Towards a General Intelligence and Interface for Wearable Health Data
作者: Girish Narayanswamy, Maxwell A. Xu, A. Ali Heydari, Samy Abdel-Ghaffar, Marius Guerard, Kara Vaillancourt, Zhihan Zhang, Jake Garrison, Levi Albuquerque, Dimitris Spathis, Hong Yu, Hamid Palangi, Xuhai "Orson" Xu, David G.T. Barrett, Joseph Breda, Jed McGiffin, Yubin Kim, Yuwei Zhang, Naghmeh Rezaei, Samuel Solomon, Karan Ahuja, Tim Althoff, Jake Sunshine, Ming-Zher Poh, Benjamin Yetton, Ari Winbush, Nicholas B. Allen, James M. Rehg, Isaac Galatzer-Levy, Yun Liu, John Hernandez, Anupam Pathak, Conor Heneghan, Yuzhe Yang, Ahmed A. Metwally, Pushmeet Kohli, Mark Malhotra, Shwetak Patel, Xin Liu, Daniel McDuff
分类: cs.AI
发布日期: 2026-07-20
💡 一句话要点
提出可穿戴健康数据的基础模型以解决个性化健康洞察问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 可穿戴健康数据 基础模型 个性化健康洞察 少量样本学习 健康预测
📋 核心要点
- 现有方法在将可穿戴传感器数据转化为个性化健康洞察方面面临挑战,尤其是数据的多样性和标签稀缺性。
- 论文提出了一种基础模型,通过在大规模未标记传感器信号上进行预训练,提升健康数据的表示能力。
- 实验结果表明,该模型在35个健康预测任务上表现出系统性的性能提升,支持少量样本学习和生成能力。
📝 摘要(中文)
尽管普遍存在的可穿戴传感器能够捕捉大量行为和生理信息,但将这些信号有效转化为个性化健康洞察仍然具有挑战性。尤其是,由于个体的表型多样性和健康、生活方式等因素的变化,将低级传感器数据转化为能够表征高级状态的表示非常困难。此外,收集配有健康结果注释的可穿戴数据既费时又昂贵,回顾性注释几乎不可行,导致高质量标签的数据稀缺。为了解决这些问题,本文提出了一种可穿戴健康的基础模型,该模型在来自五百万参与者的大规模队列中预训练了超过一万亿分钟的未标记传感器信号。我们证明了模型容量和预训练数据量的联合扩展在35个健康预测任务上系统性地提高了性能。
🔬 方法详解
问题定义:本文旨在解决如何将可穿戴传感器的低级数据有效转化为个性化健康洞察的问题。现有方法面临的主要痛点是个体差异导致的标签稀缺和数据多样性。
核心思路:论文的核心思路是构建一个基础模型,通过在大规模未标记数据上进行预训练,来增强模型对健康状态的表示能力。这种设计旨在利用大规模数据的潜力,克服标签稀缺的问题。
技术框架:整体架构包括数据收集、预训练模型的构建、下游任务的预测头设计以及个人健康代理的集成。主要模块包括基础模型、LLM代理和下游预测器。
关键创新:最重要的技术创新在于通过大规模未标记数据的预训练,显著提升了模型的表示能力和少量样本学习能力。这与传统方法依赖大量标记数据的方式形成了鲜明对比。
关键设计:在模型设计中,采用了特定的损失函数和网络结构,以确保模型能够有效捕捉健康数据的多样性。此外,模型的容量与预训练数据量的联合扩展是实现性能提升的关键因素。
📊 实验亮点
实验结果显示,模型在35个健康预测任务上表现出显著的性能提升,尤其是在心血管、代谢、睡眠和心理健康等领域。通过与基线模型的对比,性能提升幅度达到了未知的百分比,验证了模型的有效性和实用性。
🎯 应用场景
该研究的潜在应用领域包括个性化健康监测、疾病预测和健康管理。通过将基础模型集成到个人健康代理中,可以为用户提供更相关和安全的健康建议,具有重要的实际价值和未来影响。
📄 摘要(原文)
While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of characterizing higher-level states is difficult due to high phenotypic diversity and variation in individual baseline health, physiology, and lifestyle factors. Moreover, collecting wearable data paired with health outcome annotations is laborious and expensive, and retrospective annotation remains practically unfeasible, contributing to a scarcity of data with high-quality labels. To overcome these limitations, we propose a foundation model for wearable health that is pretrained on more than one trillion minutes of unlabeled sensor signals drawn from a large cohort of five million participants. We demonstrate that the joint scaling of model capacity and pretraining data volume leads to systematic improvements in performance, as evaluated on a diverse set of 35 health prediction tasks, spanning cardiovascular, metabolic, sleep, and mental health, as well as lifestyle choices and demographic factors. We find that this population scale representation unlocks label-efficient few-shot learning and generative capabilities for robust daily metric estimation. To further leverage this learned representation, we deploy a classroom of LLM agents to autonomously search the space of downstream predictive heads built on the model embeddings, showing broad performance improvements that increase with LLM model capacity. Finally, we show how integrating these downstream predictors into a Personal Health Agent can support model responses that are more relevant, contextually aware, and safe, and we validate this via 1,860 ratings from a cohort of clinicians.