TRACER：基于 450 万患者 EHR 的疾病预测基础模型
TRACER, a time-to-event EHR foundation model for disease detection across health systems
一篇值得看细节的论文：TRACER 用 450 万患者的病历训练，能在 1-5 年前预测 16 种疾病，还专门测了筛查场景下的误报负担。
研究者开发了 TRACER（Temporal Risk Assessment with Clinical EHR Representations），一个基于 decoder 架构、在 4 个医疗系统超 450 万患者纵向电子病历上预训练的时序风险模型。模型在 2 个未参与训练的医疗系统、超 200 万患者上评测 16 种疾病的 1、2、5 年发病预测。在 95% 特异度下，被 TRACER 标记的患者一年内确诊概率是未筛查人群的最多 8 倍。评测还发现，仅看 AUROC 等全局指标会掩盖各疾病和各系统间漏检率与误报负担的差异。
TRACER, a time-to-event EHR foundation model for disease detection across health systems
Foundation models trained on longitudinal electronic health records (EHRs) can predict clinical diagnoses years in the future, making them a potential tool for disease screening. We developed TRACER (Temporal Risk Assessment with Clinical EHR Representations), a decoder-based foundation model pretrained on data from over 4.5 million patients from four health systems, and evaluated it on 16 incident diseases at 1-, 2-, and 5-year horizons in more than 2 million patients from two health systems excluded from model development. In contrast to typical evaluations that focus on global metrics (e.g., AUROC), we measured performance at the low false-positive rates that are realistic for screening. We found that TRACER retained its discrimination in external health systems, and at 95% specificity, the patients it flagged were up to eight times more likely to be diagnosed within a year than unselected patients. Evaluating at this operating point also revealed what global metrics alone did not: detection and false-alert burden varied across diseases and health systems, even when discrimination appeared stable. Our results illustrate the potential of foundation models for screening and underscore the need for evaluation in health systems excluded from development to assess disease detection and false-alert burden at levels appropriate for intended clinical use.}
