心初步概念验证研究,336例JAK2 V617F阳性MPN患者用于模型训练,92例用于外部验证。
  • 分子验证聚焦于Jak2V617F敲入小鼠和共培养实验中的IL-1β。

主要发现

  • 支持向量机模型区分度最佳,AUC=0.916(95%CI 0.83-0.99),校准良好且临床效用最高。
  • SHAP解释识别血红蛋白、IL-1β和年龄为最具影响力特征。
  • 临床前实验证实IL-1β随纤维化进展上调,芦可替尼或聚乙二醇干扰素α可逆转而羟基脲不能。

关键数值与推荐

  • 支持向量机模型AUC=0.916(95%CI 0.83-0.99)。
  • SHAP识别最具影响力特征:血红蛋白、IL-1β和年龄。

临床怎么用

  • 该血基工具可作为JAK2 V617F阳性MPN患者中度至重度MF的无创补充检测手段。
  • 骨髓活检仍是诊断参考标准,该模型不能替代活检。

局限性

  • 为初步概念验证研究,样本量有限(训练336例、外部验证92例)。
  • 骨髓活检仍是参考标准,模型诊断性能需进一步验证。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Progression to moderate-to-severe myelofibrosis (MF) in JAK2 V617F-positive myeloproliferative neoplasms (MPNs) is often clinically silent, and bone marrow biopsy is invasive and unsuitable for regular monitoring. In this multicentre pilot proof-of-concept study, we aimed to develop an interpretable, non-invasive model using peripheral blood parameters to detect significant fibrosis and to explore the inflammatory mechanisms involved. A total of 336 JAK2 V617F-positive MPN patients were enrolled for model training and 92 for external validation. Candidate features (blood counts, cytokines, clinical data) were screened using least absolute shrinkage and selection operator (LASSO) and Boruta algorithms. Ten machine learning methods were compared; model discrimination, calibration and clinical benefit were evaluated. Molecular validation focused on interleukin-1β (IL-1β) in Jak2V617F knock-in mice and co-culture assays. The support vector machine model yielded the best discrimination (area under the curve [AUC] = 0.916, 95% CI 0.83-0.99), good calibration and highest clinical utility. SHapley Additive exPlanations (SHAP) interpretation identified haemoglobin, IL-1β and age as the most influential features. Preclinical experiments confirmed IL-1β upregulation with fibrosis progression, reversed by ruxolitinib or pegylated interferon-α but not hydroxyurea (hydroxycarbamide). This multicentre pilot proof-of-concept study demonstrates that an interpretable blood-based tool shows preliminary accuracy for identifying moderate-to-severe MF and underscores IL-1β as a mechanistic biomarker. The data support potential utility as a complementary approach; bone marrow biopsy remains the reference standard.

来源:Br J Haematol,查看原文。版权归原作者所有。

引用

  1. Hao Z, Song M, Wang H, et al. Interpretable machine learning model using peripheral blood for non-invasive detection of moderate-to-severe myelofibrosis in JAK2 V617F-positive MPNs: A multicentre pilot proof-of-concept study. Br J Haematol. 2026. PMID: 42203504. doi:10.1111/bjh.70552

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。