从跨医疗系统电子健康记录推断类风湿关节炎疾病活动度
研究利用Mass General Brigham和退伍军人事务部电子健康记录与类风湿关节炎登记数据,开发并验证机器学习模型推断DAS28疾病活动度。结合结构化数据与自然语言处理的模型在机构内AUC达0.843和0.833,跨机构验证AUC为0.679和0.718,推断的活动度与主要不良心血管事件风险增加相关。
要点
- 结合结构化数据与自然语言处理的模型在机构内推断RA疾病活动度性能较高。
- 跨机构验证显示算法可迁移性有限。
- 推断的疾病活动度与主要不良心血管事件风险增加相关。
核心结论
- 类风湿关节炎疾病活动度可从机构内电子健康记录数据大规模推断,但跨机构性能有限。
- 推断的疾病活动度复现了与主要不良心血管事件的已知关联,支持其用于生成真实世界证据的未来研究。
研究设计与样本
- 使用Mass General Brigham和退伍军人事务部电子健康记录数据,链接前瞻性收集DAS28的类风湿关节炎登记。
- 从电子健康记录提取结构化数据(如诊断代码)和叙述数据(使用自然语言处理),基于登记收集的DAS28训练机器学习模型。
- 评估同机构内训练和跨机构训练模型的性能,并用分层Cox模型评估推断疾病活动度与主要不良心血管事件的关联以评估表面效度。
主要发现
- 研究纳入1,105例Mass General Brigham和2,631例退伍军人事务部类风湿关节炎患者。
- 仅用结构化数据的模型AUC为0.68至0.70;结合结构化与自然语言处理的模型性能更高(Mass General Brigham,AUC=0.843;退伍军人事务部,AUC=0.833)。
- 跨机构验证显示算法跨站点可迁移性有限(Mass General Brigham→退伍军人事务部,AUC=0.679;退伍军人事务部→Mass General Brigham,AUC=0.718)。
- 同机构内,推断的疾病活动度与 incident 主要不良心血管事件风险增加显著相关(Mass General Brigham,风险比[HR]=1.12;退伍军人事务部,HR=1.14)。
临床怎么用
- 可在机构内利用电子健康记录数据大规模推断类风湿关节炎疾病活动度,用于真实世界研究。
- 跨机构应用时需注意算法可迁移性有限,可能需要本地验证或重新训练。
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: Disease activity plays a central role in rheumatoid arthritis (RA) clinical studies. The inconsistent availability of data on disease activity in real-world electronic health records (EHRs) data has limited the ability to generate real-world evidence (RWE). This study aimed to develop and validate scalable machine learning (ML) models to infer RA disease activity from EHR data. METHODS: We used EHR data from Mass General Brigham (MGB) and the Department of Veterans Affairs (VA) linked with RA registries that prospectively collected the Disease Activity Score with 28-joint counts (DAS28). Features for the algorithm were extracted from the EHRs including structured data (eg, diagnosis codes and narrative data using natural language processing [NLP]). ML models were trained on the registry-collected DAS28. The performance of models trained within the same institution and across institutions was evaluated. To assess face validity, we estimated the association between inferred disease activity and major adverse cardiovascular events (MACEs) with stratified Cox models. RESULTS: We studied 1,105 MGB and 2,631 VA patients with RA. Models with structured data achieved an area under the receiver operating curve (AUC) of 0.68 to 0.70; models incorporating structured and NLP achieved higher performance (MGB, AUC = 0.843; VA, AUC = 0.833). Cross-institution validation demonstrated limited transportability of algorithms across sites (MGB→VA, AUC = 0.679; VA→MGB, AUC = 0.718). Within the same institution, inferred disease activity was significantly associated with increased risk for incident MACEs (MGB, hazard ratio [HR] = 1.12; VA, HR = 1.14). CONCLUSION: RA disease activity can be inferred at scale from within-institution EHR data, though cross-institution performance is limited. The inferred disease activity replicated known associations with MACEs, and the results support its use in future studies to generate RWE.
引用
- Cheng D, Wang X, McDermott GC, et al. Inferring Rheumatoid Arthritis Disease Activity Status From the Electronic Health Records Across Health Systems. Arthritis Rheumatol. 2026. PMID: 41972843. doi:10.1002/art.70181
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。