Augmenting electronic health records for adverse event detection.

OBJECTIVE: Adverse events (AEs) resulting from medical interventions are significant contributors to patient morbidity, mortality, and healthcare costs. Detection of these events using electronic health records (EHRs) can facilitate timely clinical interventions. However, effective detection remains challenging due to severe class imbalance, missing labels, and the complexity of EHR records. Classical machine learning approaches frequently underperform due to insufficient representation of minority adverse event classes and limited capacity to capture interactions among patient demographics, administered medications, and associated complications. This study aims to develop and evaluate a lightweight, NLP-inspired data augmentation framework for structured EHR data that improves minority-class adverse event detection without requiring complex generative models or pre-trained clinical language models. METHODS: We introduce TASER-AE (Tokenized Augmentation for Structured EHR-Adverse Events), a novel data augmentation pipeline tailored for structured EHR data, coupled with transformer-based classification. TASER-AE addresses these issues through an NLP-inspired data augmentation framework adapted for EHR, enabling effective minority-class representation in sparse and imbalanced clinical datasets. The augmented records produced by TASER-AE alleviate class imbalance by enriching the representation of minority adverse event classes, which enhances the robustness and predictive performance of the classifier. RESULTS: TASER-AE yields minority-class F1 scores up to 0.67, substantially surpassing classical machine-learning baselines and generative augmentation, and consistently improving on prior edit-based augmentation methods, across multiple adverse event tasks. Experiments conducted on two distinct EHR datasets confirm TASER-AE's ability to substantially improve adverse event detection. CONCLUSION: These results demonstrate the potential of structured, NLP-inspired augmentation methods to overcome data limitations in clinical predictive modeling, ultimately contributing to improved patient safety outcomes. TASER-AE is available at https://github.com/Kingsford-Group/taserae.