Unifying Heterogeneous Electronic Health Records Systems via Text-Based Code Embedding
This addresses the barrier of EHR format heterogeneity for predictive healthcare research, enabling broader application of deep learning models without constraints from EHR structure or domain knowledge.
The authors tackled the problem of heterogeneous Electronic Health Records (EHR) systems lacking unified code systems, which hinders deep learning model deployment, by introducing DescEmb, a text-based code-agnostic framework that outperformed code-based approaches in prediction tasks, transfer learning, and pooled learning.
Substantial increase in the use of Electronic Health Records (EHRs) has opened new frontiers for predictive healthcare. However, while EHR systems are nearly ubiquitous, they lack a unified code system for representing medical concepts. Heterogeneous formats of EHR present a substantial barrier for the training and deployment of state-of-the-art deep learning models at scale. To overcome this problem, we introduce Description-based Embedding, DescEmb, a code-agnostic description-based representation learning framework for predictive modeling on EHR. DescEmb takes advantage of the flexibility of neural language understanding models while maintaining a neutral approach that can be combined with prior frameworks for task-specific representation learning or predictive modeling. We tested our model's capacity on various experiments including prediction tasks, transfer learning and pooled learning. DescEmb shows higher performance in overall experiments compared to code-based approach, opening the door to a text-based approach in predictive healthcare research that is not constrained by EHR structure nor special domain knowledge.