← 研踪 PaperTrailarXiv:2609.07729 · v3
Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers
首次提交 2026-09-08 00:37
版本更新 2026-11-13 07:20
雷达观测 2026-11-17 04:58
摘要
Normative age models are trained to predict chronological age in a nominally healthy cohort. In patients, the gap between predicted and chronological age is read as disease risk. 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 the Cohen's d effect size, 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, missed by diagnosis-based exclusion, show elevated cardiometabolic markers the model never sees, consistent with subclinical contamination of the reference cohort. For type 2 diabetes, where the method gains most, the marker recovered is HbA1c, the standard measure of blood sugar control. We release our influence-function package pyinfluence.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-13 07:20 · 最新观测版本
Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers
Normative age models are trained to predict chronological age in a nominally healthy cohort. In patients, the gap between predicted and chronological age is read as disease risk. 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 the Cohen's d effect size, 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, missed by diagnosis-based exclusion, show elevated cardiometabolic markers the model never sees, consistent with subclinical contamination of the reference cohort. For type 2 diabetes, where the method gains most, the marker recovered is HbA1c, the standard measure of blood sugar control. We release our influence-function package pyinfluence.
查看此版本解读 →查看此版本原文 ↗