文献速递心血管胸部CT

免疫介导炎症性疾病患者中人工智能偶然检出冠状动脉钙化的患病率与预后价值

Prevalence and Prognostic Value of Incidentally Detected Coronary Artery Calcium Using Artificial Intelligence Among Individuals With Immune-Mediated Inflammatory Diseases.
PubMed 文献 · JACC Cardiovasc Imaging · 2025-10-28

该回顾性队列纳入2000至2023年在美国波士顿2个医疗中心因常规诊疗接受胸部CT的2546例40至70岁免疫介导炎症性疾病患者,用经验证的人工智能算法评估冠状动脉钙化。中位随访8.1年,53%患者CAC-AI>0而仅6.0%使用他汀;CAC-AI 1-99与全因死亡(校正HR 1.41)和MACE(校正HR 2.05)风险升高相关,CAC-AI≥100风险更高(全因死亡校正HR 2.45,MACE校正HR 3.24)。

要点

  • 免疫介导炎症性疾病患者常规胸部CT中53%存在CAC-AI>0,仅6.0%使用他汀。
  • CAC-AI 1-99与全因死亡校正HR 1.41、MACE校正HR 2.05相关。
  • CAC-AI≥100与全因死亡校正HR 2.45、MACE校正HR 3.24相关。

核心结论

  • 在免疫介导炎症性疾病患者中,人工智能偶然检出的冠状动脉钙化高度流行,且与全因死亡和MACE显著相关;作者认为CAC-AI可能提供重要预后信息,有助于在这一高危且治疗不足的人群中改善风险分层和治疗。

研究设计与样本

  • 回顾性队列研究,纳入2000至2023年在美国马萨诸塞州波士顿2个医疗中心因常规诊疗接受胸部CT的40至70岁系统性红斑狼疮、类风湿关节炎或银屑病且无既往动脉粥样硬化性心血管疾病患者2546例,中位年龄59岁(Q1-Q3:53-65岁),女性1694例(66.5%);采用经验证的人工智能方法判定CAC存在与严重程度,以Cox比例风险模型分析CAC-AI分类与全因死亡和MACE的关联,所有模型均校正年龄、性别和传统心血管危险因素。

关键影像表现/征象

  • 常规胸部CT经人工智能判定CAC-AI>0者占53%,仅6.0%使用他汀。

诊断标准与关键数值

  • CAC-AI分类为0、1-99和≥100;以CAC-AI=0为参照,CAC-AI 1-99与全因死亡校正HR 1.41(P=0.010)、MACE校正HR 2.05(P<0.001)相关。
  • 以CAC-AI=0为参照,CAC-AI≥100与全因死亡校正HR 2.45(P<0.001)、MACE校正HR 3.24(P<0.001)相关。
  • MACE定义为非致死性心肌梗死、冠状动脉血运重建、非致死性卒中或心血管死亡。

临床应用与阅片要点

  • 对免疫介导炎症性疾病患者因常规诊疗行胸部CT时,可用经验证的人工智能算法评估冠状动脉钙化,以获取预后信息。
  • 作者认为CAC-AI可能提供重要预后信息,有助于在这一高危且治疗不足的人群中改善风险分层和治疗。

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)。

英文原文(摘要)· 点击展开

BACKGROUND: Coronary artery calcium (CAC) scoring is strongly associated with cardiovascular (CV) events among the general population; however, its prognostic value among individuals with immune-mediated inflammatory diseases (IMIDs) is not well characterized.

OBJECTIVES: This study aims to assess the prevalence of CAC derived from routine chest computed tomography (CT) using a validated artificial intelligence (AI) algorithm and its association with adverse CV events among those with IMIDs.

METHODS: The authors studied a retrospective cohort of all patients 40 to 70 years of age with a diagnosis of systemic lupus erythematosus, rheumatoid arthritis, or psoriatic disease, and no prior atherosclerotic cardiovascular disease who underwent chest CT at 2 medical centers in Boston, Massachusetts, USA, from 2000 to 2023 as part of routine care. The presence and severity of CAC was determined using a validated AI methodology. Cox proportional hazards modeling was used to assess the association of CAC-AI categories (CAC-AI = 0, CAC-AI = 1-99, and CAC-AI ≥100) with all-cause mortality and major adverse cardiovascular events (MACE) (nonfatal myocardial infarction, coronary revascularization, nonfatal stroke, or CV mortality). All models were adjusted for age, sex, and traditional CV risk factors.

RESULTS: In total, 2,546 individuals with IMIDs (median age: 59 years [Q1-Q3: 53-65 years]; 1,694 [66.5%] women) were included with a median follow-up of 8.1 years. Among this cohort, 53% had CAC-AI >0 while only 6.0% were on a statin. A low burden of CAC (CAC-AI = 1-99) was associated with an increased risk of all-cause mortality (adjusted HR: 1.41; P = 0.010) and MACE (adjusted HR: 2.05; P < 0.001) with even greater risk observed among individuals with CAC-AI ≥100 (adjusted HR: 2.45; P < 0.001) and MACE (adjusted HR: 3.24; P < 0.001).

CONCLUSIONS: Among those with IMIDs, incidental CAC-AI was highly prevalent and significantly associated with both all-cause mortality and MACE. These findings suggest that CAC-AI may provide important prognostic information, allowing for improved risk stratification and treatment within an already high-risk and undertreated population.

来源:JACC Cardiovasc Imaging,查看原文。版权归原作者所有。

引用

  1. Weber BN, Biery DW, Petranovic M, et al. Prevalence and Prognostic Value of Incidentally Detected Coronary Artery Calcium Using Artificial Intelligence Among Individuals With Immune-Mediated Inflammatory Diseases. JACC Cardiovasc Imaging. 2025. PMID: 41148065. doi:10.1016/j.jcmg.2025.08.020

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。