文献速递其他结缔组织病

系统性硬化症相关间质性肺病中利妥昔单抗疗效的预测因素:DESIRES 试验的机器学习分析

Predictors of rituximab efficacy in systemic sclerosis-associated interstitial lung disease: machine-learning analysis of the DESIRES trial.
PubMed 文献 · Rheumatology (Oxford) · 2025-01-01

该研究对双盲随机安慰剂对照 DESIRES 试验中 48 例系统性硬化症相关间质性肺病(SSc-ILD)患者的前瞻性数据进行事后分析,用机器学习因果树算法从 28 个基线因素中筛选预测利妥昔单抗 24 周时预测用力肺活量百分比(ppFVC)疗效的因素。结果显示血清 CRP 和 KL-6 被选为决策树分支,将患者分为三个亚群,其中 CRP≥0.055 mg/dl 亚群中利妥昔单抗组 ΔppFVC 显著高于安慰剂组。结论认为血清 CRP 轻微升高与 ppFVC 改善相关,可能作为利妥昔单抗疗效的预测因素。

要点

  • 血清 CRP 和 KL-6 被选为决策树分支,将 SSc-ILD 患者分为三个亚群。
  • CRP≥0.055 mg/dl 亚群中利妥昔单抗组 ΔppFVC 较安慰剂组高 8.01%(95%CI 4.40%–11.62%)。
  • CRP<0.055 mg/dl 且 KL-6<364 U/ml 亚群中利妥昔单抗组 ΔppFVC 较安慰剂组低 6.85%(95%CI -10.80%–-2.91%)。

核心结论

  • 血清 CRP 轻微升高与 ppFVC 改善相关,可能作为 SSc-ILD 中利妥昔单抗疗效的预测因素。

研究设计与样本

  • 对双盲、随机、安慰剂对照 DESIRES 试验中 48 例 SSc-ILD 患者的前瞻性数据进行事后分析。
  • 从 28 个基线因素中筛选预测利妥昔单抗 24 周时 ppFVC 疗效的候选因素,采用机器学习因果树算法探索预测因素组合以识别对利妥昔单抗应答良好的亚群。

主要发现

  • 血清 CRP 和 KL-6 被选为决策树分支,将患者分为三个亚群。
  • CRP≥0.055 mg/dl 亚群中,利妥昔单抗组 ΔppFVC 较安慰剂组高 8.01%(95%CI 4.40%–11.62%)。
  • CRP<0.055 mg/dl 且 KL-6≥364 U/ml 亚群中,两组 ΔppFVC 差异为 2.47%(95%CI -1.99%–6.92%),无显著差异。
  • CRP<0.055 mg/dl 且 KL-6<364 U/ml 亚群中,利妥昔单抗组 ΔppFVC 较安慰剂组低 6.85%(95%CI -10.80%–-2.91%)。

关键数值与推荐

  • CRP≥0.055 mg/dl 亚群:利妥昔单抗组与安慰剂组 ΔppFVC 差异 8.01%(95%CI 4.40%–11.62%)。
  • CRP<0.055 mg/dl 且 KL-6≥364 U/ml 亚群:两组 ΔppFVC 差异 2.47%(95%CI -1.99%–6.92%)。
  • CRP<0.055 mg/dl 且 KL-6<364 U/ml 亚群:利妥昔单抗组与安慰剂组 ΔppFVC 差异 -6.85%(95%CI -10.80%–-2.91%)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

OBJECTIVES: Rituximab is emerging as a promising therapeutic option for systemic sclerosis-associated interstitial lung disease (SSc-ILD). However, little is known about factors that predict the efficacy of rituximab in SSc-ILD. METHODS: A post-hoc analysis was performed on prospective data from 48 patients with SSc-ILD in the double-blind, randomized, placebo-controlled DESIRES trial. A total of 28 baseline factors were selected as candidates to predict the efficacy of rituximab on the percentage of predicted forced vital capacity (ppFVC) at 24 weeks. A machine learning causal tree algorithm was used to explore the combination of predictors to identify subpopulations with a good response to rituximab. RESULTS: Serum levels of C-reactive protein (CRP) and Krebs von den Lungen-6 (KL-6) were selected as branches of the decision tree to stratify patients into three subpopulations. In the subpopulation with serum CRP levels ≥0.055 mg/dl, ΔppFVC was significantly higher in the rituximab group than in the placebo group [difference 8.01% (95% CI: 4.40%, 11.62%)]. In the subpopulation with serum CRP levels <0.055 mg/dl and serum KL-6 levels ≥364 U/ml, ΔppFVC was comparable between the two groups [difference 2.47% (95% CI: -1.99%, 6.92%)]. In the subpopulation with serum CRP levels <0.055 mg/dl and serum KL-6 levels <364 U/ml, ΔppFVC was significantly lower in rituximab than in placebo [difference -6.85% (95% CI: -10.80%, -2.91%)]. CONCLUSION: Even slight elevations in serum CRP levels are associated with the improvement in ppFVC and may serve as predictors of rituximab efficacy in SSc-ILD.

来源:Rheumatology (Oxford),查看原文。版权归原作者所有。

引用

  1. Kuzumi A, Oba K, Ebata S, et al. Predictors of rituximab efficacy in systemic sclerosis-associated interstitial lung disease: machine-learning analysis of the DESIRES trial. Rheumatology (Oxford). 2025. PMID: 39718799. doi:10.1093/rheumatology/keae716

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。