Paper to Practice ·
用生成式 Transformer 学习人类疾病的自然史
Delphi-2M 把 GPT 架构用到了健康记录上：它在 402,799 名 UK Biobank 参与者上训练，读取一个人的诊断史，预测 1,256 种疾病和死亡的发生率与发生时间，并能模拟未来的健康轨迹。内部验证的平均 AUC 为 0.76，不重新训练直接用于丹麦 193 万人的登记数据时为 0.67。
Learning the natural history of human disease with generative transformers
Delphi-2M adapts the GPT architecture to health records: trained on 402,799 UK Biobank participants, it reads a person's diagnosis history, predicts the rates and timing of 1,256 diseases plus death, and can simulate future health trajectories. It reached an average AUC of 0.76 internally and 0.67 on 1.93 million Danish registry records without retraining.
