基于ArcFace-Inception的心电生物识别在大规模跨域数据上表现稳定但受时间与数据量影响。
ECG Biometrics with ArcFace-Inception: External Validation on MIMIC and HEEDB
- 用ArcFace训练1D Inception模型，实现心电图身份识别。
- 在多数据集上验证，最长5年跨度下识别率仍保持60%以上。
- 适合医疗系统中长期患者身份认证，需关注数据异质性与重采样处理。
ECG生物识别研究多限于小规模样本和短时间隔，难以反映真实场景下的性能。本研究在包含53,079名患者的164,440份12导联心电图上训练1D Inception-v1模型，并使用ArcFace损失函数，测试其在MIMIC-IV-ECG和HEEDB两个外部数据集上的表现。采用统一闭集留一法评估，结合Rank@K、TAR@FAR指标及尺度、时序压力、重排序与置信度分析。结果表明，在通用可比条件下，系统在ASUGI-DB上达到Rank@1=0.9506，MIMIC-GC为0.8291，HEEDB-GC为0.6884。在固定画廊规模的时序压力测试中，从1年到5年，MIMIC上Rank@1从0.7853降至0.6433，HEEDB从0.6864降至0.5560。在HEEDB上，画廊规模增大导致性能单调下降，但每位患者更多检查可部分恢复性能。在HEEDB-RR中，后处理重排序使性能提升至Rank@1=0.8005（基线0.7765）。结果表明，心电图身份信息在大规模外部验证下仍可测量，但受领域异质性、纵向漂移、画廊大小及二次评分处理显著影响。
原文摘要 · Abstract (English)
ECG biometrics has been studied mainly on small cohorts and short inter-session intervals, leaving open how identification behaves under large galleries, external domain shift, and multi-year temporal gaps. We evaluated a 1D Inception-v1 model trained with ArcFace on an internal clinical corpus of 164,440 12-lead ECGs from 53,079 patients and tested it on larger cohorts derived from MIMIC-IV-ECG and HEEDB. The study used a unified closed-set leave-one-out protocol with Rank@K and TAR@FAR metrics, together with scale, temporal-stress, reranking, and confidence analyses. Under general comparability, the system achieved Rank@1 of 0.9506 on ASUGI-DB, 0.8291 on MIMIC-GC, and 0.6884 on HEEDB-GC. In the temporal stress test at constant gallery size, Rank@1 declined from 0.7853 to 0.6433 on MIMIC and from 0.6864 to 0.5560 on HEEDB from 1 to 5 years. Scale analysis on HEEDB showed monotonic degradation as gallery size increased and recovery as more examinations per patient became available. On HEEDB-RR, post-hoc reranking further improved retrieval, with AS-norm reaching Rank@1 = 0.8005 from a 0.7765 baseline. ECG identity information therefore remains measurable under externally validated large-scale closed-set conditions, but its operational quality is strongly affected by domain heterogeneity, longitudinal drift, gallery size, and second-stage score processing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。