机器学习预测类风湿关节炎6至24个月缓解:JAK国际合作注册研究
研究基于11个国际注册库数据,开发并外部验证机器学习模型预测RA患者启动TNF抑制剂、JAK抑制剂等后6-24个月缓解。XGBoost全模型外部验证AUC 0.797,简化10变量模型和逻辑回归表现相近;模型鉴别力有限,最适合排除缓解。
要点
- 全模型外部验证AUC 0.797,敏感度0.804,特异度0.650,PPV 0.454,NPV 0.902。
- 简化10变量模型AUC 0.802,逻辑回归AUC 0.809,模型复杂度增量价值有限。
- 关键预测因子包括患者总体评估、28压痛关节数、既往生物/靶向合成DMARD暴露和HAQ-DI评分。
核心结论
- 基于常规收集的基线数据预测6-24个月缓解鉴别力有限,最适合用于排除缓解。
- 简化10变量模型与逻辑回归性能相似,提示无更丰富预测因子时增加模型复杂度增量价值有限。
研究设计与样本
- 国际多注册库协作研究,使用JAK-pot协作中11个国际注册库数据。
- 21,675个治疗疗程用于模型训练,5,418个用于内部验证,1,807个来自瑞士的疗程用于外部验证。
- 训练XGBoost模型,输入63个基线人口学和临床变量,并评估简化10变量模型和逻辑回归基准。
主要发现
- 外部验证中全模型AUC为0.797(95%CI 0.774-0.821),敏感度0.804,特异度0.650,PPV 0.454,NPV 0.902。
- 简化模型AUC为0.802,使用相同10个预测因子的逻辑回归AUC为0.809。
- 关键预测因子包括患者总体评估、28压痛关节数、既往生物/靶向合成DMARD暴露和HAQ-DI评分。
关键数值与推荐
- 缓解定义为治疗起始或切换后6至24个月内临床疾病活动指数(CDAI)评分≤2.8。
- 模型性能评价指标包括AUC、敏感度、特异度、阳性预测值(PPV)和阴性预测值(NPV)。
- 预测因子贡献使用Shapley Additive Explanations值量化。
临床怎么用
- 该模型高NPV(0.902)提示可用于识别不太可能达到缓解的患者,辅助排除缓解。
- 因鉴别力有限,不宜单独用于确认缓解,需结合临床评估。
- 简化模型或逻辑回归可替代复杂模型,便于临床落地。
局限性
- 模型鉴别力有限,AUC低于0.8,确认缓解能力不足。
- 外部验证仅来自瑞士单国注册库,外推性需进一步验证。
- 未纳入更丰富预测因子,模型复杂度增量价值有限。
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
OBJECTIVE: To develop, externally validate, and simplify a machine learning model to predict remission between 6 and 24 months in patients with rheumatoid arthritis (RA) initiating tumor necrosis factor inhibitors, JAK inhibitors, interleukin-6 inhibitors, abatacept, or rituximab using data from 11 international registries in the JAK-pot collaboration. METHODS: We analyzed 21,675 treatment courses for model training, 5,418 courses for internal validation, and 1,807 courses from Switzerland for external validation. Remission was defined as a Clinical Disease Activity Index score ≤2.8 within 6 to 24 months after treatment initiation or switching. An XGBoost model was trained on 63 baseline demographic and clinical variables. Model performance was evaluated using the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Predictor contributions were quantified using Shapley Additive Explanations values. A simplified model using the top 10 predictors and a logistic regression benchmark were also evaluated. RESULTS: In external validation, the full model achieved an AUC of 0.797 (95% confidence interval 0.774-0.821), sensitivity of 0.804, specificity of 0.650, PPV of 0.454, and NPV of 0.902. The simplified model performed comparably (AUC 0.802). Logistic regression using the same 10 predictors achieved an AUC of 0.809. Key predictors included patient global assessment, 28-tender joint count, previous biologic/targeted synthetic disease-modifying antirheumatic drug exposure, and Health Assessment Questionnaire Disability Index score. CONCLUSION: Using routinely collected baseline data across 11 registries, prediction of remission showed limited discrimination and was best suited to ruling out remission. Performance was similar for a 10-variable model and logistic regression, indicating limited incremental value of model complexity without richer predictors.
引用
- Salis Z, Mongin D, Choquette D, et al. Machine Learning to Predict Remission Between 6 and 24 Months in Rheumatoid Arthritis: Insights From JAK, an International Registry Collaboration. Arthritis Rheumatol. 2026. PMID: 41940462. doi:10.1002/art.70165
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。