用Transformer分析患者长期病历，预测心衰患者三年死亡率，效果优于传统模型。
A Transformer-based survival model for prediction of all-cause mortality in heart failure patients: a multi-cohort study
- 基于英国电子病历构建Transformer模型，捕捉患者长期健康轨迹。
- 36个月死亡率预测C-index达0.845，显著高于对比模型的0.728。
- 识别出癌症、肝衰竭等被忽视的预后因子，适合临床风险评估使用。
我们开发并验证了TRisk——一种基于Transformer的AI模型，通过分析英国电子健康记录（EHR）中的时间序列患者病历，预测心衰患者的36个月全因死亡率。研究纳入1,418家英格兰全科诊所的403,534名心衰患者（年龄40-90岁），其中1,063家用于模型构建，355家用于外部验证。在多个患者亚组中，TRisk与MAGGIC-EHR模型进行比较。中位随访9个月，TRisk的协和指数（C-index）为0.845（95%置信区间：[0.841, 0.849]），显著优于MAGGIC-EHR的0.728（0.723, 0.733）。TRisk在性别、年龄及基线特征上表现更一致，提示偏差更小。通过迁移学习，我们成功将TRisk应用于美国医院数据，涵盖21,767名患者，取得C-index 0.802（0.789, 0.816）。可解释性分析显示，TRisk捕捉到已知风险因素，并识别出癌症和肝衰竭等被低估的预测因子，且癌症即使在诊断十年后仍具强预后价值。TRisk在两种医疗体系下均表现出良好校准性。研究结果凸显追踪纵向健康数据的价值，并揭示了以往专家模型未包含的风险因素。
原文摘要 · Abstract (English)
We developed and validated TRisk, a Transformer-based AI model predicting 36-month mortality in heart failure patients by analysing temporal patient journeys from UK electronic health records (EHR). Our study included 403,534 heart failure patients (ages 40-90) from 1,418 English general practices, with 1,063 practices for model derivation and 355 for external validation. TRisk was compared against the MAGGIC-EHR model across various patient subgroups. With median follow-up of 9 months, TRisk achieved a concordance index of 0.845 (95% confidence interval: [0.841, 0.849]), significantly outperforming MAGGIC-EHR's 0.728 (0.723, 0.733) for predicting 36-month all-cause mortality. TRisk showed more consistent performance across sex, age, and baseline characteristics, suggesting less bias. We successfully adapted TRisk to US hospital data through transfer learning, achieving a C-index of 0.802 (0.789, 0.816) with 21,767 patients. Explainability analyses revealed TRisk captured established risk factors while identifying underappreciated predictors like cancers and hepatic failure that were important across both cohorts. Notably, cancers maintained strong prognostic value even a decade after diagnosis. TRisk demonstrated well-calibrated mortality prediction across both healthcare systems. Our findings highlight the value of tracking longitudinal health profiles and revealed risk factors not included in previous expert-driven models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。