作为自身科学家的运动员:面向消费级可穿戴设备的个性化生理数据的智能体贝叶斯实验设计
The Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables
AI总结:
提出智能体系统EpiCoach,将运动员作为N-of-1科学对象,用数字孪生模型做预测,通过约束实验最大化信息增益,可实现可审计的个性化健康管理。
摘要:
用于个人健康的大语言模型(LLM)智能体可读取可穿戴设备数据并给出建议,但无法以可审计或可证伪的方式了解个体情况。我们提出EpiCoach,这是一个智能体系统,将一名越野山地自行车运动员作为可问责的N-of-1科学研究对象。关于该运动员的主张存储在证据门控假说注册库中:每个主张必须在未来训练 session 开始前给出概率预测,其信念仅通过记录的统计拟合得出的证据更新。预测来自从心率、GPS和气压高度推断出的机械数字孪生模型:包括滞后心率响应模型、带有学习时间常数的 fitness-fatigue 模型,以及在发现的赛道路段上测量的潜在技术下坡技能状态。该智能体将下一个训练周规定为受负荷和安全约束的约束实验,围绕两次仪器骑行最大化信息增益。我们通过18个月的数据以两种方式评估该系统。滚动原点重放基准测试显示,该孪生模型在心率预测上优于标准预测器,但在路段时间预测上不占优势,且智能体循环与静态模型表现相当。实时前瞻性阶段运行每周循环:在前三周中,注册库封存了20个预测,评分14分,下坡预测在一次修正后校准,随着运动员进步,上坡预测偏悲观,安全官员两次否决了智能体。每次修正都保留在注册库中,这是数字健康中可审计、可证伪的个性化模板。我们发布该注册库、基准测试和协议。
英文摘要:
Large language model (LLM) agents for personal health read wearable data and recommend, but do not learn about the individual in a way that can be audited or falsified. We present EpiCoach, an agentic system that treats one athlete, a cross-country mountain biker, as the subject of accountable N-of-1 science. Claims about the athlete live in an evidence-gated hypothesis registry: each must issue a probabilistic prediction about a future session before it occurs, and its belief moves only through computed evidence from a logged statistical fit. Predictions come from a mechanistic digital twin inferred from heart rate, GPS and barometric altitude: a lagged heart-rate response model, a fitness-fatigue model with learned time constants, and a latent technical-descending skill state, measured on discovered trail segments. The agent prescribes the next training week as a constrained experiment maximizing information gain subject to load and safety constraints, around two instrument rides. We evaluate the system two ways over eighteen months of data. A rolling-origin replay benchmark shows the twin beats standard forecasters on heart rate but not segment time, and the agentic loop matches a static model. A live prospective phase runs the weekly cycle: in its first three weeks the ledger sealed 20 predictions, scored 14, the descent forecast calibrated after one correction, the climb forecast pessimistic as the athlete improved, and the safety officer vetoed the agent twice. Every correction is preserved in the registry, a template for auditable, falsifiable personalization in digital health. We release the registry, benchmark and protocol.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。