用人脸照片预测生物年龄与癌症死亡风险，效果优于传统方法。
Foundation Artificial Intelligence Models for Health Recognition Using Face Photographs (FAHR-Face)
- 基于超4000万张人脸训练基础模型，分两阶段微调用于年龄与生存风险预测。
- 年龄估计误差仅5.1年，高风险组死亡率是低风险组的3.22倍（P<0.001）。
- 模型对妆容、姿势等变化鲁棒，适用于不同人群，适合临床辅助诊断。
面部外观提供了非侵入性健康窗口。我们构建了FAHR-Face，一个在超过4000万张人脸图像上训练的基础模型，并针对两项任务进行微调：生物年龄估计（FAHR-FaceAge）和生存风险预测（FAHR-FaceSurvival）。FAHR-FaceAge在749,935张公开图像上进行两阶段、年龄平衡的微调；FAHR-FaceSurvival则在34,389张癌症患者照片上微调。模型在化妆、手术、姿态、光照等条件下的鲁棒性及特征重要性（显著性映射）均经过严格测试。两个模型在两个独立癌症患者数据集上进行临床验证，生存分析采用多变量Cox模型并调整临床预后因素。结果显示，年龄估计方面，FAHR-FaceAge在公开数据集上平均绝对误差最低为5.1年，优于基准模型，并覆盖全人生命周期。在癌症患者中，其年龄估计能力显著提升生存预判效果。FAHR-FaceSurvival能稳健预测死亡风险，最高风险四分位组死亡率超过最低组的三倍（校正风险比3.22；P<0.001）。该结果在独立队列中得到验证，且两种模型在年龄、性别、种族及癌症亚型中均表现出良好泛化性。两个算法提供互补的预后信息，显著性映射显示各自依赖不同面部区域。结合两者可进一步提升预后准确度。结论表明，单一基础模型可生成低成本、可扩展的人脸生物标志物，同时捕捉生物衰老与疾病相关死亡风险。该模型使小规模临床数据也能实现高效训练。
原文摘要 · Abstract (English)
Background: Facial appearance offers a noninvasive window into health. We built FAHR-Face, a foundation model trained on >40 million facial images and fine-tuned it for two distinct tasks: biological age estimation (FAHR-FaceAge) and survival risk prediction (FAHR-FaceSurvival). Methods: FAHR-FaceAge underwent a two-stage, age-balanced fine-tuning on 749,935 public images; FAHR-FaceSurvival was fine-tuned on 34,389 photos of cancer patients. Model robustness (cosmetic surgery, makeup, pose, lighting) and independence (saliency mapping) was tested extensively. Both models were clinically tested in two independent cancer patient datasets with survival analyzed by multivariable Cox models and adjusted for clinical prognostic factors. Findings: For age estimation, FAHR-FaceAge had the lowest mean absolute error of 5.1 years on public datasets, outperforming benchmark models and maintaining accuracy across the full human lifespan. In cancer patients, FAHR-FaceAge outperformed a prior facial age estimation model in survival prognostication. FAHR-FaceSurvival demonstrated robust prediction of mortality, and the highest-risk quartile had more than triple the mortality of the lowest (adjusted hazard ratio 3.22; P<0.001). These findings were validated in the independent cohort and both models showed generalizability across age, sex, race and cancer subgroups. The two algorithms provided distinct, complementary prognostic information; saliency mapping revealed each model relied on distinct facial regions. The combination of FAHR-FaceAge and FAHR-FaceSurvival improved prognostic accuracy. Interpretation: A single foundation model can generate inexpensive, scalable facial biomarkers that capture both biological ageing and disease-related mortality risk. The foundation model enabled effective training using relatively small clinical datasets.
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。