基于机器学习的甲状腺眼病细胞因子内分型
研究对101例甲状腺眼病患者检测102种血浆细胞因子,用机器学习识别出四细胞因子特征谱,并通过无监督K-means聚类定义四种内分型,构建CKC评分列线图在外部队列验证。该特征谱可稳健分层患者,CKC评分内部AUC为0.742并在外部验证中保持判别力。
要点
- 机器学习识别出VCAM-1、CCL19、CX3CL1、CXCL13四细胞因子特征谱。
- 该特征谱将TED分为炎症型、增殖型、纤维型和代谢型四种内分型。
- CKC评分列线图预测内分型内部AUC为0.742,外部验证保持判别力。
核心结论
- 四细胞因子特征谱可稳健地将TED患者分为四种免疫学和临床不同的内分型。
- 基于该特征谱的CKC评分模型能准确且可重复地预测内分型归属。
研究设计与样本
- 研究对101例TED患者使用Luminex assay检测102种血浆细胞因子。
- 采用 integrative 机器学习识别关键细胞因子特征,并用无监督K-means聚类定义四种内分型。
- 开发CKC评分列线图并在独立外部队列中评估。
主要发现
- CKC1(炎症型,n=34)临床活动度评分最高, gaze-evoked pain 占23.5%。
- CKC2(增殖型,n=32)结构改变突出,突眼和复视占比最高达81.3%。
- CKC3(纤维型,n=20)表现慢性纤维化特征。
- CKC4(代谢型,n=15)伴代谢合并症,糖尿病占53.3%。
- CKC评分列线图预测内分型内部AUC为0.742,外部验证队列保持稳健判别力。
临床怎么用
- 可利用四细胞因子特征谱对TED患者进行分子内分型,辅助临床分层。
- CKC评分列线图可用于预测患者所属内分型,支持个体化评估。
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
PURPOSE: Thyroid eye disease (TED) exhibits profound phenotypic heterogeneity that conventional binary thyrotropin receptor antibody fails to capture. We aimed to deconstruct this heterogeneity by establishing a cytokine-derived molecular taxonomy. METHODS: We profiled 102 plasma cytokines in 101 TED patients using a Luminex assay. Integrative machine learning identified key cytokine signatures. Unsupervised K-means clustering defined four discrete endotypes. A diagnostic nomogram (named the cytokine-derived cluster [CKC] score) was developed and evaluated in an independent external cohort. RESULTS: Machine learning identified a robust four-cytokine signature (vascular cell adhesion molecule 1, C-C motif chemokine ligand 19, C-X3-C motif chemokine ligand 1, chemokine (C-X-C motif) ligand 13). This signature stratified TED patients into four distinct endotypes: CKC1 (inflammatory; n = 34) showed the highest Clinical Activity Score and gaze-evoked pain (23.5%); CKC2 (proliferative; n = 32) demonstrated prominent structural changes with the highest proptosis and diplopia (81.3%); CKC3 (fibrogenic; n = 20) exhibited chronic fibrotic features; and CKC4 (metabolic; n = 15) presented with metabolic comorbidities (diabetes 53.3%). The CKC score nomogram successfully predicted endotypes assignment, achieving an internal area under the receiver operating characteristic curve of 0.742 and maintaining robust discriminative power in the external validation cohort. CONCLUSIONS: Using machine learning, we identified a four-cytokine signature that robustly stratifies TED patients into four immunologically and clinically distinct endotypes. The CKC scoring model, derived from this signature, enables the accurate and reproducible prediction of endotype membership.
引用
- Jing G, Wu X, Huang Z, et al. Machine Learning-Based Cytokine Endotyping of Thyroid Eye Disease. Invest Ophthalmol Vis Sci. 2026. PMID: 42657997. doi:10.1167/iovs.67.10.67
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。