文献速递甲状腺与颈部外科围术期管理与 ERAS

可穿戴单导联心电图深度学习用于甲状腺切除术后低钙血症早期检测

Deep learning using wearable single-lead electrocardiograms for early detection of post-thyroidectomy hypocalcemia.
PubMed 文献 · Surgery · 2026-09-01

这项前瞻性队列研究(N=51)评估了基于可穿戴单导联心电图的深度学习模型检测甲状腺切除术后生化性早期预警低钙血症(白蛋白校正钙<8.5 mg/dL)的能力。DenseNet模型在内部和外部队列中分别达到AUC 0.878和0.870,优于术后第1天12导联校正QT间期的AUC 0.526。结论认为该模型具有较强判别性能,但需多中心验证后方可临床部署。

要点

  • 可穿戴单导联心电图深度学习模型对校正钙<8.5 mg/dL的AUC内部0.878、外部0.870。
  • 术后第1天12导联校正QT间期判别能力有限,AUC仅0.526。
  • 生化性早期预警低钙血症患病率术后第1天为60.8%,第2天58.8%。

核心结论

  • 基于可穿戴单导联心电图的深度学习模型对甲状腺切除术后生化性低钙血症表现出较强的判别性能,优于校正QT间期评估。

研究设计与样本

  • 前瞻性队列研究,共纳入51例患者,在基线及术后多个时间点同步采集实验室检查和30秒可穿戴单导联心电图。
  • 数据按患者层面拆分(无重叠)为内部和外部队列用于训练、验证和测试,评估了DenseNet、EfficientNet、ResNet、ResNeXt和RegNet架构。
  • 主要终点为校正钙<8.5 mg/dL的受试者工作特征曲线下面积,以同期12导联心电图校正QT间期作为非深度学习基准。

主要发现

  • 共分析来自38例患者的490张心电图图像(内部31例,外部7例)。
  • DenseNet对校正钙<8.5 mg/dL的AUC内部为0.878,外部为0.870。
  • 术后第1天12导联校正QT间期的AUC为0.526,判别能力有限。
  • 全队列(N=51)中生化性早期预警低钙血症患病率:术后第1天60.8%,第2天58.8%,2-3周17.6%,2-3个月29.4%。
  • 伴低甲状旁腺素的生化显著性低钙血症患病率分别为27.5%、27.5%、2.0%和0%。

临床怎么用

  • 该模型有望作为无创工具辅助甲状腺切除术后低钙血症的早期识别,但当前证据尚不足以支持临床部署。

局限性

  • 样本量较小(N=51,分析38例),需更大规模多中心验证后方可临床推广。

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: Timely recognition of post-thyroidectomy hypocalcemia remains challenging. We evaluated whether deep learning models using wearable single-lead electrocardiograms detect biochemical early warning hypocalcemia, defined as albumin-corrected calcium <8.5 mg/dL, compared with a heart rate-corrected QT interval benchmark. METHODS: In a prospective cohort (N = 51), at baseline and postoperative day 1, postoperative day 2, 2-3 weeks, and 2-3 months, we obtained synchronized laboratory measurements and four 30-second wearable single-lead electrocardiogram recordings within 60 minutes and recorded symptom severity. Data were split at the patient level (no overlap) into internal and external cohorts for training, validation, and testing. We evaluated DenseNet, EfficientNet, ResNet, ResNeXt, and RegNet architectures. The primary end point was the area under the receiver operating characteristic curve for corrected calcium <8.5 mg/dL. Corrected QT interval from contemporaneous 12-lead electrocardiograms served as the non-deep learning benchmark. RESULTS: We analyzed 490 electrocardiogram images from 38 patients (internal: 31; external: 7). DenseNet achieved area under the receiver operating characteristic curves of 0.878 (internal) and 0.870 (external) for corrected calcium <8.5 mg/dL, whereas postoperative day 1 12-lead corrected QT interval showed limited discrimination (area under the receiver operating characteristic curve, 0.526). In the full cohort (N = 51), the prevalence of biochemical early warning hypocalcemia was 60.8% (postoperative day 1), 58.8% (postoperative day 2), 17.6% (2-3 weeks), and 29.4% (2-3 months); the prevalence of biochemically significant hypocalcemia with low parathyroid hormone was 27.5%, 27.5%, 2.0%, and 0%, respectively. CONCLUSION: A wearable single-lead electrocardiogram-based deep learning model demonstrated strong discriminative performance for biochemical hypocalcemia after thyroidectomy. Compared with corrected QT interval-based assessment, the model achieved superior performance. Larger multi-institutional validation is warranted before clinical deployment.

来源:Surgery,查看原文。版权归原作者所有。

引用

  1. Lee S, Jeong S, Joo H, et al. Deep learning using wearable single-lead electrocardiograms for early detection of post-thyroidectomy hypocalcemia. Surgery. 2026. PMID: 42816214. doi:10.1016/j.surg.2026.110599

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。