Progression to dialysis or end-stage renal disease is a rare but clinically important outcome. Clinicians need evidence on how medication exposures influence downstream risk. We constructed a fixed-window EHR cohort (90-day observation, 730-day prediction; N=81401; dialysis/ESRD prevalence: 1.1%) and modeled sequences of diagnoses, procedures, and medications with kidney laboratory trends (creatinine, BUN, eGFR). A transformer-based causal multi-head model was trained to estimate drug- and ingredient-level average treatment effects (ATEs) using counterfactual exposure removal and insertion under a full medication history setup. On test set, predictive performance reached an AUC of 0.694 and PR-AUC of 0.094. At the selected decision threshold (0.883), the model achieved an F1 score of 0.201 with a Brier score of 0.018. Post-hoc causal analyses of lab changes (eGFR, creatinine, BUN) using IPTW, AIPW, naive, and covariate-adjusted OLS methods assessed clinical directionality. Results showed partial protective-direction support for ACE/ARB exposures and worsening-direction signals for loop diuretics.

翻译：进展至透析或终末期肾病是罕见但临床重要的结局。临床医生需要了解药物暴露如何影响下游风险的证据。我们构建了一个固定窗口的电子健康记录队列（观察期90天，预测期730天；样本量81401例；透析/终末期肾病患病率：1.1%），并对诊断、手术和用药序列结合肾脏实验室指标趋势（肌酐、血尿素氮、估算肾小球滤过率）进行建模。基于Transformer的因果多头模型在完整用药史设置下，通过反事实暴露移除与插入方法，训练估计药物及成分水平的平均治疗效果（ATEs）。在测试集上，预测性能达到AUC为0.694，PR-AUC为0.094。在选定决策阈值（0.883）下，模型取得F1分数0.201，Brier分数0.018。采用IPTW、AIPW、朴素法和协变量调整OLS方法对实验室指标变化（eGFR、肌酐、BUN）的事后因果分析评估了临床方向性。结果显示ACE/ARB类暴露呈部分保护方向支持，而袢利尿剂暴露呈现恶化方向信号。