Dialysis Risk Prediction and Treatment Effect Estimation for AKI patients using Longitudinal Electronic Health Records

TL;DR

This study developed a transformer-based causal model to predict dialysis risk in AKI patients using longitudinal EHR data, providing insights into medication effects on renal outcomes.

Contribution

It introduces a novel transformer-based approach for estimating treatment effects from EHR sequences in AKI patients.

Findings

Predictive model achieved AUC of 0.694 for dialysis risk.

Causal analysis indicated ACE/ARB may be protective.

Loop diuretics associated with worsening renal outcomes.

Abstract

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.