文献速递心力衰竭与心肌病瓣膜病与结构性心脏病

基于单帧超声心动图视频 clip 的心脏淀粉样变 AI 筛查工具

Cardiac amyloidosis detection from a single echocardiographic video clip: a novel artificial intelligence-based screening tool.
PubMed 文献 · Eur Heart J · 2025-01-01

本研究利用多中心多种族数据集(n=2612,52% 为 CA)训练卷积神经网络,通过心尖四腔心视频 clip 区分心脏淀粉样变(CA)与表型对照。外部验证覆盖 18 个中心(597 例 CA,2122 例对照),模型 AUROC 达 0.93,敏感度 85%、特异度 93%,且优于转甲状腺素蛋白 CA 评分和心室壁增厚评分。

要点

  • AI 模型仅用心尖四腔心视频 clip 即可高精度区分 CA 与左室壁增厚 mimic。
  • 外部验证 AUROC 0.93,各 CA 亚型敏感度 84%–86%,特异度 93%。
  • 模型性能优于转甲状腺素蛋白 CA 评分(AUROC 0.73)和室壁增厚评分(AUROC 0.80)。

核心结论

  • 仅使用心尖四腔心视图的 AI 筛查模型可有效区分 CA 与其他左室壁增厚原因。

研究设计与样本

  • 多中心、多种族数据集(n=2612,52% CA)训练卷积神经网络,外部验证覆盖 18 个中心(597 例 CA,2122 例对照)。

主要发现

  • 去除不确定 AI 预测(13%)后,全外部验证集 AUROC 0.93,敏感度 85%,特异度 93%。
  • CA 亚型敏感度:轻链型 84%,野生型转甲状腺素蛋白 85%,遗传型转甲状腺素蛋白 86%。
  • 临床转诊行锝焦磷酸盐闪烁显像亚组 AUROC 0.86,敏感度 77%,特异度 86%。
  • 年龄、性别和室壁厚度匹配亚组 AUROC 0.92,敏感度 84%,特异度 91%。

关键数值与推荐

  • 全外部验证集 AUROC 0.93,敏感度 85%,特异度 93%。
  • 锝焦磷酸盐闪烁显像转诊亚组 AUROC 0.86,敏感度 77%,特异度 86%。
  • 匹配亚组 AUROC 0.92,敏感度 84%,特异度 91%。
  • AI 模型 AUROC 0.93 优于转甲状腺素蛋白 CA 评分(AUROC 0.73)和室壁增厚评分(AUROC 0.80)。

临床怎么用

  • 该 AI 工具可作为心尖四腔心视图下的辅助筛查手段,帮助鉴别 CA 与左室壁增厚 mimic。
  • 在临床转诊行锝焦磷酸盐闪烁显像的患者中仍保持较好判别能力。

局限性

  • 外部验证中剔除了 13% 的不确定 AI 预测,可能影响真实世界全样本性能。
  • 研究为回顾性多中心验证,尚未报告前瞻性临床影响或预后数据。

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

BACKGROUND AND AIMS: Accurate differentiation of cardiac amyloidosis (CA) from phenotypic mimics remains challenging using current clinical and echocardiographic techniques. The accuracy of a novel artificial intelligence (AI) screening algorithm for echocardiography-based CA detection was assessed. METHODS: Utilizing a multisite, multiethnic dataset (n = 2612, 52% CA), a convolutional neural network was trained to differentiate CA from phenotypic controls using transthoracic apical four-chamber video clips. External validation was conducted globally across 18 sites including 597 CA cases and 2122 controls. Classification accuracy was assessed on the entire external validation dataset, and subgroup analyses were performed both on technetium pyrophosphate scintigraphy referrals, and individuals matched for age, sex, and wall thickness. Model accuracy was also compared with the transthyretin CA score and the increased wall thickness score within a subset of older heart failure with preserved ejection fraction patients with increased wall thickness. RESULTS: Cardiac amyloidosis patients and controls displayed similar age, sex, race, and comorbidities. After the removal of uncertain AI predictions (13%), model discrimination and classification were excellent for the entire external validation dataset [area under the receiver operating characteristic curve (AUROC) 0.93, sensitivity 85%, specificity 93%], irrespective of CA subtype (sensitivity: light-chain = 84%, wild-type transthyretin = 85%, and hereditary transthyretin = 86%). Performance was maintained in subgroup analysis in patients clinically referred for technetium pyrophosphate scintigraphy imaging (AUROC 0.86, sensitivity 77%, specificity 86%) and matched patients (AUROC 0.92, sensitivity 84%, specificity 91%). The AI model (AUROC 0.93) also outperformed transthyretin CA score (AUROC 0.73) and increased wall thickness (AUROC 0.80) scores. CONCLUSIONS: This AI screening model-using only an apical four-chamber view-effectively differentiated CA from other causes of increased left ventricular wall thickness.

来源:Eur Heart J,查看原文。版权归原作者所有。

引用

  1. Slivnick JA, Hawkes W, Oliveira J, et al. Cardiac amyloidosis detection from a single echocardiographic video clip: a novel artificial intelligence-based screening tool. Eur Heart J. 2025. PMID: 40631729. doi:10.1093/eurheartj/ehaf387

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。