归因Cohen's d：规范年龄生物标志物中疾病相关效应的训练数据归因

中文摘要 AI 辅助

规范年龄模型在名义上健康的队列中训练，用于预测实际年龄。应用于患者时，模型预测会产生偏差，预测年龄与实际年龄之间的差距被解读为疾病风险。在此，我们直接将年龄差距的疾病相关效应量归因于个体训练样本，而非使用预测级别的损失作为归因目标。对于Cohen's d，所得到的闭式影响函数（已通过留一法重训练验证）根据训练样本对留出病例-对照分离的影响对其进行排序。在英国生物银行（UK Biobank）的四种疾病和两种生物标志物模态中，移除最具影响力的前10%训练样本，在每个随机种子下均提高了留出疾病相关效应量。该方法使2型糖尿病的代谢组学年龄效应提高了一倍以上，并使多发性硬化症的脑年龄效应提高了约三分之一。随机移除即使在移除50%样本时也使效应量保持不变，这证实了增益来自被移除的样本本身，而非移除的数量。被标记的受试者携带亚临床心脏代谢负担，这是基于诊断的排除法所遗漏的，且这些标志物是模型从未见过的。对于该方法获益最大的2型糖尿病，所恢复的标志物是HbA1c，即血糖控制的标准测量指标。我们发布了pyinfluence（我们的影响函数软件包），以供可重复性和复用。

英文摘要

Normative age models are trained to predict chronological age in a nominally healthy cohort. Applied to patients, they deviate, and the gap between predicted and chronological age is read as disease risk. Here, we attribute the disease-related effect size of the age gap directly to individual training samples, rather than using a prediction-level loss as the attribution target. For Cohen's $d$, the resulting closed-form influence functional, validated against leave-one-out retraining, ranks training samples by their effect on held-out case-control separation. Across four diseases and two biomarker modalities in UK Biobank, removing the 10% most influential training samples raises held-out disease-related effect size in every seed. It more than doubles the metabolomic-age effect for type-2 diabetes and raises the brain-age effect for multiple sclerosis by roughly a third. Random removal leaves effect size flat even at 50% removal, confirming the gain comes from which samples are removed, not how many. Flagged subjects carry subclinical cardiometabolic burden that diagnosis-based exclusion misses, on markers the model never sees. For type-2 diabetes, where the method gains most, the marker recovered is HbA1c, the standard measure of blood sugar control. We release pyinfluence, our influence-function package, for reproducibility and reuse.

发表机构

• Hertie Institute for AI in Brain Health（赫蒂脑健康人工智能研究所）
• University of Tübingen（蒂宾根大学）
• Tübingen AI Center（蒂宾根人工智能中心）
• Charité – Universitätsmedizin Berlin（柏林夏里特医学院）
• German Center for Mental Health (DZPG)（德国心理健康中心（DZPG））

机构由 AI 辅助整理，请以论文原文为准。