开源心率波模型在手术患者中预测生物年龄，效果优于专有模型。
Benchmarking Open-Source PPG Foundation Models for Biological Age Prediction
- 用冻结特征+岭回归评估三个开源模型，脉搏波信号表现最佳。
- 最优结果MAE达8.22年，与苹果专有模型差距主要因数据量和人群差异。
- 预测偏差与舒张压相关，提示生理机制可解释性更强。
基于英国生物银行212,231名受试者训练的专用血管年龄预测模型（AI-PPG Age）在另一临床人群中失效：预测值始终集中在38-67岁区间，与真实年龄无关。相比之下，无年龄目标训练的通用基础模型在相同数据上误差更低。本文在PulseDB的906名外科患者上评估三个开源脉搏波模型（Pulse-PPG、PaPaGei-S、AI-PPG Age），采用冻结嵌入与岭回归，5折交叉验证。Pulse-PPG取得9.28年平均绝对误差（MAE），优于线性探针模式下的AI-PPG Age（9.72年）及心率/心率变异性结合人口学特征的结果（9.59年）。加入人口学特征后最佳结果为MAE = 8.22年（R² = 0.517，r = 0.725）。校正年龄后，预测年龄差与舒张压显著相关（r = -0.188，p = 1.2e-8），与苹果公司报告一致。与苹果模型（MAE 2.43）的剩余差距主要源于数据规模（906 vs 213,593）和人群差异，而非模型架构，学习曲线显示无性能饱和迹象。代码已公开。
原文摘要 · Abstract (English)
A task-specific model trained on 212,231 UK Biobank subjects to predict vascular age from PPG (AI-PPG Age) fails on a different clinical population: predictions collapse to a narrow 38-67 year range regardless of true age. Meanwhile, a general-purpose foundation model with no age-related training objective achieves lower error on the same data. We investigate why this happens and what it means for PPG-based biological age prediction. We evaluate three open-source PPG models (Pulse-PPG, PaPaGei-S, AI-PPG Age) on 906 surgical patients from PulseDB, using frozen embeddings with Ridge regression and 5-fold cross-validation. Pulse-PPG reaches MAE = 9.28 years, beating both AI-PPG Age in linear probe mode (9.72) and HR/HRV combined with demographics (9.59). Adding demographic features brings the best result down to MAE = 8.22 years (R2 = 0.517, r = 0.725). The predicted age gap correlates with diastolic blood pressure after adjusting for chronological age (r = -0.188, p = 1.2e-8), consistent with what Apple reported for their proprietary PpgAge model. The remaining gap with Apple (MAE 2.43) appears driven by dataset size (906 vs 213,593 subjects) and population differences rather than model architecture, as our learning curve shows no plateau. Code is publicly available.
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。