Textual Data Augmentation for Patient Outcomes Prediction
This addresses data scarcity in healthcare AI for patient outcomes prediction, but it is incremental as it adapts existing methods to a specific domain.
The authors tackled the problem of limited high-quality training data in healthcare by proposing a textual data augmentation method using GPT-2 to generate artificial clinical notes, which improved predictive performance for 30-day readmission rate prediction.
Deep learning models have demonstrated superior performance in various healthcare applications. However, the major limitation of these deep models is usually the lack of high-quality training data due to the private and sensitive nature of this field. In this study, we propose a novel textual data augmentation method to generate artificial clinical notes in patients' Electronic Health Records (EHRs) that can be used as additional training data for patient outcomes prediction. Essentially, we fine-tune the generative language model GPT-2 to synthesize labeled text with the original training data. More specifically, We propose a teacher-student framework where we first pre-train a teacher model on the original data, and then train a student model on the GPT-augmented data under the guidance of the teacher. We evaluate our method on the most common patient outcome, i.e., the 30-day readmission rate. The experimental results show that deep models can improve their predictive performance with the augmented data, indicating the effectiveness of the proposed architecture.