Data augmentation method for modeling health records with applications to clopidogrel treatment failure detection
This addresses the problem of limited labeled data for healthcare professionals and researchers in EHR analysis, though it is incremental as it builds on existing NLP methods.
The paper tackled data scarcity in modeling longitudinal patterns in Electronic Health Records by proposing a novel data augmentation method that rearranges medical record orders within visits, resulting in up to a 5.3% absolute improvement in ROC-AUC for clopidogrel treatment failure detection.
We present a novel data augmentation method to address the challenge of data scarcity in modeling longitudinal patterns in Electronic Health Records (EHR) of patients using natural language processing (NLP) algorithms. The proposed method generates augmented data by rearranging the orders of medical records within a visit where the order of elements are not obvious, if any. Applying the proposed method to the clopidogrel treatment failure detection task enabled up to 5.3% absolute improvement in terms of ROC-AUC (from 0.908 without augmentation to 0.961 with augmentation) when it was used during the pre-training procedure. It was also shown that the augmentation helped to improve performance during fine-tuning procedures, especially when the amount of labeled training data is limited.